From cf0ef8814a249eecea9895d4031e33ea2406dcda Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Thu, 21 May 2020 13:18:34 -0500 Subject: [PATCH 1/7] upgrade to new format --- gdcdictionary/schemas/_definitions.yaml | 32 +- gdcdictionary/schemas/_settings.yaml | 6 - gdcdictionary/schemas/_terms.yaml | 1841 ----------------- gdcdictionary/schemas/acknowledgement.yaml | 61 - .../schemas/aligned_reads_index.yaml | 77 - gdcdictionary/schemas/aliquot.yaml | 103 - gdcdictionary/schemas/case.yaml | 71 - gdcdictionary/schemas/clinical_test.yaml | 242 --- .../schemas/core_metadata_collection.yaml | 113 - gdcdictionary/schemas/demographic.yaml | 114 - gdcdictionary/schemas/diagnosis.yaml | 844 -------- gdcdictionary/schemas/experiment.yaml | 108 - .../schemas/experimental_metadata.yaml | 77 - gdcdictionary/schemas/exposure.yaml | 132 -- gdcdictionary/schemas/family_history.yaml | 98 - gdcdictionary/schemas/keyword.yaml | 61 - gdcdictionary/schemas/program.yaml | 41 - gdcdictionary/schemas/project.yaml | 147 -- gdcdictionary/schemas/projects/project1.yaml | 21 - gdcdictionary/schemas/publication.yaml | 62 - gdcdictionary/schemas/read_group.yaml | 225 -- gdcdictionary/schemas/read_group_qc.yaml | 133 -- gdcdictionary/schemas/sample.yaml | 686 ------ gdcdictionary/schemas/slide.yaml | 138 -- gdcdictionary/schemas/slide_count.yaml | 100 - gdcdictionary/schemas/slide_image.yaml | 109 - .../schemas/submitted_aligned_reads.yaml | 95 - .../schemas/submitted_copy_number.yaml | 91 - .../schemas/submitted_methylation.yaml | 86 - .../schemas/submitted_somatic_mutation.yaml | 83 - .../schemas/submitted_unaligned_reads.yaml | 92 - gdcdictionary/schemas/treatment.yaml | 217 -- 32 files changed, 16 insertions(+), 6290 deletions(-) delete mode 100644 gdcdictionary/schemas/_settings.yaml delete mode 100644 gdcdictionary/schemas/_terms.yaml delete mode 100644 gdcdictionary/schemas/acknowledgement.yaml delete mode 100644 gdcdictionary/schemas/aligned_reads_index.yaml delete mode 100644 gdcdictionary/schemas/aliquot.yaml delete mode 100644 gdcdictionary/schemas/case.yaml delete mode 100644 gdcdictionary/schemas/clinical_test.yaml delete mode 100644 gdcdictionary/schemas/core_metadata_collection.yaml delete mode 100644 gdcdictionary/schemas/demographic.yaml delete mode 100644 gdcdictionary/schemas/diagnosis.yaml delete mode 100644 gdcdictionary/schemas/experiment.yaml delete mode 100644 gdcdictionary/schemas/experimental_metadata.yaml delete mode 100644 gdcdictionary/schemas/exposure.yaml delete mode 100644 gdcdictionary/schemas/family_history.yaml delete mode 100644 gdcdictionary/schemas/keyword.yaml delete mode 100644 gdcdictionary/schemas/program.yaml delete mode 100644 gdcdictionary/schemas/project.yaml delete mode 100644 gdcdictionary/schemas/projects/project1.yaml delete mode 100644 gdcdictionary/schemas/publication.yaml delete mode 100644 gdcdictionary/schemas/read_group.yaml delete mode 100644 gdcdictionary/schemas/read_group_qc.yaml delete mode 100644 gdcdictionary/schemas/sample.yaml delete mode 100644 gdcdictionary/schemas/slide.yaml delete mode 100644 gdcdictionary/schemas/slide_count.yaml delete mode 100644 gdcdictionary/schemas/slide_image.yaml delete mode 100644 gdcdictionary/schemas/submitted_aligned_reads.yaml delete mode 100644 gdcdictionary/schemas/submitted_copy_number.yaml delete mode 100644 gdcdictionary/schemas/submitted_methylation.yaml delete mode 100644 gdcdictionary/schemas/submitted_somatic_mutation.yaml delete mode 100644 gdcdictionary/schemas/submitted_unaligned_reads.yaml delete mode 100644 gdcdictionary/schemas/treatment.yaml diff --git a/gdcdictionary/schemas/_definitions.yaml b/gdcdictionary/schemas/_definitions.yaml index bd91b5fdc..5208c6360 100644 --- a/gdcdictionary/schemas/_definitions.yaml +++ b/gdcdictionary/schemas/_definitions.yaml @@ -1,8 +1,8 @@ id: _definitions -UUID: +uuid: term: - $ref: "_terms.yaml#/UUID" + $ref: "_terms.yaml#/uuid" type: string pattern: "^[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}$" @@ -10,7 +10,7 @@ parent_uuids: type: array minItems: 1 items: - $ref: "#/UUID" + $ref: "#/uuid" uniqueItems: true foreign_key_project: @@ -18,11 +18,11 @@ foreign_key_project: # Allow true here because we can have other unique keys defined on # a target type additionalProperties: true - # Can either use 'id' which are Gen3 IDs (UUID) or 'code' + # Can either use 'id' which are Gen3 IDs (uuid) or 'code' # which is the user defined ID for project properties: id: - $ref: "#/UUID" + $ref: "#/uuid" code: type: string @@ -48,11 +48,11 @@ foreign_key: # Allow true here because we can have other unique keys defined on # a target type additionalProperties: True - # Can either use 'id' which are GDC IDs (UUID) or 'submitter_id' + # Can either use 'id' which are GDC IDs (uuid) or 'submitter_id' # which are user defined IDs ("submitter IDs in the backend") properties: id: - $ref: "#/UUID" + $ref: "#/uuid" submitter_id: type: string @@ -88,7 +88,7 @@ file_name: file_size: type: integer - term: + term: $ref: "_terms.yaml#/file_size" file_format: @@ -135,7 +135,7 @@ data_file_error_type: state: term: - $ref: "_terms.yaml#/state" + $ref: "_terms.yaml#/state" default: validated downloadable: - uploaded @@ -166,7 +166,7 @@ state: file_state: term: - $ref: "_terms.yaml#/file_state" + $ref: "_terms.yaml#/file_state" default: registered enum: - registered @@ -195,7 +195,7 @@ project_id: data_file_properties: id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: @@ -211,7 +211,7 @@ data_file_properties: file_size: $ref: "#/file_size" md5sum: - $ref: "#/md5sum" + $ref: "#/md5sum" file_state: $ref: "#/file_state" object_id: @@ -222,7 +222,7 @@ data_file_properties: $ref: "#/data_file_error_type" state_comment: type: string - description: > + description: > Optional comment about why the file is in the current state, mainly for invalid state. project_id: @@ -234,7 +234,7 @@ data_file_properties: workflow_properties: id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: @@ -264,14 +264,14 @@ ubiquitous_properties: type: type: string id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: - string description: > A project-specific identifier for a node. This property is the calling card/nickname/alias for - a unit of submission. It can be used in place of the UUID for identifying or recalling a node. + a unit of submission. It can be used in place of the uuid for identifying or recalling a node. state: $ref: "#/state" project_id: diff --git a/gdcdictionary/schemas/_settings.yaml b/gdcdictionary/schemas/_settings.yaml deleted file mode 100644 index d7e2171a4..000000000 --- a/gdcdictionary/schemas/_settings.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Global settings for the graph - -# Is the graph case centric, that we want -# to create a link between all children to case -# to expedite case filter on nodes -enable_case_cache: false diff --git a/gdcdictionary/schemas/_terms.yaml b/gdcdictionary/schemas/_terms.yaml deleted file mode 100644 index 0ca296bac..000000000 --- a/gdcdictionary/schemas/_terms.yaml +++ /dev/null @@ -1,1841 +0,0 @@ -id: _terms - -28s_16s_ribosomal_rna_ratio: - description: > - The 28S/18S ribosomal RNA band ratio used to assess the quality of total RNA. - termDef: - term: "28s/18s Ribosomal RNA Ratio" - source: null - cde_id: null - cde_version: null - term_url: null - -a260_a280_ratio: - description: > - Numeric value that represents the sample ratio of nucleic acid absorbance at 260 nm and 280 nm, - used to determine a measure of DNA purity. - termDef: - term: Nucleic Acid Absorbance at 260 And Absorbance at 280 DNA Purity Ratio Value - source: caDSR - cde_id: 5432595 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432595&version=1.0" - -adapter_name: # TOREVIEW - description: > - Name of the sequencing adapter. - -adapter_sequence: # TOREVIEW - description: > - Base sequence of the sequencing adapter. - -age_at_diagnosis: - description: > - Age at the time of diagnosis expressed in number of days since birth. - termDef: - term: Patient Diagnosis Age Day Value - source: caDSR - cde_id: 3225640 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225640&version=2.0" - -ajcc_clinical_m: - description: > - Extent of the distant metastasis for the cancer based on evidence obtained from clinical - assessment parameters determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Distant Metastasis M Stage - source: caDSR - cde_id: 3440331 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440331&version=1.0" - -ajcc_clinical_n: - description: > - Extent of the regional lymph node involvement for the cancer based on evidence obtained from - clinical assessment parameters determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Regional Lymph Node N Stage - source: caDSR - cde_id: 3440330 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440330&version=1.0" - -ajcc_clinical_stage: - description: > - Stage group determined from clinical information on the tumor (T), regional node (N) and - metastases (M) and by grouping cases with similar prognosis for cancer. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Group Stage - source: caDSR - cde_id: 3440332 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440332&version=1.0" - -ajcc_clinical_t: - description: > - Extent of the primary cancer based on evidence obtained from clinical assessment parameters - determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Primary Tumor T Stage - source: caDSR - cde_id: 3440328 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440328&version=1.0" - -ajcc_pathologic_m: - description: > - Code to represent the defined absence or presence of distant spread or metastases (M) to - locations via vascular channels or lymphatics beyond the regional lymph nodes, using - criteria established by the American Joint Committee on Cancer (AJCC). - termDef: - term: American Joint Committee on Cancer Metastasis Stage Code - source: caDSR - cde_id: 3045439 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045439&version=1.0" - -ajcc_pathologic_n: - description: > - The codes that represent the stage of cancer based on the nodes present (N stage) according - to criteria based on multiple editions of the AJCC's Cancer Staging Manual. - termDef: - term: Neoplasm Disease Lymph Node Stage American Joint Committee on Cancer Code - source: caDSR - cde_id: 3203106 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203106&version=1.0" - -ajcc_pathologic_stage: - description: > - The extent of a cancer, especially whether the disease has spread from the original site to - other parts of the body based on AJCC staging criteria. - termDef: - term: Neoplasm Disease Stage American Joint Committee on Cancer Code - source: caDSR - cde_id: 3203222 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203222&version=1.0" - -ajcc_pathologic_t: - description: > - Code of pathological T (primary tumor) to define the size or contiguous extension of the - primary tumor (T), using staging criteria from the American Joint Committee on Cancer - (AJCC). - termDef: - term: American Joint Committee on Cancer Tumor Stage Code - source: caDSR - cde_id: 3045435 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045435&version=1.0" - -alcohol_history: - description: > - A response to a question that asks whether the participant has consumed at least 12 drinks of - any kind of alcoholic beverage in their lifetime. - termDef: - term: Alcohol Lifetime History Indicator - source: caDSR - cde_id: 2201918 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2201918&version=1.0" - -alcohol_intensity: - description: > - Category to describe the patient's current level of alcohol use as self-reported by the patient. - termDef: - term: Person Self-Report Alcoholic Beverage Exposure Category - source: caDSR - cde_id: 3457767 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3457767&version=1.0" - -aliquot_quantity: - description: > - The quantity in micrograms (ug) of the aliquot(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Aliquot Quantity - source: null - cde_id: null - cde_version: null - term_url: null - -aliquot_volume: - description: > - The volume in microliters (ml) of the aliquot(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Aliquot Volume - source: null - cde_id: null - cde_version: null - term_url: null - -amount: # TOREVIEW - description: > - Weight in grams or volume in mL. - -analyte_quantity: - description: > - The quantity in micrograms (ug) of the analyte(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Analyte Quantity - source: null - cde_id: null - cde_version: null - term_url: null - -analyte_type: - description: > - Text term that represents the kind of molecular specimen analyte. - termDef: - term: Molecular Specimen Type Text Name - source: caDSR - cde_id: 2513915 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2513915&version=2.0" - -analyte_type_id: - description: > - A single letter code used to identify a type of molecular analyte. - termDef: - term: Molecular Analyte Identification Code - source: caDSR - cde_id: 5432508 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432508&version=1.0" - -analyte_volume: - description: > - The volume in microliters (ml) of the analyte(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Analyte Volume - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_b_symptoms: - description: > - Text term to signify whether lymphoma B-symptoms are present as noted in the patient's medical - record. - termDef: - term: Lymphoma B-Symptoms Medical Record Documented Indicator - source: caDSR - cde_id: 2902402 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2902402&version=1.0" - -ann_arbor_clinical_stage: - description: > - The classification of the clinically confirmed anatomic disease extent of lymphoma (Hodgkin's - and Non-Hodgkins) based on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Clinical Stage - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_extranodal_involvement: - description: > - Indicator that identifies whether a patient with malignant lymphoma has lymphomatous involvement - of an extranodal site. - termDef: - term: Lymphomatous Extranodal Site Involvement Indicator - source: caDSR - cde_id: 3364582 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3364582&version=1.0" - -ann_arbor_pathologic_stage: - description: > - The classification of the pathologically confirmed anatomic disease extent of lymphoma - (Hodgkin's and Non-Hodgkins) based on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Pathologic Stage - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_tumor_stage: - description: > - The classification of the anatomic disease extent of lymphoma (Hodgkin's and Non-Hodgkins) based - on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Tumor Stage - source: null - cde_id: null - cde_version: null - term_url: null - -base_caller_name: # TOREVIEW - description: > - Name of the base caller. - -base_caller_version: # TOREVIEW - description: > - Version of the base caller. - -biomarker_name: - description: > - The name of the biomarker being tested for this specimen and set of test results. - termDef: - term: Biomarker Name - source: caDSR - cde_id: 5473 - cde_version: 11.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5473&version=2.31" - -biomarker_result: - description: > - Text term to define the results of genetic testing. - termDef: - term: Laboratory Procedure Genetic Abnormality Test Result Type - source: caDSR - cde_id: 3234680 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3234680&version=1.0" - -biomarker_test_method: - description: > - Text descriptor of a molecular analysis method used for an individual. - termDef: - term: Disease Detection Molecular Analysis Method Type - source: caDSR - cde_id: 3121575 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121575&version=1.0" - -biospecimen_anatomic_site: - description: > - Text term that represents the name of the primary disease site of the submitted tumor sample. - termDef: - term: Submitted Tumor Sample Primary Anatomic Site - source: caDSR - cde_id: 4742851 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4742851&version=1.0" - -bmi: - description: > - The body mass divided by the square of the body height expressed in units of kg/m^2. - termDef: - term: Body Mass Index (BMI) - source: caDSR - cde_id: 4973892 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4973892&version=1.0" - -burkitt_lymphoma_clinical_variant: - description: > - Burkitt's lymphoma categorization based on clinical features that differ from other forms of the - same disease. - termDef: - term: Burkitt Lymphoma Clinical Variant Type - source: caDSR - cde_id: 3770421 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3770421&version=1.0" - -cause_of_death: - description: > - Text term to identify the cause of death for a patient. - termDef: - term: Patient Death Reason - source: caDSR - cde_id: 2554674 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2554674&version=3.0" - -cea_level_preoperative: - description: > - Numeric value of the Carcinoembryonic antigen or CEA at the time before surgery. [Manually- - curated] - termDef: - term: Preoperative Carcinoembryonic Antigen Result Value - source: caDSR - cde_id: 2716510 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2716510&version=1.0" - -cigarettes_per_day: - description: > - The average number of cigarettes smoked per day. - termDef: - term: Smoking Use Average Number - source: caDSR - cde_id: 2001716 - cde_version: 4.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2001716&version=4.0" - -circumferential_resection_margin: - description: > - A value in millimeters indicating the measured length between a malignant lesion of the - colon or rectum and the nearest radial (or circumferential) border of tissue removed during - cancer surgery. - termDef: - term: Colorectal Surgical Margin Circumferential Distance Measurement - source: caDSR - cde_id: 64202 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64202&version=3.0" - -classification_of_tumor: - description: > - Text that describes the kind of disease present in the tumor specimen as related to a specific - timepoint. - termDef: - term: Tumor Tissue Disease Description Type - source: caDSR - cde_id: 3288124 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" - -colon_polyps_history: - description: > - Yes/No indicator to describe if the subject had a previous history of colon polyps as noted - in the history/physical or previous endoscopic report (s). - termDef: - term: Colon Carcinoma Polyp Occurrence Indicator - source: caDSR - cde_id: 3107197 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3107197&version=1.0" - -composition: - description: > - Text term that represents the cellular composition of the sample. - termDef: - term: Biospecimen Cellular Composition Type - source: caDSR - cde_id: 5432591 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432591&version=1.0" - -concentration: - description: > - Numeric value that represents the concentration of an analyte or aliquot extracted from the - sample or sample portion, measured in milligrams per milliliter. - termDef: - term: Biospecimen Analyte or Aliquot Extracted Concentration Milligram per Milliliter Value - source: caDSR - cde_id: 5432594 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432594&version=1.0" - -creation_datetime: - description: > - The datetime of portion creation encoded as seconds from epoch. - termDef: - term: Biospecimen Portion Creation Seconds Date/Time - source: caDSR - cde_id: 5432592 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432592&version=1.0" - -current_weight: - description: > - Numeric value that represents the current weight of the sample, measured in milligrams. - termDef: - term: Tissue Sample Current Weight Milligram Value - source: caDSR - cde_id: 5432606 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432606&version=1.0" - -data_category: # TOREVIEW - description: > - Broad categorization of the contents of the data file. - -data_file_error_type: # TOREVIEW - description: > - Type of error for the data file object. - -data_format: # TOREVIEW - description: > - Format of the data files. - -data_type: # TOREVIEW - description: > - Specific content type of the data file. - -datetime: - description: > - A combination of date and time of day in the form [-]CCYY-MM-DDThh:mm:ss[Z|(+|-)hh:mm] - -days_to_birth: - description: > - Time interval from a person's date of birth to the date of initial pathologic diagnosis, - represented as a calculated negative number of days. - termDef: - term: Person Birth Date Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008233 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008233&version=1.0" - -days_to_collection: - description: > - Time interval from the date of biospecimen collection to the date of initial pathologic - diagnosis, represented as a calculated number of days. - termDef: - term: Biospecimen Collection Date Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008340 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008340&version=1.0" - -days_to_death: - description: > - Time interval from a person's date of death to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Death Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3165475 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3165475&version=1.0" - -days_to_hiv_diagnosis: - description: > - Time interval from the date of the initial pathologic diagnosis to the date of human - immunodeficiency diagnosis, represented as a calculated number of days. - termDef: - term: Human Immunodeficiency Virus Diagnosis Subtract Initial Pathologic Diagnosis Time Duration Day Calculation Value - source: caDSR - cde_id: 4618491 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4618491&version=1.0" - -days_to_last_follow_up: - description: > - Time interval from the date of last follow up to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008273 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" - -days_to_last_known_disease_status: - description: > - Time interval from the date of last follow up to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008273 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" - -days_to_new_event: - description: > - Time interval from the date of new tumor event including progression, recurrence and new - primary malignacies to the date of initial pathologic diagnosis, represented as a calculated - number of days. - termDef: - term: New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3392464 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" - -days_to_recurrence: - description: > - Time interval from the date of new tumor event including progression, recurrence and new primary - malignancies to the date of initial pathologic diagnosis, represented as a calculated number of - days. - termDef: - term: New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3392464 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" - -days_to_sample_procurement: - description: > - The number of days from the date the patient was diagnosed to the date of the procedure that - produced the sample. - -days_to_treatment: - description: > - Number of days from date of initial pathologic diagnosis that treatment began. - termDef: - term: Days to Treatment Start - source: null - cde_id: null - cde_version: null - term_url: null - -days_to_treatment_end: - description: > - Time interval from the date of the initial pathologic diagnosis to the date of treatment end, - represented as a calculated number of days. - termDef: - term: Treatment End Subtract First Pathologic Diagnosis Day Calculation Value - source: caDSR - cde_id: 5102431 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102431&version=1.0" - -days_to_treatment_start: - description: > - Time interval from the date of the initial pathologic diagnosis to the start of treatment, - represented as a calculated number of days. - termDef: - term: Treatment Start Subtract First Pathologic Diagnosis Time Day Calculation Value - source: caDSR - cde_id: 5102411 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102411&version=1.0" - -diagnosis_pathologically_confirmed: - description: > - The histologic description of tissue or cells confirmed by a pathology review of frozen or - formalin fixed slide(s) completed after the diagnostic pathology review of the tumor sample used - to extract analyte(s). - termDef: - term: Post-Diagnostic Pathology Review Confirmation - source: null - cde_id: null - cde_version: null - term_url: null - -dlco_ref_predictive_percent: - description: > - The value, as a percentage of predicted lung volume, measuring the amount of carbon monoxide - detected in a patient's lungs. - termDef: - term: Lung Carbon Monoxide Diffusing Capability Test Assessment Predictive Value Percentage Value - source: caDSR - cde_id: 2180255 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2180255&version=1.0" - -encoding: - description: > - Version of ASCII encoding of quality values found in the file. - termDef: - term: Encoding - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -estrogen_receptor_percent_positive_ihc: - description: > - Classification to represent ER Positive results expressed as a percentage value. - termDef: - term: ER Level Cell Percentage Category - source: caDSR - cde_id: 3128341 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128341&version=1.0" - -estrogen_receptor_result_ihc: - description: > - Text term to represent the overall result of Estrogen Receptor (ER) testing. - termDef: - term: Breast Carcinoma Estrogen Receptor Status - source: caDSR - cde_id: 2957359 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957359&version=2.0" - -ethnicity: - description: > - An individual's self-described social and cultural grouping, specifically whether an individual - describes themselves as Hispanic or Latino. The provided values are based on the categories - defined by the U.S. Office of Management and Business and used by the U.S. Census Bureau. - termDef: - term: Ethnic Group Category Text - source: caDSR - cde_id: 2192217 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192217&version=2.0" - -experiment_name: # TOREVIEW - description: > - Submitter-defined name for the experiment. - -experimental_strategy: # TOREVIEW - description: > - The sequencing strategy used to generate the data file. - -fastq_name: # TOREVIEW - description: > - Names of FASTQs. - -fev1_ref_post_bronch_percent: - description: > - The percentage comparison to a normal value reference range of the volume of air that a - patient can forcibly exhale from the lungs in one second post-bronchodilator. - termDef: - term: Post Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value - source: caDSR - cde_id: 3302948 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302948&version=1.0" - -fev1_ref_pre_bronch_percent: - description: > - The percentage comparison to a normal value reference range of the volume of air that a - patient can forcibly exhale from the lungs in one second pre-bronchodilator. - termDef: - term: Pre Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value - source: caDSR - cde_id: 3302947 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302947&version=1.0" - -fev1_fvc_post_bronch_percent: - description: > - Percentage value to represent result of Forced Expiratory Volume in 1 second (FEV1) divided - by the Forced Vital Capacity (FVC) post-bronchodilator. - termDef: - term: Post Bronchodilator FEV1/FVC Percent Value - source: caDSR - cde_id: 3302956 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302956&version=1.0" - -fev1_fvc_pre_bronch_percent: - description: > - Percentage value to represent result of Forced Expiratory Volume in 1 second (FEV1) divided - by the Forced Vital Capacity (FVC) pre-bronchodilator. - termDef: - term: Pre Bronchodilator FEV1/FVC Percent Value - source: caDSR - cde_id: 3302955 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302955&version=1.0" - -figo_stage: - description: > - The extent of a cervical or endometrial cancer within the body, especially whether the - disease has spread from the original site to other parts of the body, as described by the - International Federation of Gynecology and Obstetrics (FIGO) stages. - termDef: - term: Gynecologic Tumor Grouping Cervical Endometrial FIGO 2009 Stage - source: caDSR - cde_id: 3225684 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225684&version=1.0" - -file_name: # TOREVIEW - description: > - The name (or part of a name) of a file (of any type). - -file_size: # TOREVIEW - description: > - The size of the data file (object) in bytes. - -file_state: # TOREVIEW - description: > - The current state of the data file object. - -flow_cell_barcode: # TOREVIEW - description: > - Flow Cell Barcode. - -freezing_method: - description: > - Text term that represents the method used for freezing the sample. - termDef: - term: Tissue Sample Freezing Method Type - source: caDSR - cde_id: 5432607 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432607&version=1.0" - -gender: - description: > - Text designations that identify gender. Gender is described as the assemblage of properties that - distinguish people on the basis of their societal roles. [Explanatory Comment 1: Identification - of gender is based upon self-report and may come from a form, questionnaire, interview, etc.] - termDef: - term: Person Gender Text Type - source: caDSR - cde_id: 2200604 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2200604&version=3.0" - -height: - description: > - The height of the patient in centimeters. - termDef: - term: Patient Height Measurement - source: caDSR - cde_id: 649 - cde_version: 4.1 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=649&version=4.1" - -her2_erbb2_percent_positive_ihc: - description: > - Classification to represent the number of positive HER2/ERBB2 cells in a specimen or sample. - termDef: - term: HER2 ERBB Positive Finding Cell Percentage Category - source: caDSR - cde_id: 3086980 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3086980&version=1.0" - -her2_erbb2_result_fish: - description: > - the type of outcome for HER2 as determined by an in situ hybridization (ISH) assay. - termDef: - term: Laboratory Procedure HER2/neu in situ Hybridization Outcome Type - source: caDSR - cde_id: 2854089 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2854089&version=1.0" - -her2_erbb2_result_ihc: - description: > - Text term to signify the result of the medical procedure that involves testing a sample of - blood or tissue for HER2 by histochemical localization of immunoreactive substances using - labeled antibodies as reagents. - termDef: - term: Laboratory Procedure HER2/neu Immunohistochemistry Receptor Status - source: caDSR - cde_id: 2957563 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957563&version=2.0" - -hiv_positive: - description: > - Text term to signify whether a physician has diagnosed HIV infection in a patient. - termDef: - term: Physician Diagnosed HIV Infection Personal Medical History Yes No Not Applicable Indicator - source: caDSR - cde_id: 4030799 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4030799&version=1.0" - -hpv_positive_type: - description: > - Text classification to represent the strain or type of human papillomavirus identified in an - individual. - termDef: - term: Human Papillomavirus Type - source: caDSR - cde_id: 2922649 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2922649&version=1.0" - -hpv_status: - description: > - The findings of the oncogenic HPV. - termDef: - term: Oncogenic Human Papillomavirus Result Type - source: caDSR - cde_id: 2230033 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2230033&version=1.0" - -includes_spike_ins: # TOREVIEW - description: > - Spike-in included? - -initial_weight: - description: > - Numeric value that represents the initial weight of the sample, measured in milligrams. - termDef: - term: Tissue Sample Initial Weight Milligram Value - source: caDSR - cde_id: 5432605 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432605&version=1.0" - -instrument_model: - description: > - Numeric value that represents the sample dimension that is greater than the shortest - dimension and less than the longest dimension, measured in millimeters. - termDef: - term: Tissue Sample Intermediate Dimension Millimeter Measurement - source: caDSR - cde_id: 5432604 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432604&version=1.0" - -intermediate_dimension: # TOREVIEW - description: > - Intermediate dimension of the sample, in millimeters. - -is_ffpe: - description: > - Indicator to signify whether or not the tissue sample was fixed in formalin and embedded in - paraffin (FFPE). - termDef: - term: Specimen Processing Formalin Fixed Paraffin Embedded Tissue Indicator - source: caDSR - cde_id: 4170557 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4170557&version=1.0" - -is_paired_end: # TOREVIEW - description: > - Are the reads paired end? - -last_known_disease_status: - description: > - Text term that describes the last known state or condition of an individual's neoplasm. - termDef: - term: Person Last Known Neoplasm Status - source: caDSR - cde_id: 5424231 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2759550&version=1.0" - -laterality: - description: > - For tumors in paired organs, designates the side on which the cancer originates. - termDef: - term: Primary Tumor Laterality - source: caDSR - cde_id: 827 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=827&version=3.0" - -ldh_level_at_diagnosis: - description: > - The 2 decimal place numeric laboratory value measured, assigned or computed related to the - assessment of lactate dehydrogenase in a specimen. - termDef: - term: Laboratory Procedure Lactate Dehydrogenase Result Integer::2 Decimal Place Value - source: caDSR - cde_id: 2798766 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2798766&version=1.0" - -ldh_normal_range_upper: - description: > - The top value of the range of statistical characteristics that are supposed to represent - accepted standard, non-pathological pattern for lactate dehydrogenase (units not specified). - termDef: - term: Laboratory Procedure Lactate Dehydrogenase Result Upper Limit of Normal Value - source: caDSR - cde_id: 2597015 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2597015&version=1.0" - -library_strategy: # TOREVIEW - description: > - Library strategy. - -library_selection: # TOREVIEW - description: > - Library Selection Method - -library_name: # TOREVIEW - description: > - Name of the library. - -library_preparation_kit_name: # TOREVIEW - description: > - Name of Library Preparation Kit - -library_preparation_kit_vendor: # TOREVIEW - description: > - Vendor of Library Preparation Kit - -library_preparation_kit_catalog_number: # TOREVIEW - description: > - Catalog of Library Preparation Kit - -library_preparation_kit_version: # TOREVIEW - description: > - Version of Library Preparation Kit - -library_strand: # TOREVIEW - description: > - Library stranded-ness. - -longest_dimension: - description: > - Numeric value that represents the longest dimension of the sample, measured in millimeters. - termDef: - term: Tissue Sample Longest Dimension Millimeter Measurement - source: caDSR - cde_id: 5432602 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432602&version=1.0" - -lymph_nodes_positive: - description: > - The number of lymph nodes involved with disease as determined by pathologic examination. - termDef: - term: Lymph Node(s) Positive Number - source: caDSR - cde_id: 89 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=89&version=3.0" - -lymphatic_invasion_present: - description: > - A yes/no indicator to ask if small or thin-walled vessel invasion is present, indicating - lymphatic involvement - termDef: - term: Lymphatic/Small vessel Invasion Ind - source: caDSR - cde_id: 64171 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64171&version=3.0" - -method_of_diagnosis: - description: > - The method used to initially the patient's diagnosis. - termDef: - term: Method of Diagnosis - source: null - cde_id: null - cde_version: null - term_url: null - -method_of_sample_procurement: - description: > - The method used to procure the sample used to extract analyte(s). - termDef: - term: Method of Sample Procurement - source: null - cde_id: null - cde_version: null - term_url: null - -md5sum: # TOREVIEW - description: > - The 128-bit hash value expressed as a 32 digit hexadecimal number used as a file's digital - fingerprint. - -microsatellite_instability_abnormal: - description: > - The yes/no indicator to signify the status of a tumor for microsatellite instability. - termDef: - term: Microsatellite Instability Occurrence Indicator - source: caDSR - cde_id: 3123142 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3123142&version=1.0" - -morphology: - description: > - The third edition of the International Classification of Diseases for Oncology, published in - 2000 used principally in tumor and cancer registries for coding the site (topography) and the - histology (morphology) of neoplasms. The study of the structure of the cells and their - arrangement to constitute tissues and, finally, the association among these to form organs. In - pathology, the microscopic process of identifying normal and abnormal morphologic - characteristics in tissues, by employing various cytochemical and immunocytochemical stains. A - system of numbered categories for representation of data. - termDef: - term: International Classification of Diseases for Oncology, Third Edition ICD-O-3 Histology Code - source: caDSR - cde_id: 3226275 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226275&version=1.0" - -new_event_anatomic_site: - description: > - Text term to specify the anatomic location of the return of tumor after treatment. - termDef: - term: New Neoplasm Event Occurrence Anatomic Site - source: caDSR - cde_id: 3108271 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3108271&version=2.0" - -new_event_type: - description: > - Text term to identify a new tumor event. - termDef: - term: New Neoplasm Event Type - source: caDSR - cde_id: 3119721 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3119721&version=1.0" - -normal_tumor_genotype_snp_match: - description: > - Text term that represents whether or not the genotype of the normal tumor matches or if the data - is not available. - termDef: - term: Normal Tumor Genotype Match Indicator - source: caDSR - cde_id: 4588156 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4588156&version=1.0" - -number_proliferating_cells: - description: > - Numeric value that represents the count of proliferating cells determined during pathologic - review of the sample slide(s). - termDef: - term: Pathology Review Slide Proliferating Cell Count - source: caDSR - cde_id: 5432636 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432636&version=1.0" - -oct_embedded: - description: > - Indicator of whether or not the sample was embedded in Optimal Cutting Temperature (OCT) compound. - termDef: - term: Tissue Sample Optimal Cutting Temperature Compound Embedding Indicator - source: caDSR - cde_id: 5432538 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432538&version=1.0" - -pack_years_smoked: - description: > - Numeric computed value to represent lifetime tobacco exposure defined as number of cigarettes - smoked per day x number of years smoked divided by 20. - termDef: - term: Person Cigarette Smoking History Pack Year Value - source: caDSR - cde_id: 2955385 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" - -percent_eosinophil_infiltration: - description: > - Numeric value to represent the percentage of infiltration by eosinophils in a tumor sample or - specimen. - termDef: - term: Specimen Eosinophilia Percentage Value - source: caDSR - cde_id: 2897700 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897700&version=2.0" - -percent_gc_content: - description: > - The overall %GC of all bases in all sequences. - termDef: - term: "%GC" - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -percent_granulocyte_infiltration: - description: > - Numeric value to represent the percentage of infiltration by granulocytes in a tumor sample or - specimen. - termDef: - term: Specimen Granulocyte Infiltration Percentage Value - source: caDSR - cde_id: 2897705 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897705&version=2.0" - -percent_inflam_infiltration: - description: > - Numeric value to represent local response to cellular injury, marked by capillary dilatation, - edema and leukocyte infiltration; clinically, inflammation is manifest by reddness, heat, pain, - swelling and loss of function, with the need to heal damaged tissue. - termDef: - term: Specimen Inflammation Change Percentage Value - source: caDSR - cde_id: 2897695 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897695&version=1.0" - -percent_lymphocyte_infiltration: - description: > - Numeric value to represent the percentage of infiltration by lymphocytes in a solid tissue - normal sample or specimen. - termDef: - term: Specimen Lymphocyte Infiltration Percentage Value - source: caDSR - cde_id: 2897710 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897710&version=2.0" - -percent_monocyte_infiltration: - description: > - Numeric value to represent the percentage of monocyte infiltration in a sample or specimen. - termDef: - term: Specimen Monocyte Infiltration Percentage Value - source: caDSR - cde_id: 5455535 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5455535&version=1.0" - -percent_necrosis: - description: > - Numeric value to represent the percentage of cell death in a malignant tumor sample or specimen. - termDef: - term: Malignant Neoplasm Necrosis Percentage Value - source: caDSR - cde_id: 2841237 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841237&version=1.0" - -percent_neutrophil_infiltration: - description: > - Numeric value to represent the percentage of infiltration by neutrophils in a tumor sample or - specimen. - termDef: - term: Malignant Neoplasm Neutrophil Infiltration Percentage Cell Value - source: caDSR - cde_id: 2841267 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841267&version=1.0" - -percent_normal_cells: - description: > - Numeric value to represent the percentage of normal cell content in a malignant tumor sample or - specimen. - termDef: - term: Malignant Neoplasm Normal Cell Percentage Value - source: caDSR - cde_id: 2841233 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841233&version=1.0" - -percent_stromal_cells: - description: > - Numeric value to represent the percentage of reactive cells that are present in a malignant - tumor sample or specimen but are not malignant such as fibroblasts, vascular structures, etc. - termDef: - term: Malignant Neoplasm Stromal Cell Percentage Value - source: caDSR - cde_id: 2841241 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841241&version=1.0" - -percent_tumor_cells: - description: > - Numeric value that represents the percentage of infiltration by granulocytes in a sample. - termDef: - term: Specimen Tumor Cell Percentage Value - source: caDSR - cde_id: 5432686 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432686&version=1.0" - -percent_tumor_nuclei: - description: > - Numeric value to represent the percentage of tumor nuclei in a malignant neoplasm sample or specimen. - termDef: - term: Malignant Neoplasm Neoplasm Nucleus Percentage Cell Value - source: caDSR - cde_id: 2841225 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841225&version=1.0" - -perineural_invasion_present: - description: > - a yes/no indicator to ask if perineural invasion or infiltration of tumor or cancer is - present. - termDef: - term: Tumor Perineural Invasion Ind - source: caDSR - cde_id: 64181 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64181&version=3.0" - -platform: # TOREVIEW - description: > - Name of the platform used to obtain data. - -portion_number: - description: > - Numeric value that represents the sequential number assigned to a portion of the sample. - termDef: - term: Biospecimen Portion Sequence Number - source: caDSR - cde_id: 5432711 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432711&version=1.0" - -portion_weight: - description: > - Numeric value that represents the sample portion weight, measured in milligrams. - termDef: - term: Biospecimen Portion Weight Milligram Value - source: caDSR - cde_id: 5432593 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432593&version=1.0" - -preservation_method: - description: > - Text term that represents the method used to preserve the sample. - termDef: - term: Tissue Sample Preservation Method Type - source: caDSR - cde_id: 5432521 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432521&version=1.0" - -primary_diagnosis: - description: > - Text term for the structural pattern of cancer cells used to define a microscopic diagnosis. - termDef: - term: Neoplasm Histologic Type Name - source: caDSR - cde_id: 3081934 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3081934&version=3.0" - -prior_malignancy: - description: > - Text term to describe the patient's history of prior cancer diagnosis and the spatial location - of any previous cancer occurrence. - termDef: - term: Prior Cancer Diagnosis Occurrence Description Text - source: caDSR - cde_id: 3382736 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3382736&version=2.0" - -prior_treatment: - description: > - A yes/no/unknown/not applicable indicator related to the administration of therapeutic agents - received before the body specimen was collected. - termDef: - term: Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown Not Applicable Indicator - source: caDSR - cde_id: 4231463 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" - -progesterone_receptor_percent_positive_ihc: - description: > - Classification to represent Progesterone Receptor Positive results expressed as a percentage - value. - termDef: - term: Progesterone Receptor Level Cell Percentage Category - source: caDSR - cde_id: 3128342 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128342&version=1.0" - -progesterone_receptor_result_ihc: - description: > - Text term to represent the overall result of Progresterone Receptor (PR) testing. - termDef: - term: Breast Carcinoma Progesterone Receptor Status - source: caDSR - cde_id: 2957357 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957357&version=2.0" - -progression_or_recurrence: - description: > - Yes/No/Unknown indicator to identify whether a patient has had a new tumor event - after initial treatment. - termDef: - term: New Neoplasm Event Post Initial Therapy Indicator - source: caDSR - cde_id: 3121376 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121376&version=1.0" - -project_id: # TOREVIEW - description: > - Unique ID for any specific defined piece of work that is undertaken or attempted to - meet a single requirement. - -qc_metric_state: - description: > - State classification given by FASTQC for the metric. Metric specific details about the states - are available on their website. - termDef: - term: QC Metric State - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/" - -race: - description: > - An arbitrary classification of a taxonomic group that is a division of a species. It usually - arises as a consequence of geographical isolation within a species and is characterized by - shared heredity, physical attributes and behavior, and in the case of humans, by common history, - nationality, or geographic distribution. The provided values are based on the categories defined - by the U.S. Office of Management and Business and used by the U.S. Census Bureau. - termDef: - term: Race Category Text - source: caDSR - cde_id: 2192199 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192199&version=1.0" - -read_length: # TOREVIEW - description: > - The length of the reads. - -read_group_name: # TOREVIEW - description: > - The name of the read group. - -relationship_age_at_diagnosis: - description: > - The age (in years) when the patient's relative was first diagnosed. - termDef: - term: Relative Diagnosis Age Value - source: caDSR - cde_id: 5300571 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5300571&version=1.0" - -relationship_type: - description: > - The subgroup that describes the state of connectedness between members of the unit of society - organized around kinship ties. - termDef: - term: Family Member Relationship Type - source: caDSR - cde_id: 2690165 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2690165&version=2.0" - -relative_with_cancer_history: - description: > - Indicator to signify whether or not an individual's biological relative has been diagnosed with - another type of cancer. - termDef: - term: Other Cancer Biological Relative History Indicator - source: caDSR - cde_id: 3901752 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3901752&version=1.0" - -residual_disease: - description: > - Text terms to describe the status of a tissue margin following surgical resection. - termDef: - term: Surgical Margin Resection Status - source: caDSR - cde_id: 2608702 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2608702&version=1.0" - -RIN: - description: > - A numerical assessment of the integrity of RNA based on the entire electrophoretic trace of the - RNA sample including the presence or absence of degradation products. - termDef: - term: Biospecimen RNA Integrity Number Value - source: caDSR - cde_id: 5278775 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5278775&version=1.0" - -sample_type: - description: > - Text term to describe the source of a biospecimen used for a laboratory test. - termDef: - term: Specimen Type Collection Biospecimen Type - source: caDSR - cde_id: 3111302 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3111302&version=2.0" - -sample_type_id: # TOREVIEW - description: > - The accompanying sample type id for the sample type. - -section_location: # TOREVIEW - description: > - Tissue source of the slide. - -sequencing_center: # TOREVIEW - description: > - Name of the center that provided the sequence files. - -shortest_dimension: - description: > - Numeric value that represents the shortest dimension of the sample, measured in millimeters. - termDef: - term: Tissue Sample Short Dimension Millimeter Measurement - source: caDSR - cde_id: 5432603 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432603&version=1.0" - -site_of_resection_or_biopsy: - description: > - The third edition of the International Classification of Diseases for Oncology, published in - 2000, used principally in tumor and cancer registries for coding the site (topography) and the - histology (morphology) of neoplasms. The description of an anatomical region or of a body part. - Named locations of, or within, the body. A system of numbered categories for representation of - data. - termDef: - term: International Classification of Diseases for Oncology, Third Edition ICD-O-3 Site Code - source: caDSR - cde_id: 3226281 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226281&version=1.0" - -size_selection_range: # TOREVIEW - description: > - Range of size selection. - -smoking_history: - description: > - Category describing current smoking status and smoking history as self-reported by a patient. - termDef: - term: Smoking History - source: caDSR - cde_id: 2181650 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" - -smoking_intensity: - description: > - Numeric computed value to represent lifetime tobacco exposure defined as number of cigarettes - smoked per day x number of years smoked divided by 20 - termDef: - term: Person Cigarette Smoking History Pack Year Value - source: caDSR - cde_id: 2955385 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" - -source_center: # TOREVIEW - description: > - Name of the center that provided the item. - -spectrophotometer_method: - description: > - Name of the method used to determine the concentration of purified nucleic acid within a - solution. - termDef: - term: Purification Nucleic Acid Solution Concentration Determination Method Type - source: caDSR - cde_id: 3008378 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008378&version=1.0" - -spike_ins_fasta: # TOREVIEW - description: > - Name of the FASTA file that contains the spike-in sequences. - -spike_ins_concentration: # TOREVIEW - description: > - Spike in concentration. - -state: # TOREVIEW - description: > - The current state of the object. - -target_capture_kit_name: # TOREVIEW - description: > - Name of Target Capture Kit. - -target_capture_kit_vendor: # TOREVIEW - description: > - Vendor of Target Capture Kit. - -target_capture_kit_catalog_number: # TOREVIEW - description: > - Catalog of Target Capture Kit. - -target_capture_kit_version: # TOREVIEW - description: > - Version of Target Capture Kit. - -target_capture_kit_target_region: # TOREVIEW - description: > - Target Capture Kit BED file. - -therapeutic_agents: - description: > - Text identification of the individual agent(s) used as part of a prior treatment regimen. - termDef: - term: Prior Therapy Regimen Text - source: caDSR - cde_id: 2975232 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2975232&version=1.0" - -time_between_clamping_and_freezing: - description: > - Numeric representation of the elapsed time between the surgical clamping of blood supply and - freezing of the sample, measured in minutes. - termDef: - term: Tissue Sample Clamping and Freezing Elapsed Minute Time - source: caDSR - cde_id: 5432611 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432611&version=1.0" - -time_between_excision_and_freezing: - description: > - Numeric representation of the elapsed time between the excision and freezing of the sample, - measured in minutes. - termDef: - term: Tissue Sample Excision and Freezing Elapsed Minute Time - source: caDSR - cde_id: 5432612 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432612&version=1.0" - -tissue_or_organ_of_origin: - description: > - Text term that describes the anatomic site of the tumor or disease. - termDef: - term: Tumor Disease Anatomic Site - source: caDSR - cde_id: 3427536 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3427536&version=3.0" - -tissue_type: - description: > - Text term that represents a description of the kind of tissue collected with respect to disease - status or proximity to tumor tissue. - termDef: - term: Tissue Sample Description Type - source: caDSR - cde_id: 5432687 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432687&version=1.0" - -to_trim_adapter_sequence: # TOREVIEW - description: > - Does the user suggest adapter trimming? - -tobacco_smoking_onset_year: - description: > - The year in which the participant began smoking. - termDef: - term: Started Smoking Year - source: caDSR - cde_id: 2228604 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228604&version=1.0" - -tobacco_smoking_quit_year: - description: > - The year in which the participant quit smoking. - termDef: - term: Stopped Smoking Year - source: caDSR - cde_id: 2228610 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228610&version=1.0" - -tobacco_smoking_status: - description: > - Category describing current smoking status and smoking history as self-reported by a - patient. - termDef: - term: Patient Smoking History Category - source: caDSR - cde_id: 2181650 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" - -total_sequences: - description: > - A count of the total number of sequences processed. - termDef: - term: Total Sequences - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -treatment_anatomic_site: - description: > - The anatomic site or field targeted by a treatment regimen or single agent therapy. - termDef: - term: Treatment Anatomic Site - source: null - cde_id: null - cde_version: null - term_url: null - -treatment_intent_type: - description: > - Text term to identify the reason for the administration of a treatment regimen. [Manually-curated] - termDef: - term: Treatment Regimen Intent Type - source: caDSR - cde_id: 2793511 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2793511&version=1.0" - -treatment_or_therapy: - description: > - A yes/no/unknown/not applicable indicator related to the administration of therapeutic agents - received before the body specimen was collected. - termDef: - term: Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown Not Applicable Indicator - source: caDSR - cde_id: 4231463 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" - -treatment_outcome: - description: > - Text term that describes the patient¿s final outcome after the treatment was administered. - termDef: - term: Treatment Outcome Type - source: caDSR - cde_id: 5102383 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102383&version=1.0" - -treatment_type: - description: > - Text term that describes the kind of treatment administered. - termDef: - term: Treatment Method Type - source: caDSR - cde_id: 5102381 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102381&version=1.0" - -tumor_grade: - description: > - Numeric value to express the degree of abnormality of cancer cells, a measure of differentiation - and aggressiveness. - termDef: - term: Neoplasm Histologic Grade - source: caDSR - cde_id: 2785839 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2785839&version=2.0" - -tumor_code: # TOREVIEW - description: > - Diagnostic tumor code of the tissue sample source. - -tumor_code_id: # TOREVIEW - description: > - BCR-defined id code for the tumor sample. - -tumor_descriptor: - description: > - Text that describes the kind of disease present in the tumor specimen as related to a specific - timepoint. - termDef: - term: Tumor Tissue Disease Description Type - source: caDSR - cde_id: 3288124 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" - -tumor_stage: - description: > - The extent of a cancer in the body. Staging is usually based on the size of the tumor, whether - lymph nodes contain cancer, and whether the cancer has spread from the original site to other - parts of the body. The accepted values for tumor_stage depend on the tumor site, type, and - accepted staging system. These items should accompany the tumor_stage value as associated - metadata. - termDef: - term: Tumor Stage - source: NCIt - cde_id: C16899 - cde_version: null - term_url: "https://ncit.nci.nih.gov/ncitbrowser/pages/concept_details.jsf?dictionary=NCI%20Thesaurus&code=C16899" - -UUID: - description: > - A 128-bit identifier. Depending on the mechanism used to generate it, it is either guaranteed to - be different from all other UUIDs/GUIDs generated until 3400 AD or extremely likely to be - different. Its relatively small size lends itself well to sorting, ordering, and hashing of all - sorts, storing in databases, simple allocation, and ease of programming in general. - termDef: - term: Universally Unique Identifier - source: NCIt - cde_id: C54100 - cde_version: null - term_url: "https://ncit.nci.nih.gov/ncitbrowser/ConceptReport.jsp?dictionary=NCI_Thesaurus&version=16.02d&ns=NCI_Thesaurus&code=C54100" - -vascular_invasion_present: - description: > - The yes/no indicator to ask if large vessel or venous invasion was detected by surgery or - presence in a tumor specimen. - termDef: - term: Tumor Vascular Invasion Ind-3 - source: caDSR - cde_id: 64358 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64358&version=3.0" - -vital_status: - description: > - The survival state of the person registered on the protocol. - termDef: - term: Patient Vital Status - source: caDSR - cde_id: 5 - cde_version: 5.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5&version=5.0" - -weight: - description: > - The weight of the patient measured in kilograms. - termDef: - term: Patient Weight Measurement - source: caDSR - cde_id: 651 - cde_version: 4.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=651&version=4.0" - -well_number: - description: > - Numeric value that represents the the well location within a plate for the analyte or - aliquot from the sample. - termDef: - term: Biospecimen Analyte or Aliquot Plate Well Number - source: caDSR - cde_id: 5432613 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432613&version=1.0" - -workflow_type: - description: > - Generic name for the workflow used to analyze a data set. - -year_of_birth: - description: > - Numeric value to represent the calendar year in which an individual was born. - termDef: - term: Year Birth Date Number - source: caDSR - cde_id: 2896954 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896954&version=1.0" - -year_of_diagnosis: - description: > - Numeric value to represent the year of an individual's initial pathologic diagnosis of cancer. - termDef: - term: Year of initial pathologic diagnosis - source: caDSR - cde_id: 2896960 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896960&version=1.0" - -year_of_death: - description: > - Numeric value to represent the year of the death of an individual. - termDef: - term: Year Death Number - source: caDSR - cde_id: 2897030 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897030&version=1.0" - -years_smoked: - description: > - Numeric value (or unknown) to represent the number of years a person has been smoking. - termDef: - term: Person Smoking Duration Year Count - source: caDSR - cde_id: 3137957 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3137957&version=1.0" diff --git a/gdcdictionary/schemas/acknowledgement.yaml b/gdcdictionary/schemas/acknowledgement.yaml deleted file mode 100644 index cee5d3d99..000000000 --- a/gdcdictionary/schemas/acknowledgement.yaml +++ /dev/null @@ -1,61 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "acknowledgement" -title: Acknowledgement -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "Acknowledgement of an individual involved in a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: acknowledgements - label: contribute_to - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "acknowledgement" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - acknowledgee: - description: "The indvidiual or group being acknowledged by the project." - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/aligned_reads_index.yaml b/gdcdictionary/schemas/aligned_reads_index.yaml deleted file mode 100644 index e09ee3edc..000000000 --- a/gdcdictionary/schemas/aligned_reads_index.yaml +++ /dev/null @@ -1,77 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "aligned_reads_index" -title: Aligned Reads Index -type: object -namespace: http://gdc.nci.nih.gov -category: index_file -program: '*' -project: '*' -description: "Data file containing the index for a set of aligned reads." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: submitted_aligned_reads_files - backref: aligned_reads_indexes - label: derived_from - target_type: submitted_aligned_reads - multiplicity: one_to_one - required: false - - name: core_metadata_collections - backref: aligned_reads_indexes - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "aligned_reads_index" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Aligned Reads Index" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: [ "BAI" ] - submitted_aligned_reads_files: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/aliquot.yaml b/gdcdictionary/schemas/aliquot.yaml deleted file mode 100644 index 078cb17ac..000000000 --- a/gdcdictionary/schemas/aliquot.yaml +++ /dev/null @@ -1,103 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "aliquot" -title: Aliquot -type: object -category: biospecimen -program: '*' -project: '*' -description: > - Pertaining to a portion of the whole; any one of two or more samples of something, of the same - volume or weight. -additionalProperties: false -submittable: true -validators: [] - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - - samples - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -links: - - name: samples - backref: aliquots - label: derived_from - multiplicity: many_to_many - target_type: sample - required: true - -constraints: null - -# Aliquot properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - description: > - The legacy barcode used before prior to the use - UUIDs. For TCGA this is bcraliquotbarcode. - aliquot_quantity: - term: - $ref: "_terms.yaml#/aliquot_quantity" - type: number - aliquot_volume: - term: - $ref: "_terms.yaml#/aliquot_volume" - type: number - amount: - term: - $ref: "_terms.yaml#/amount" - type: number - analyte_type: - term: - $ref: "_terms.yaml#/analyte_type" - type: string - analyte_type_id: - term: - $ref: "_terms.yaml#/analyte_type_id" - enum: - - D - - E - - G - - H - - R - - S - - T - - W - - X - - Y - concentration: - term: - $ref: "_terms.yaml#/concentration" - type: number - project_id: - $ref: "_definitions.yaml#/project_id" - source_center: - term: - $ref: "_terms.yaml#/source_center" - type: string - samples: - $ref: "_definitions.yaml#/to_one" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/case.yaml b/gdcdictionary/schemas/case.yaml deleted file mode 100644 index 3db55f5a3..000000000 --- a/gdcdictionary/schemas/case.yaml +++ /dev/null @@ -1,71 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "case" -title: Case -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: > - The collection of all data related to a specific subject in the - context of a specific experiment. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: experiments - backref: cases - label: member_of - target_type: experiment - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - experiments - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -# Case properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - consent_codes: - type: array - items: - type: string - primary_site: - description: "Primary site for the case." - type: string - disease_type: - description: "Name of the disease for the case." - type: string - experiments: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/clinical_test.yaml b/gdcdictionary/schemas/clinical_test.yaml deleted file mode 100644 index 0ac0376f6..000000000 --- a/gdcdictionary/schemas/clinical_test.yaml +++ /dev/null @@ -1,242 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "clinical_test" -title: Clinical Test -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -project: '*' -program: '*' -description: > - Metadata concerning any clinical tests used in relation to a case diagnosis. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: cases - backref: clinical_tests - label: performed_for - target_type: case - multiplicity: many_to_one - required: true - - name: diagnoses - backref: clinical_tests - label: relates_to - target_type: diagnosis - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - biomarker_name - - biomarker_result - - biomarker_test_method - - cases - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "clinical_test" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - biomarker_name: - term: - $ref: "_terms.yaml#/biomarker_name" - type: string - - biomarker_result: - term: - $ref: "_terms.yaml#/biomarker_result" - enum: - - Amplification - - Gain - - Loss - - Normal - - Other - - Translocation - - Not Reported - - Not Allowed To Collect - - Pending - - biomarker_test_method: - term: - $ref: "_terms.yaml#/biomarker_test_method" - enum: - - Cytogenetics - - FISH - - IHC - - Karyotype - - NGS - - Nuclear Staining - - Other - - RT-PCR - - Southern - - Not Reported - - Not Allowed To Collect - - Pending - - cea_level_preoperative: - term: - $ref: "_terms.yaml#/cea_level_preoperative" - type: number - - dlco_ref_predictive_percent: - term: - $ref: "_terms.yaml#/dlco_ref_predictive_percent" - type: number - - estrogen_receptor_percent_positive_ihc: - term: - $ref: "_terms.yaml#/estrogen_receptor_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - estrogen_receptor_result_ihc: - term: - $ref: "_terms.yaml#/estrogen_receptor_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - fev1_ref_post_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_ref_post_bronch_percent" - type: number - - fev1_ref_pre_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_ref_pre_bronch_percent" - type: number - - fev1_fvc_post_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_fvc_post_bronch_percent" - type: number - - fev1_fvc_pre_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_fvc_pre_bronch_percent" - type: number - - her2_erbb2_percent_positive_ihc: - term: - $ref: "_terms.yaml#/her2_erbb2_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - her2_erbb2_result_fish: - term: - $ref: "_terms.yaml#/her2_erbb2_result_fish" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - her2_erbb2_result_ihc: - term: - $ref: "_terms.yaml#/her2_erbb2_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - ldh_level_at_diagnosis: - term: - $ref: "_terms.yaml#/ldh_level_at_diagnosis" - type: number - - ldh_normal_range_upper: - term: - $ref: "_terms.yaml#/ldh_normal_range_upper" - type: number - - microsatellite_instability_abnormal: - term: - $ref: "_terms.yaml#/microsatellite_instability_abnormal" - enum: - - "Yes" - - "No" - - Unknown - - progesterone_receptor_percent_positive_ihc: - term: - $ref: "_terms.yaml#/progesterone_receptor_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - progesterone_receptor_result_ihc: - term: - $ref: "_terms.yaml#/progesterone_receptor_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - cases: - $ref: "_definitions.yaml#/to_one" - diagnoses: - $ref: "_definitions.yaml#/to_many" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/core_metadata_collection.yaml b/gdcdictionary/schemas/core_metadata_collection.yaml deleted file mode 100644 index 1a2bcebc6..000000000 --- a/gdcdictionary/schemas/core_metadata_collection.yaml +++ /dev/null @@ -1,113 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "core_metadata_collection" -title: Core Metadata Collection -type: object -namespace: https://dcp.bionimbus.org/ -category: administrative -program: '*' -project: '*' -description: > - Structured description of a collection of several dataset -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: core_metadata_collections - label: data_from - target_type: project - multiplicity: many_to_one - required: true - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -required: - - submitter_id - - type - - projects - -properties: - $ref: "_definitions.yaml#/ubiquitous_properties" - - contributor: - description: > - An entity responsible for making contributions to the resource. Examples of a Contributor include a person, an organization, or a service. Typically, the name of a Contributor should be used to indicate the entity. - type: string - - coverage: - description: > - The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant. Spatial topic and spatial applicability may be a named place or a location specified by its geographic coordinates. Temporal topic may be a named period, date, or date range. A jurisdiction may be a named administrative entity or a geographic place to which the resource applies. Recommended best practice is to use a controlled vocabulary such as the Thesaurus of Geographic Names [TGN] (http://www.getty.edu/research/tools/vocabulary/tgn/index.html). Where appropriate, named places or time periods can be used in preference to numeric identifiers such as sets of coordinates or date ranges. - type: string - - creator: - description: > - An entity primarily responsible for making the resource. Examples of a Creator include a person, an organization, or a service. Typically, the name of a Creator should be used to indicate the entity. - type: string - - date: - $ref: "_definitions.yaml#/datetime" - - description: - description: > - An account of the resource. Description may include but is not limited to: an abstract, a table of contents, a graphical representation, or a free-text account of the resource. - type: string - - format: - description: > - The file format, physical medium, or dimensions of the resource. Examples of dimensions include size and duration. Recommended best practice is to use a controlled vocabulary such as the list of Internet Media Types [MIME] (http://www.iana.org/assignments/media-types/). - type: string - - language: - description: > - A language of the resource. Recommended best practice is to use a controlled vocabulary such as RFC 4646 (http://www.ietf.org/rfc/rfc4646.txt). - type: string - - publisher: - description: > - An entity responsible for making the resource available. Examples of a Publisher include a person, an organization, or a service. Typically, the name of a Publisher should be used to indicate the entity. - type: string - - relation: - description: > - A related resource. Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system.  - type: string - - rights: - description: > - Information about rights held in and over the resource. Typically, rights information includes a statement about various property rights associated with the resource, including intellectual property rights. - type: string - - source: - description: > - A related resource from which the described resource is derived. The described resource may be derived from the related resource in whole or in part. Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system. - type: string - - subject: - description: > - The topic of the resource. Typically, the subject will be represented using keywords, key phrases, or classification codes. Recommended best practice is to use a controlled vocabulary. - type: string - - title: - description: > - A name given to the resource. Typically, a Title will be a name by which the resource is formally known. - type: string - - data_type: - description: > - The nature or genre of the resource. Recommended best practice is to use a controlled vocabulary such as the DCMI Type Vocabulary [DCMITYPE]. To describe the file format, physical medium, or dimensions of the resource, use the Format element. - type: string - - projects: - $ref: "_definitions.yaml#/to_one_project" - diff --git a/gdcdictionary/schemas/demographic.yaml b/gdcdictionary/schemas/demographic.yaml deleted file mode 100644 index ea8a2b422..000000000 --- a/gdcdictionary/schemas/demographic.yaml +++ /dev/null @@ -1,114 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "demographic" -title: Demographic -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Data for the characterization of the patient by means of segementing the population (e.g., - characterization by age, sex, or race). -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: cases - backref: demographics - label: describes - target_type: case - multiplicity: one_to_one - required: true - -required: - - submitter_id - - type - - cases - -preferred: - - year_of_death - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - type: string - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - gender: - term: - $ref: "_terms.yaml#/gender" - enum: - - female - - male - - unknown - - unspecified - - not reported - - race: - term: - $ref: "_terms.yaml#/race" - enum: - - white - - american indian or alaska native - - black or african american - - asian - - native hawaiian or other pacific islander - - other - - Unknown - - not reported - - not allowed to collect - - ethnicity: - term: - $ref: "_terms.yaml#/ethnicity" - enum: - - hispanic or latino - - not hispanic or latino - - Unknown - - not reported - - not allowed to collect - - year_of_birth: - term: - $ref: "_terms.yaml#/year_of_birth" - type: - - number - - "null" - - year_of_death: - term: - $ref: "_terms.yaml#/year_of_death" - type: number - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/diagnosis.yaml b/gdcdictionary/schemas/diagnosis.yaml deleted file mode 100644 index 28c424081..000000000 --- a/gdcdictionary/schemas/diagnosis.yaml +++ /dev/null @@ -1,844 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "diagnosis" -title: Diagnosis -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Data from the investigation, analysis and recognition of the presence and nature of disease, - condition, or injury from expressed signs and symptoms; also, the scientific determination of any - kind; the concise results of such an investigation. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: cases - backref: diagnoses - label: describes - target_type: case - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - age_at_diagnosis - - days_to_last_follow_up - - vital_status - - primary_diagnosis - - morphology - - tissue_or_organ_of_origin - - site_of_resection_or_biopsy - - classification_of_tumor - - tumor_stage - - tumor_grade - - progression_or_recurrence - - days_to_recurrence - - days_to_last_known_disease_status - - last_known_disease_status - -preferred: - - days_to_birth - - site_of_resection_or_biopsy - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - type: string - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - age_at_diagnosis: - term: - $ref: "_terms.yaml#/age_at_diagnosis" - type: - - number - - "null" - maximum: 32872 - minimum: 0 - - ajcc_clinical_m: - term: - $ref: "_terms.yaml#/ajcc_clinical_m" - enum: - - M0 - - M1 - - M1a - - M1b - - M1c - - MX - - cM0 (i+) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_n: - term: - $ref: "_terms.yaml#/ajcc_clinical_n" - enum: - - N0 - - N0 (i+) - - N0 (i-) - - N0 (mol+) - - N0 (mol-) - - N1 - - N1a - - N1b - - N1bI - - N1bII - - N1bIII - - N1bIV - - N1c - - N1mi - - N2 - - N2a - - N2b - - N2c - - N3 - - N3a - - N3b - - N3c - - N4 - - NX - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_stage: - term: - $ref: "_terms.yaml#/ajcc_clinical_stage" - enum: - - Stage 0 - - Stage 0a - - Stage 0is - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB Cervix - - Stage IB1 - - Stage IB2 - - Stage II - - Stage II Cervix - - Stage IIA - - Stage IIA Cervix - - Stage IIB - - Stage IIC - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IS - - Stage IV - - Stage IVA - - Stage IVB - - Stage IVC - - Stage Tis - - Stage X - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_t: - term: - $ref: "_terms.yaml#/ajcc_clinical_t" - enum: - - T0 - - T1 - - T1a - - T1a1 - - T1a2 - - T1b - - T1b1 - - T1b2 - - T1c - - T1mi - - T2 - - T2a - - T2a1 - - T2a2 - - T2b - - T2c - - T2d - - T3 - - T3a - - T3b - - T3c - - T3d - - T4 - - T4a - - T4b - - T4c - - T4d - - T4e - - TX - - Ta - - Tis - - Tis (DCIS) - - Tis (LCIS) - - Tis (Paget's) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_m: - term: - $ref: "_terms.yaml#/ajcc_pathologic_m" - enum: - - M0 - - M1 - - M1a - - M1b - - M1c - - M2 - - MX - - cM0 (i+) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_n: - term: - $ref: "_terms.yaml#/ajcc_pathologic_n" - enum: - - N0 - - N0 (i+) - - N0 (i-) - - N0 (mol+) - - N0 (mol-) - - N1 - - N1a - - N1b - - N1bI - - N1bII - - N1bIII - - N1bIV - - N1c - - N1mi - - N2 - - N2a - - N2b - - N2c - - N3 - - N3a - - N3b - - N3c - - N4 - - NX - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_stage: - term: - $ref: "_terms.yaml#/ajcc_pathologic_stage" - enum: - - Stage 0 - - Stage 0a - - Stage 0is - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB1 - - Stage IB2 - - Stage IC - - Stage II - - Stage IIA - - Stage IIA1 - - Stage IIA2 - - Stage IIB - - Stage IIC - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IV - - Stage IVA - - Stage IVB - - Stage IVC - - Stage Tis - - Stage X - - ajcc_pathologic_t: - term: - $ref: "_terms.yaml#/ajcc_pathologic_t" - enum: - - T0 - - T1 - - T1a - - T1a1 - - T1a2 - - T1b - - T1b1 - - T1b2 - - T1c - - T1mi - - T2 - - T2a - - T2a1 - - T2a2 - - T2b - - T2c - - T2d - - T3 - - T3a - - T3b - - T3c - - T3d - - T4 - - T4a - - T4b - - T4c - - T4d - - T4e - - TX - - Ta - - Tis - - Tis (DCIS) - - Tis (LCIS) - - Tis (Paget's) - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_b_symptoms: - term: - $ref: "_terms.yaml#/ann_arbor_b_symptoms" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_clinical_stage: - term: - $ref: "_terms.yaml#/ann_arbor_clinical_stage" - enum: - - Stage I - - Stage II - - Stage III - - Stage IV - - ann_arbor_extranodal_involvement: - term: - $ref: "_terms.yaml#/ann_arbor_extranodal_involvement" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_pathologic_stage: - term: - $ref: "_terms.yaml#/ann_arbor_pathologic_stage" - enum: - - Stage I - - Stage II - - Stage III - - Stage IV - - burkitt_lymphoma_clinical_variant: - term: - $ref: "_terms.yaml#/burkitt_lymphoma_clinical_variant" - enum: - - "Endemic" - - "Immunodeficiency-associated, adult" - - "Immunodeficiency-associated, pediatric" - - "Sporadic, adult" - - "Sporadic, pediatric" - - Unknown - - Not Reported - - Not Allowed To Collect - - cause_of_death: - term: - $ref: "_terms.yaml#/cause_of_death" - enum: - - Cancer Related - - Not Cancer Related - - Unknown - - circumferential_resection_margin: - term: - $ref: "_terms.yaml#/circumferential_resection_margin" - type: number - - classification_of_tumor: - term: - $ref: "_terms.yaml#/classification_of_tumor" - enum: - - primary - - metastasis - - recurrence - - other - - Unknown - - not reported - - Not Allowed To Collect - - colon_polyps_history: - term: - $ref: "_terms.yaml#/colon_polyps_history" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - days_to_birth: - term: - $ref: "_terms.yaml#/days_to_birth" - type: - - number - - "null" - maximum: 0 - minimum: -32872 - - days_to_death: - term: - $ref: "_terms.yaml#/days_to_death" - type: number - maximum: 32872 - minimum: 0 - - days_to_hiv_diagnosis: - term: - $ref: "_terms.yaml#/days_to_hiv_diagnosis" - type: - - number - - "null" - - days_to_last_follow_up: - term: - $ref: "_terms.yaml#/days_to_last_follow_up" - type: - - number - - "null" - - days_to_last_known_disease_status: - term: - $ref: "_terms.yaml#/days_to_last_known_disease_status" - type: - - number - - "null" - - days_to_new_event: - term: - $ref: "_terms.yaml#/days_to_new_event" - type: - - number - - "null" - - days_to_recurrence: - term: - $ref: "_terms.yaml#/days_to_recurrence" - type: - - number - - "null" - - figo_stage: - term: - $ref: "_terms.yaml#/figo_stage" - enum: - - Stage 0 - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB1 - - Stage IB2 - - Stage IC - - Stage II - - Stage IIA - - Stage IIA1 - - Stage IIA2 - - Stage IIB - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IIIC1 - - Stage IIIC2 - - Stage IV - - Stage IVA - - Stage IVB - - Unknown - - Not Reported - - Not Allowed To Collect - - hiv_positive: - term: - $ref: "_terms.yaml#/hiv_positive" - enum: - - "Yes" - - "No" - - Unknown - - hpv_positive_type: - term: - $ref: "_terms.yaml#/hpv_positive_type" - enum: - - HPV 16 - - HPV 18 - - Other HPV type(s) - - Unknown - - hpv_status: - term: - $ref: "_terms.yaml#/hpv_status" - enum: - - Negative - - Positive - - Unknown - - last_known_disease_status: - term: - $ref: "_terms.yaml#/last_known_disease_status" - enum: - - Distant met recurrence/progression - - Loco-regional recurrence/progression - - Biochemical evidence of disease without structural correlate - - Tumor free - - Unknown tumor status - - With tumor - - not reported - - Not Allowed To Collect - - laterality: - term: - $ref: "_terms.yaml#/laterality" - enum: - - Bilateral - - Left - - Right - - Unknown - - ldh_level_at_diagnosis: - term: - $ref: "_terms.yaml#/ldh_level_at_diagnosis" - type: - - number - - "null" - - ldh_normal_range_upper: - term: - $ref: "_terms.yaml#/ldh_normal_range_upper" - type: - - number - - "null" - - lymph_nodes_positive: - term: - $ref: "_terms.yaml#/lymph_nodes_positive" - type: integer - - lymphatic_invasion_present: - term: - $ref: "_terms.yaml#/lymphatic_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - method_of_diagnosis: - term: - $ref: "_terms.yaml#/method_of_diagnosis" - enum: - - Autopsy - - Biopsy - - Blood Draw - - Bone Marrow Aspirate - - Core Biopsy - - Cytology - - Debulking - - Diagnostic Imaging - - Excisional Biopsy - - Fine Needle Aspiration - - Incisional Biopsy - - Laparoscopy - - Laparotomy - - Other - - Surgical Resection - - Ultrasound Guided Biopsy - - Unknown - - Not Reported - - Not Allowed To Collect - - morphology: - term: - $ref: "_terms.yaml#/morphology" - type: string - - new_event_anatomic_site: - term: - $ref: "_terms.yaml#/new_event_anatomic_site" - enum: - - Abdomen - - Adrenal - - Anus - - Appendix - - Ascites/Peritoneum - - Axillary lymph nodes - - Bladder - - Bone - - Bone Marrow - - Brain - - Breast - - Cervical lymph nodes - - Cervix - - Colon - - Conjunctiva - - Contralateral Pleura - - Distant Metastasis - - Epididymis - - Epidural - - Epitrochlear lymph nodes - - Esophagus - - Extremities - - Femoral lymph nodes - - Gallbladder - - Gastrointestinal/Abdominal - - Head & Neck - - Heart - - Hilar lymph nodes - - Hypopharynx - - Iliac Lymph Node - - Iliac-common lymph nodes - - Iliac-external lymph nodes - - Inguinal lymph nodes - - Intraocular - - Ipsilateral Chest Cavity - - Ipsilateral Chest Wall - - Ipsilateral Lymph Nodes - - Ipsilateral Pleura - - Kidney - - Large Intestine - - Larynx - - Leptomeninges - - Liver - - Lung - - Lymph Node Only - - Lymph Node(s) - - Mandible - - Maxilla - - Mediastinal Soft Tissue - - Mediastinal lymph nodes - - Mediastinal/Intra-thoracic - - Mesenteric lymph nodes - - Nasal Soft Tissue - - Nasopharynx - - No Known Extranodal Involvement - - Non-regional / Distant Lymph Nodes - - Not Applicable - - Occipital lymph nodes - - Oral Cavity - - Oropharynx - - Other - - Other Extranodal Site - - Other, specify - - Ovary - - Pancreas - - Paraaortic lymph nodes - - Parotid Gland - - Parotid lymph nodes - - Pelvis - - Peri-orbital Soft Tissue - - Pericardium - - Perihilar Lymph Node - - Peripheral Blood - - Peritoneal Surfaces - - Pleura/Pleural Effusion - - Popliteal lymph nodes - - Prostate - - Pulmonary - - Rectum - - Renal Pelvis - - Retroperitoneal lymph nodes - - Retroperitoneum - - Salivary Gland - - Sinus - - Skin - - Small Intestine - - Soft Tissue - - Splenic lymph nodes - - Stomach - - Submandibular lymph nodes - - Supraclavicular lymph nodes - - Testes - - Thyroid - - Trunk - - Tumor Bed - - Ureter - - Urethra - - Uterus - - Vulva - - Unknown - - Not Reported - - Not Allowed To Collect - - new_event_type: - term: - $ref: "_terms.yaml#/new_event_type" - enum: - - Biochemical Evidence of Disease - - Both Locoregional and Distant Metastasis - - Distant Metastasis - - Extrahepatic Recurrence - - Intrahepatic Recurrence - - Intrapleural Progression - - Locoregional (Urothelial tumor event) - - Locoregional Disease - - Locoregional Recurrence - - Metachronous Testicular Tumor - - Metastatic - - New Primary Tumor - - New primary Melanoma - - No New Tumor Event - - Not Applicable - - Progression of Disease - - Recurrence - - Regional Lymph Node - - Unknown - - Not Reported - - Not Allowed To Collect - - perineural_invasion_present: - term: - $ref: "_terms.yaml#/perineural_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - primary_diagnosis: - term: - $ref: "_terms.yaml#/primary_diagnosis" - type: string - - prior_malignancy: - term: - $ref: "_terms.yaml#/prior_malignancy" - enum: - - "yes" - - "no" - - unknown - - not reported - - Not Allowed To Collect - - prior_treatment: - term: - $ref: "_terms.yaml#/prior_treatment" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - progression_or_recurrence: - term: - $ref: "_terms.yaml#/progression_or_recurrence" - enum: - - "yes" - - "no" - - unknown - - not reported - - Not Allowed To Collect - - residual_disease: - term: - $ref: "_terms.yaml#/residual_disease" - enum: - - R0 - - R1 - - R2 - - RX - - site_of_resection_or_biopsy: - term: - $ref: "_terms.yaml#/site_of_resection_or_biopsy" - type: string - - tissue_or_organ_of_origin: - term: - $ref: "_terms.yaml#/tissue_or_organ_of_origin" - type: string - - tumor_grade: - term: - $ref: "_terms.yaml#/tumor_grade" - type: string - - tumor_stage: - term: - $ref: "_terms.yaml#/tumor_stage" - type: string - - vascular_invasion_present: - term: - $ref: "_terms.yaml#/vascular_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - vital_status: - term: - $ref: "_terms.yaml#/vital_status" - enum: - - alive - - dead - - lost to follow-up - - unknown - - not reported - - Not Allowed To Collect - - pending # this is from TARGET RT clinical data - - year_of_diagnosis: - term: - $ref: "_terms.yaml#/year_of_diagnosis" - type: - - number - - "null" - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/experiment.yaml b/gdcdictionary/schemas/experiment.yaml deleted file mode 100644 index b60cd0682..000000000 --- a/gdcdictionary/schemas/experiment.yaml +++ /dev/null @@ -1,108 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "experiment" -title: Experiment -type: object -namespace: http://bloodprofilingatlas.org/bpa/ -category: administrative -program: '*' -project: '*' -description: > - A coordinated set of actions and observations designed to generate data, with the ultimate goal - of discovery or hypothesis testing. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: projects - backref: experiments - label: performed_for - target_type: project - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "experiment" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - number_experimental_group: - description: "The number denoting this experiment's place within the group within the whole." - type: - - integer - number_samples_per_experimental_group: - description: "The number of samples contained within this experimental group." - type: - - integer - experimental_description: - description: "A brief description of the experiment being performed." - type: - - string - experimental_intent: - description: "Summary of the goals the experiment is designed to discover." - type: - - string - associated_experiment: - description: "The submitter_id for any experiment with which this experiment is associated, paired, or matched." - type: - - string - type_of_sample: - description: "String indicator identifying the types of samples as contrived or clinical." - type: - - string - type_of_specimen: - description: "Broad description of the specimens used in the experiment." - type: - - string - marker_panel_description: - description: "Brief description of the marker panel used in this experiment." - type: string - somatic_mutations_identified: - description: "Are somatic mutations identified for this experiment?" - type: boolean - indels_identified: - description: "Are indels identified in this experiment?" - type: boolean - copy_numbers_identified: - description: "Are copy number variations identified in this experiment?" - type: boolean - type_of_data: - description: "Is the data raw or processed?" - enum: - - Raw - - Processed - data_description: - description: "Brief description of the data being provided for this experiment." - type: string - projects: - $ref: "_definitions.yaml#/to_one_project" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/experimental_metadata.yaml b/gdcdictionary/schemas/experimental_metadata.yaml deleted file mode 100644 index cd4f321a5..000000000 --- a/gdcdictionary/schemas/experimental_metadata.yaml +++ /dev/null @@ -1,77 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "experimental_metadata" -title: Experimental Metadata -type: object -namespace: http://gdc.nci.nih.gov -category: metadata_file -project: '*' -program: '*' -description: > - Data file containing the metadata for the experiment performed. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: experiment_metadata_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: experiments - backref: experiment_metadata_files - label: derived_from - target_type: experiment - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "experimental_metadata" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: - - string - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Experimental Metadata" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: - - string - experiments: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/exposure.yaml b/gdcdictionary/schemas/exposure.yaml deleted file mode 100644 index 76cfe72c9..000000000 --- a/gdcdictionary/schemas/exposure.yaml +++ /dev/null @@ -1,132 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "exposure" -title: Exposure -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Clinically relevant patient information not immediately resulting from genetic predispositions. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: cases - backref: exposures - label: describes - target_type: case - multiplicity: many_to_one - required: true - -preferred: - - cigarettes_per_day - - years_smoked - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "exposure" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - alcohol_history: - term: - $ref: "_terms.yaml#/alcohol_history" - type: string - - alcohol_intensity: - term: - $ref: "_terms.yaml#/alcohol_intensity" - type: string - - bmi: - term: - $ref: "_terms.yaml#/bmi" - type: number - - cigarettes_per_day: - term: - $ref: "_terms.yaml#/cigarettes_per_day" - type: number - - height: - term: - $ref: "_terms.yaml#/height" - type: number - - pack_years_smoked: - term: - $ref: "_terms.yaml#/pack_years_smoked" - type: number - - tobacco_smoking_onset_year: - term: - $ref: "_terms.yaml#/tobacco_smoking_onset_year" - type: integer - - tobacco_smoking_quit_year: - term: - $ref: "_terms.yaml#/tobacco_smoking_quit_year" - type: integer - - tobacco_smoking_status: - term: - $ref: "_terms.yaml#/tobacco_smoking_status" - enum: - - "1" - - "2" - - "3" - - "4" - - "5" - - "6" - - "7" - - Unknown - - Not Reported - - Not Allowed To Collect - - weight: - term: - $ref: "_terms.yaml#/weight" - type: number - - years_smoked: - term: - $ref: "_terms.yaml#/years_smoked" - type: number - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/family_history.yaml b/gdcdictionary/schemas/family_history.yaml deleted file mode 100644 index add3a1523..000000000 --- a/gdcdictionary/schemas/family_history.yaml +++ /dev/null @@ -1,98 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "family_history" -title: Family History -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Record of a patient's background regarding cancer events of blood relatives. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: cases - backref: family_histories - label: describes - target_type: case - multiplicity: many_to_one - required: true - - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "family_history" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - relative_with_cancer_history: - term: - $ref: "_terms.yaml#/relative_with_cancer_history" - enum: - - "yes" - - "no" - - unknown - - not reported - - relationship_type: - term: - $ref: "_terms.yaml#/relationship_type" - type: string - - relationship_gender: - term: - $ref: "_terms.yaml#/gender" - enum: - - female - - male - - unknown - - unspecified - - not reported - - relationship_age_at_diagnosis: - term: - $ref: "_terms.yaml#/relationship_age_at_diagnosis" - type: number - - relationship_primary_diagnosis: - term: - $ref: "_terms.yaml#/primary_diagnosis" - type: string - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/keyword.yaml b/gdcdictionary/schemas/keyword.yaml deleted file mode 100644 index 99a3a050f..000000000 --- a/gdcdictionary/schemas/keyword.yaml +++ /dev/null @@ -1,61 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "keyword" -title: Keyword -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "A keyword for a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: keywords - label: describe - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "keyword" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - keyword_name: - description: "The name of the keyword." - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/program.yaml b/gdcdictionary/schemas/program.yaml deleted file mode 100644 index 4504f8572..000000000 --- a/gdcdictionary/schemas/program.yaml +++ /dev/null @@ -1,41 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "program" -title: Program -type: object -category: administrative -program: '*' -project: '*' -description: > - A broad framework of goals to be achieved. (NCIt C52647) -additionalProperties: false -submittable: false -validators: null - -systemProperties: - - id - -required: - - name - - dbgap_accession_number - -uniqueKeys: - - [id] - - [name] - -links: [] - -# Program is the root entity and so it is the only entity -# without a project or parents. -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - name: - type: string - description: "Full name/title of the program." - dbgap_accession_number: - type: string - description: "The dbgap accession number provided for the program." diff --git a/gdcdictionary/schemas/project.yaml b/gdcdictionary/schemas/project.yaml deleted file mode 100644 index dc21d32f5..000000000 --- a/gdcdictionary/schemas/project.yaml +++ /dev/null @@ -1,147 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "project" -title: Project -type: object -program: '*' -project: '*' -category: administrative -description: > - Any specifically defined piece of work that is undertaken or attempted to meet a single - requirement. (NCIt C47885) -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - state - - released - - releasable - - intended_release_date - -required: - - code - - name - - dbgap_accession_number - - programs - -uniqueKeys: - - [ id ] - - [ code ] - -links: - - name: programs - backref: projects - label: member_of - target_type: program - multiplicity: many_to_one - required: true - -constraints: null - -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - description: "UUID for the project." # TOREVIEW - name: - type: string - description: "Display name/brief description for the project." # TOREVIEW - code: - type: string - description: "Unique identifier for the project." - investigator_name: - description: "Name of the principal investigator for the project." - type: string - investigator_affiliation: - description: "The investigator's affiliation with respect to a research institution." - type: string - date_collected: - description: "The date or date range in which the project data was collected." - type: string - availability_type: - description: "Is the project open or restricted?" - enum: - - Open - - Restricted - availability_mechanism: - description: "Mechanism by which the project will be made avilable." - type: string - support_source: - description: "The name of source providing support/grant resources." - type: string - support_id: - description: "The ID of the source providing support/grant resources." - type: string - programs: - $ref: "_definitions.yaml#/to_one" - description: > - Indicates that the project is logically part of the indicated project. - state: - description: | - The possible states a project can be in. All but `open` are - equivalent to some type of locked state. - default: open - enum: - # open: the only state users can perform 'upload' actions - # possible actions in `open`: - # - upload (no state change) - # - review -> review - # - release (project.released -> true) - - open - - # locked: admin has locked project for review - # possible actions in `locked`: - # - open -> open - # - submit -> submitted - # - release (project.released -> true) - - review - - # submitted: An admin has submitted project, it is locked against - # upload. - # possible actions in `submitted`: - # - process -> processing - # - release (project.released -> true) - - submitted - - # processing: The system is processing data in the project and - # is locked against upload and submission - # - (system transition to open) - # - release (project.released -> true) - - processing - - - # closed: The closed state is introduced to replace the - # ``legacy`` state and means that no further action - # can be taken on the project - # - (system transition to open) - # - release (project.released -> true) - - closed - - # DEPRECATED(2016-03-01): synonymous with closed. included for - # backwards compatibility - - legacy - - released: - description: | - To release a project is to tell the GDC to include all submitted - entities in the next GDC index. - default: false - type: boolean - - releasable: - description: | - A project can only be released by the user when `releasable` is true. - default: false - type: boolean - - intended_release_date: - description: Tracks a Project's intended release date. - type: string - format: date-time - dbgap_accession_number: - type: string - description: "The dbgap accession number provided for the project." diff --git a/gdcdictionary/schemas/projects/project1.yaml b/gdcdictionary/schemas/projects/project1.yaml deleted file mode 100644 index c5d141abe..000000000 --- a/gdcdictionary/schemas/projects/project1.yaml +++ /dev/null @@ -1,21 +0,0 @@ -##################################################################### -# Project 1 specific overrides -##################################################################### - -$schema: "http://json-schema.org/draft-04/schema#" - -##################################################################### -# Aliquot -##################################################################### - -id: "aliquot" -program: 'program1' -project: 'project1' -required: - - submitter_aliquot_id - - parents - - project_1_specific_thing - -properties: - project_1_specific_thing: -type: string diff --git a/gdcdictionary/schemas/publication.yaml b/gdcdictionary/schemas/publication.yaml deleted file mode 100644 index 2feb6a1ab..000000000 --- a/gdcdictionary/schemas/publication.yaml +++ /dev/null @@ -1,62 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "publication" -title: Publication -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "Publication for a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: publications - label: refers_to - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "publication" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - pmid: - type: string - doi: - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/read_group.yaml b/gdcdictionary/schemas/read_group.yaml deleted file mode 100644 index d1a8bdd4b..000000000 --- a/gdcdictionary/schemas/read_group.yaml +++ /dev/null @@ -1,225 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "read_group" -title: Read Group -type: object -description: "Sequencing reads from one lane of an NGS experiment." -namespace: http://gdc.nci.nih.gov -category: biospecimen -project: '*' -program: '*' -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: aliquots - label: derived_from - target_type: aliquot - multiplicity: many_to_one - required: true - backref: read_groups - -required: - - type - - submitter_id - - aliquots - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - id: - $ref: "_definitions.yaml#/UUID" - project_id: - $ref: "_definitions.yaml#/project_id" - submitter_id: - type: string - state: - $ref: "_definitions.yaml#/state" - type: - enum: [ "read_group" ] - experiment_name: - term: - $ref: "_terms.yaml#/experiment_name" - type: string - sequencing_center: - term: - $ref: "_terms.yaml#/sequencing_center" - type: string - sequencing_date: - $ref: "_definitions.yaml#/datetime" - platform: - term: - $ref: "_terms.yaml#/platform" - enum: - - Illumina - - SOLiD - - LS454 - - Ion Torrent - - Complete Genomics - - PacBio - - Other - instrument_model: - terms: - $ref: "_terms.yaml#/instrument_model" - enum: - - 454 GS FLX Titanium - - AB SOLiD 4 - - AB SOLiD 2 - - AB SOLiD 3 - - Complete Genomics - - Illumina HiSeq X Ten - - Illumina HiSeq X Five - - Illumina Genome Analyzer II - - Illumina Genome Analyzer IIx - - Illumina HiSeq 2000 - - Illumina HiSeq 2500 - - Illumina HiSeq 4000 - - Illumina MiSeq - - Illumina NextSeq - - Ion Torrent PGM - - Ion Torrent Proton - - PacBio RS - - Ion S5 XL System, Ion 530 Chip - - Other - library_strategy: - term: - $ref: "_terms.yaml#/library_strategy" - enum: - - WGS - - WXS - - RNA-Seq - - ChIP-Seq - - miRNA-Seq - - Bisulfite-Seq - - Validation - - Amplicon - - Other - RIN: - term: - $ref: "_terms.yaml#/RIN" - type: number - flow_cell_barcode: - term: - $ref: "_terms.yaml#/flow_cell_barcode" - type: string - includes_spike_ins: - term: - $ref: "_terms.yaml#/includes_spike_ins" - type: boolean - spike_ins_fasta: - term: - $ref: "_terms.yaml#/spike_ins_fasta" - type: string - spike_ins_concentration: - term: - $ref: "_terms.yaml#/spike_ins_concentration" - type: string - library_selection: - term: - $ref: "_terms.yaml#/library_selection" - enum: - - Hybrid_Selection - - PCR - - Affinity_Enrichment - - Poly-T_Enrichment - - RNA_Depletion - - Other - library_preparation_kit_name: - term: - $ref: "_terms.yaml#/library_preparation_kit_name" - type: string - library_preparation_kit_vendor: - term: - $ref: "_terms.yaml#/library_preparation_kit_vendor" - type: string - library_preparation_kit_catalog_number: - term: - $ref: "_terms.yaml#/library_preparation_kit_catalog_number" - type: string - library_preparation_kit_version: - term: - $ref: "_terms.yaml#/library_preparation_kit_version" - type: string - library_name: - term: - $ref: "_terms.yaml#/library_name" - type: string - target_capture_kit_name: # conditionally required for WXS etc - term: - $ref: "_terms.yaml#/target_capture_kit_name" - type: string - target_capture_kit_vendor: - term: - $ref: "_terms.yaml#/target_capture_kit_vendor" - type: string - target_capture_kit_catalog_number: - term: - $ref: "_terms.yaml#/target_capture_kit_catalog_number" - type: string - target_capture_kit_version: - term: - $ref: "_terms.yaml#/target_capture_kit_version" - type: string - target_capture_kit_target_region: - term: - $ref: "_terms.yaml#/target_capture_kit_target_region" - type: string - size_selection_range: - term: - $ref: "_terms.yaml#/size_selection_range" - type: string - adapter_name: - term: - $ref: "_terms.yaml#/adapter_name" - type: string - adapter_sequence: - term: - $ref: "_terms.yaml#/adapter_sequence" - type: string - to_trim_adapter_sequence: - term: - $ref: "_terms.yaml#/to_trim_adapter_sequence" - type: boolean - library_strand: - term: - $ref: "_terms.yaml#/library_strand" - enum: - - Unstranded - - First_Stranded - - Second_Stranded - base_caller_name: - term: - $ref: "_terms.yaml#/base_caller_name" - type: string - base_caller_version: - term: - $ref: "_terms.yaml#/base_caller_version" - type: string - is_paired_end: - term: - $ref: "_terms.yaml#/is_paired_end" - type: boolean - read_length: - type: integer - read_group_name: # it may be good to assign UUID to read group - description: "Read Group Name" - type: string - barcoding_applied: - description: "True/False: was barcoding applied?" - type: boolean - aliquots: - $ref: "_definitions.yaml#/to_one" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/read_group_qc.yaml b/gdcdictionary/schemas/read_group_qc.yaml deleted file mode 100644 index 9b235528c..000000000 --- a/gdcdictionary/schemas/read_group_qc.yaml +++ /dev/null @@ -1,133 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "read_group_qc" -title: Read Group QC -type: object -namespace: http://gdc.nci.nih.gov -category: notation -project: '*' -program: '*' -description: "GDC QC run metadata." -additionalProperties: false -submittable: false -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - exclusive: true - required: true - subgroup: - - name: submitted_aligned_reads_files - backref: read_group_qcs - label: data_from - target_type: submitted_aligned_reads - multiplicity: one_to_one - required: false - - name: submitted_unaligned_reads_files - backref: read_group_qcs - label: data_from - target_type: submitted_unaligned_reads - multiplicity: one_to_many - required: false - - name: read_groups - label: generated_from - target_type: read_group - multiplicity: many_to_one - required: true - backref: read_group_qcs - -required: - - submitter_id - - workflow_link - - type - - percent_gc_content - - encoding - - total_sequences - - basic_statistics - - per_base_sequence_quality - - per_tile_sequence_quality - - per_sequence_quality_score - - per_base_sequence_content - - per_sequence_gc_content - - per_base_n_content - - sequence_length_distribution - - sequence_duplication_levels - - overrepresented_sequences - - adapter_content - - kmer_content - - read_groups - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/workflow_properties" - type: - enum: [ "read_group_qc" ] - workflow_type: - term: - $ref: "_terms.yaml#/workflow_type" - enum: [ "Read Group Quality Control" ] - fastq_name: - term: - $ref: "_terms.yaml#/file_name" - type: string - percent_aligned: - description: "The percent of reads with at least one reported alignment." - type: integer - minimum: 0 - maximum: 100 - percent_gc_content: - term: - $ref: "_terms.yaml#/percent_gc_content" - type: integer - minimum: 0 - maximum: 100 - encoding: - term: - $ref: "_terms.yaml#/encoding" - type: string - total_aligned_reads: - description: "The total number of reads with at least one reported alignment." - type: integer - total_sequences: - term: - $ref: "_terms.yaml#/total_sequences" - type: integer - basic_statistics: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_sequence_quality: - $ref: "_definitions.yaml#/qc_metrics_state" - per_tile_sequence_quality: - $ref: "_definitions.yaml#/qc_metrics_state" - per_sequence_quality_score: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_sequence_content: - $ref: "_definitions.yaml#/qc_metrics_state" - per_sequence_gc_content: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_n_content: - $ref: "_definitions.yaml#/qc_metrics_state" - sequence_length_distribution: - $ref: "_definitions.yaml#/qc_metrics_state" - sequence_duplication_levels: - $ref: "_definitions.yaml#/qc_metrics_state" - overrepresented_sequences: - $ref: "_definitions.yaml#/qc_metrics_state" - adapter_content: - $ref: "_definitions.yaml#/qc_metrics_state" - kmer_content: - $ref: "_definitions.yaml#/qc_metrics_state" - submitted_aligned_reads_files: - $ref: "_definitions.yaml#/to_one" - submitted_unaligned_reads_files: - $ref: "_definitions.yaml#/to_many" - read_groups: - $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/sample.yaml b/gdcdictionary/schemas/sample.yaml deleted file mode 100644 index 7680e5cb3..000000000 --- a/gdcdictionary/schemas/sample.yaml +++ /dev/null @@ -1,686 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "sample" -title: Sample -type: object -namespace: http://gdc.nci.nih.gov -category: biospecimen -program: '*' -project: '*' -description: > - Any material sample taken from a biological entity for testing, diagnostic, propagation, treatment - or research purposes, including a sample obtained from a living organism or taken from the - biological object after halting of all its life functions. Biospecimen can contain one or more - components including but not limited to cellular molecules, cells, tissues, organs, body fluids, - embryos, and body excretory products. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - - cases - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -links: - - name: cases - backref: samples - label: derived_from - target_type: case - multiplicity: many_to_one #not sure - required: true - - name: diagnoses - backref: samples - label: related_to - target_type: diagnosis - multiplicity: many_to_one - required: false - -# Sample properties: keep TCGA-specific fields -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - description: > - The legacy barcode used before prior to the use UUIDs, varies by project. - For TCGA this is bcrsamplebarcode. - biospecimen_anatomic_site: - term: - $ref: "_terms.yaml#/biospecimen_anatomic_site" - enum: - - Abdomen - - Abdominal Wall - - Acetabulum - - Adenoid - - Adipose - - Adrenal - - Alveolar Ridge - - Amniotic Fluid - - Ampulla Of Vater - - Anal Sphincter - - Ankle - - Anorectum - - Antecubital Fossa - - Antrum - - Anus - - Aorta - - Aortic Body - - Appendix - - Aqueous Fluid - - Arm - - Artery - - Ascending Colon - - Ascending Colon Hepatic Flexure - - Auditory Canal - - Autonomic Nervous System - - Axilla - - Back - - Bile Duct - - Bladder - - Blood - - Blood Vessel - - Bone - - Bone Marrow - - Bowel - - Brain - - Brain Stem - - Breast - - Broad Ligament - - Bronchiole - - Bronchus - - Brow - - Buccal Cavity - - Buccal Mucosa - - Buttock - - Calf - - Capillary - - Cardia - - Carina - - Carotid Artery - - Carotid Body - - Cartilage - - Cecum - - Cell-Line - - Central Nervous System - - Cerebellum - - Cerebral Cortex - - Cerebrospinal Fluid - - Cerebrum - - Cervical Spine - - Cervix - - Chest - - Chest Wall - - Chin - - Clavicle - - Clitoris - - Colon - - Colon - Mucosa Only - - Common Duct - - Conjunctiva - - Connective Tissue - - Dermal - - Descending Colon - - Diaphragm - - Duodenum - - Ear - - Ear Canal - - Ear, Pinna (External) - - Effusion - - Elbow - - Endocrine Gland - - Epididymis - - Epidural Space - - Esophagogastric Junction - - Esophagus - - Esophagus - Mucosa Only - - Eye - - Fallopian Tube - - Femoral Artery - - Femoral Vein - - Femur - - Fibroblasts - - Fibula - - Finger - - Floor Of Mouth - - Fluid - - Foot - - Forearm - - Forehead - - Foreskin - - Frontal Cortex - - Frontal Lobe - - Fundus Of Stomach - - Gallbladder - - Ganglia - - Gastroesophageal Junction - - Gastrointestinal Tract - - Groin - - Gum - - Hand - - Hard Palate - - Head & Neck - - Head - Face Or Neck, Nos - - Heart - - Hepatic - - Hepatic Duct - - Hepatic Vein - - Hip - - Hippocampus - - Humerus - - Hypopharynx - - Ileum - - Ilium - - Index Finger - - Ischium - - Islet Cells - - Jaw - - Jejunum - - Joint - - Kidney - - Knee - - Lacrimal Gland - - Large Bowel - - Laryngopharynx - - Larynx - - Leg - - Leptomeninges - - Ligament - - Lip - - Liver - - Lumbar Spine - - Lung - - Lymph Node - - Lymph Node(s) Axilla - - Lymph Node(s) Cervical - - Lymph Node(s) Distant - - Lymph Node(s) Epitrochlear - - Lymph Node(s) Femoral - - Lymph Node(s) Hilar - - Lymph Node(s) Iliac-Common - - Lymph Node(s) Iliac-External - - Lymph Node(s) Inguinal - - Lymph Node(s) Internal Mammary - - Lymph Node(s) Mammary - - Lymph Node(s) Mesenteric - - Lymph Node(s) Occipital - - Lymph Node(s) Paraaortic - - Lymph Node(s) Parotid - - Lymph Node(s) Pelvic - - Lymph Node(s) Popliteal - - Lymph Node(s) Regional - - Lymph Node(s) Retroperitoneal - - Lymph Node(s) Scalene - - Lymph Node(s) Splenic - - Lymph Node(s) Subclavicular - - Lymph Node(s) Submandibular - - Lymph Node(s) Supraclavicular - - Lymph Nodes(s) Mediastinal - - Mandible - - Maxilla - - Mediastinal Soft Tissue - - Mediastinum - - Mesentery - - Mesothelium - - Middle Finger - - Mitochondria - - Muscle - - Nails - - Nasal Cavity - - Nasal Soft Tissue - - Nasopharynx - - Neck - - Nerve - - Nerve(s) Cranial - - Occipital Cortex - - Ocular Orbits - - Omentum - - Oral Cavity - - Oral Cavity - Mucosa Only - - Oropharynx - - Other - - Ovary - - Palate - - Pancreas - - Paraspinal Ganglion - - Parathyroid - - Parotid Gland - - Patella - - Pelvis - - Penis - - Pericardium - - Periorbital Soft Tissue - - Peritoneal Cavity - - Peritoneum - - Pharynx - - Pineal - - Pineal Gland - - Pituitary Gland - - Placenta - - Pleura - - Popliteal Fossa - - Prostate - - Pylorus - - Rectosigmoid Junction - - Rectum - - Retina - - Retro-Orbital Region - - Retroperitoneum - - Rib - - Ring Finger - - Round Ligament - - Sacrum - - Salivary Gland - - Scalp - - Scapula - - Sciatic Nerve - - Scrotum - - Seminal Vesicle - - Shoulder - - Sigmoid Colon - - Sinus - - Sinus(es), Maxillary - - Skeletal Muscle - - Skin - - Skull - - Small Bowel - - Small Bowel - Mucosa Only - - Small Finger - - Soft Tissue - - Spinal Column - - Spinal Cord - - Spleen - - Splenic Flexure - - Sternum - - Stomach - - Stomach - Mucosa Only - - Subcutaneous Tissue - - Synovium - - Temporal Cortex - - Tendon - - Testis - - Thigh - - Thoracic Spine - - Thorax - - Throat - - Thumb - - Thymus - - Thyroid - - Tibia - - Tongue - - Tonsil - - Tonsil (Pharyngeal) - - Trachea / Major Bronchi - - Transverse Colon - - Trunk - - Umbilical Cord - - Ureter - - Urethra - - Urinary Tract - - Uterus - - Uvula - - Vagina - - Vas Deferens - - Vein - - Venous - - Vertebra - - Vulva - - White Blood Cells - - Wrist - - Unknown - - Not Reported - - Not Allowed To Collect - composition: - term: - $ref: "_terms.yaml#/composition" - enum: - - Buccal Cells - - Buffy Coat - - Bone Marrow Components - - Bone Marrow Components NOS - - Control Analyte - - Cell - - Circulating Tumor Cell (CTC) - - Derived Cell Line - - EBV Immortalized - - Fibroblasts from Bone Marrow Normal - - Granulocytes - - Human Original Cells - - Lymphocytes - - Mononuclear Cells from Bone Marrow Normal - - Peripheral Blood Components NOS - - Peripheral Blood Nucleated Cells - - Pleural Effusion - - Plasma - - Peripheral Whole Blood - - Serum - - Saliva - - Sputum - - Solid Tissue - - Whole Bone Marrow - - Unknown - - Not Reported - - Not Allowed To Collect - current_weight: - term: - $ref: "_terms.yaml#/current_weight" - type: number - days_to_collection: - term: - $ref: "_terms.yaml#/days_to_collection" - type: integer - days_to_sample_procurement: - term: - $ref: "_terms.yaml#/days_to_sample_procurement" - type: integer - diagnosis_pathologically_confirmed: - term: - ref: "_terms.yaml#/diagnosis_pathologically_confirmed" - enum: - - "Yes" - - "No" - - Unknown - freezing_method: - term: - $ref: "_terms.yaml#/freezing_method" - type: string - initial_weight: - term: - $ref: "_terms.yaml#/initial_weight" - type: number - intermediate_dimension: - terms: - $ref: "_terms.yaml#/intermediate_dimension" - type: string - is_ffpe: - term: - $ref: "_terms.yaml#/is_ffpe" - type: boolean - longest_dimension: - terms: - $ref: "_terms.yaml#/longest_dimension" - type: string - method_of_sample_procurement: - term: - $ref: "_terms.yaml#/method_of_sample_procurement" - enum: - - Abdomino-perineal Resection of Rectum - - Anterior Resection of Rectum - - Aspirate - - Biopsy - - Blood Draw - - Bone Marrow Aspirate - - Core Biopsy - - Cystectomy - - Endo Rectal Tumor Resection - - Endoscopic Biopsy - - Endoscopic Mucosal Resection (EMR) - - Enucleation - - Excisional Biopsy - - Fine Needle Aspiration - - Full Hysterectomy - - Gross Total Resection - - Hand Assisted Laparoscopic Radical Nephrectomy - - Hysterectomy NOS - - Incisional Biopsy - - Indeterminant - - Laparoscopic Biopsy - - Laparoscopic Partial Nephrectomy - - Laparoscopic Radical Nephrectomy - - Laparoscopic Radical Prostatectomy with Robotics - - Laparoscopic Radical Prostatectomy without Robotics - - Left Hemicolectomy - - Lobectomy - - Local Resection (Exoresection; wall resection) - - Lumpectomy - - Modified Radical Mastectomy - - Needle Biopsy - - Open Craniotomy - - Open Partial Nephrectomy - - Open Radical Nephrectomy - - Open Radical Prostatectomy - - Orchiectomy - - Other - - Other Surgical Resection - - Pan-Procto Colectomy - - Pneumonectomy - - Right Hemicolectomy - - Sigmoid Colectomy - - Simple Mastectomy - - Subtotal Resection - - Surgical Resection - - Thoracoscopic Biopsy - - Total Colectomy - - Total Mastectomy - - Transplant - - Transurethral resection (TURBT) - - Transverse Colectomy - - Tumor Resection - - Wedge Resection - - Unknown - - Not Reported - - Not Allowed To Collect - oct_embedded: - term: - $ref: "_terms.yaml#/oct_embedded" - type: string - preservation_method: - term: - $ref: "_terms.yaml#/preservation_method" - enum: - - Cryopreserved - - FFPE - - Fresh - - OCT - - Snap Frozen - - Frozen - - Unknown - - Not Reported - - Not Allowed To Collect - sample_type: - description: "Characterization of the sample as either clinical or contrived." - enum: - - Additional Metastatic - - Additional - New Primary - - Blood Derived Cancer - Bone Marrow, Post-treatment - - Blood Derived Cancer - Peripheral Blood, Post-treatment - - Blood Derived Normal - - Bone Marrow Normal - - Buccal Cell Normal - - Cell Line Derived Xenograft Tissue - - Cell Lines - - cfDNA - - Circulating Tumor Cell (CTC) - - Control Analyte - - Clinical - - Contrived - - ctDNA - - DNA - - EBV Immortalized Normal - - FFPE Recurrent - - FFPE Scrolls - - Fibroblasts from Bone Marrow Normal - - GenomePlex (Rubicon) Amplified DNA - - Granulocytes - - Human Tumor Original Cells - - Metastatic - - Mononuclear Cells from Bone Marrow Normal - - Primary Blood Derived Cancer - Peripheral Blood - - Recurrent Blood Derived Cancer - Peripheral Blood - - Pleural Effusion - - Primary Blood Derived Cancer - Bone Marrow - - Primary Tumor - - Primary Xenograft Tissue - - Post neo-adjuvant therapy - - Recurrent Blood Derived Cancer - Bone Marrow - - Recurrent Tumor - - Repli-G (Qiagen) DNA - - Repli-G X (Qiagen) DNA - - RNA - - Slides - - Solid Tissue Normal - - Total RNA - - Xenograft Tissue - - Unknown - - Not Reported - - Not Allowed To Collect - sample_type_id: - term: - $ref: "_terms.yaml#/sample_type_id" - enum: - - '01' - - '02' - - '03' - - '04' - - '05' - - '06' - - '07' - - '08' - - '09' - - '10' - - '11' - - '12' - - '13' - - '14' - - '15' - - '16' - - '20' - - '40' - - '41' - - '42' - - '50' - - '60' - - '61' - - '99' - sample_volume: - description: "The volume of the sample in mL." - type: number - shortest_dimension: - term: - $ref: "_terms.yaml#/shortest_dimension" - type: string - time_between_clamping_and_freezing: - term: - $ref: "_terms.yaml#/time_between_clamping_and_freezing" - type: string - time_between_excision_and_freezing: - term: - $ref: "_terms.yaml#/time_between_excision_and_freezing" - type: string - tissue_type: - term: - $ref: "_terms.yaml#/tissue_type" - enum: - - Tumor - - Normal - - Abnormal - - Peritumoral - - Contrived - - Unknown - - Not Reported - - Not Allowed To Collect - tumor_code: - term: - $ref: "_terms.yaml#/tumor_code" - enum: - - Non cancerous tissue - - Diffuse Large B-Cell Lymphoma (DLBCL) - - Lung Cancer (all types) - - Lung Adenocarcinoma - - Non-small Cell Lung Carcinoma (NSCLC) - - Colon Cancer (all types) - - Breast Cancer (all types) - - Cervical Cancer (all types) - - Anal Cancer (all types) - - Acute lymphoblastic leukemia (ALL) - - Acute myeloid leukemia (AML) - - Induction Failure AML (AML-IF) - - Neuroblastoma (NBL) - - Osteosarcoma (OS) - - Ewing sarcoma - - Wilms tumor (WT) - - Clear cell sarcoma of the kidney (CCSK) - - Rhabdoid tumor (kidney) (RT) - - CNS, ependymoma - - CNS, glioblastoma (GBM) - - CNS, rhabdoid tumor - - CNS, low grade glioma (LGG) - - CNS, medulloblastoma - - CNS, other - - NHL, anaplastic large cell lymphoma - - NHL, Burkitt lymphoma (BL) - - Rhabdomyosarcoma - - Soft tissue sarcoma, non-rhabdomyosarcoma - - Castration-Resistant Prostate Cancer (CRPC) - - Prostate Cancer - - Hepatocellular Carcinoma (HCC) - tumor_code_id: - term: - $ref: "_terms.yaml#/tumor_code_id" - enum: - - "00" - - "01" - - "02" - - "03" - - "04" - - "10" - - "20" - - "21" - - "30" - - "40" - - "41" - - "50" - - "51" - - "52" - - "60" - - "61" - - "62" - - "63" - - "64" - - "65" - - "70" - - "71" - - "80" - - "81" - tumor_descriptor: - term: - $ref: "_terms.yaml#/tumor_descriptor" - enum: - - Metastatic - - Not Applicable - - Primary - - Recurrence - - Xenograft - - NOS - - Unknown - - Not Reported - - Not Allowed To Collect - description: "A description of the tumor from which the sample was derived." # TOREVIEW - cases: - $ref: "_definitions.yaml#/to_one" - diagnoses: - $ref: "_definitions.yaml#/to_one" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide.yaml b/gdcdictionary/schemas/slide.yaml deleted file mode 100644 index 2812c2d0f..000000000 --- a/gdcdictionary/schemas/slide.yaml +++ /dev/null @@ -1,138 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide" -title: Slide -type: object -namespace: http://gdc.nci.nih.gov -category: biospecimen -program: '*' -project: '*' -description: > - A digital image, microscopic or otherwise, of any sample, portion, or sub-part thereof. (GDC) -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: samples - backref: slides - label: derived_from - target_type: sample - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - samples - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -# slide properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - apoptotic_concentration: - description: "The concentration, in cells/mL, of apoptotic cells in the slide blood." - type: number - ctc_concentration: - description: "The concentration, in cells/mL, of traditional CTC cells (intact and enlarged cell and nucleus, cytokeratin positive, and CD45 negative) in the slide blood." - type: number - ctc_low_concentration: - description: "The concentration, in cells/mL, of CTC-low cells (those with low cytokeratin levels compared to traditional CTCs) in the slide blood." - type: number - ctc_small_concentration: - description: "The concentration, in cells/mL, of CTC-small cells (those with a small nuclear and cellular size relative to traditional CTCs) in the slide blood." - type: number - section_location: - term: - $ref: "_terms.yaml#/section_location" - type: string - methanol_added: - description: "True/False indicator for if methanol was used in the slide preparation process." - type: boolean - number_proliferating_cells: - term: - $ref: "_terms.yaml#/number_proliferating_cells" - type: integer - number_nucleated_cells: - description: "The total number of nucleated cells identified on the slide." - type: integer - percent_tumor_cells: - term: - $ref: "_terms.yaml#/percent_tumor_cells" - type: number - percent_tumor_nuclei: - term: - $ref: "_terms.yaml#/percent_tumor_nuclei" - type: number - percent_normal_cells: - term: - $ref: "_terms.yaml#/percent_normal_cells" - type: number - percent_necrosis: - term: - $ref: "_terms.yaml#/percent_necrosis" - type: number - percent_stromal_cells: - term: - $ref: "_terms.yaml#/percent_stromal_cells" - type: number - percent_inflam_infiltration: - term: - $ref: "_terms.yaml#/percent_inflam_infiltration" - type: number - percent_lymphocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_lymphocyte_infiltration" - type: number - percent_monocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_monocyte_infiltration" - type: number - percent_granulocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_granulocyte_infiltration" - type: number - percent_neutrophil_infiltration: - term: - $ref: "_terms.yaml#/percent_neutrophil_infiltration" - type: number - percent_eosinophil_infiltration: - term: - $ref: "_terms.yaml#/percent_eosinophil_infiltration" - type: number - run_datetime: - $ref: "_definitions.yaml#/datetime" - run_name: - description: "Name, number, or other identifier given to this slide's run." - type: string - slide_identifier: - description: "Unique identifier given to the this slide." - type: string - samples: - $ref: "_definitions.yaml#/to_many" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide_count.yaml b/gdcdictionary/schemas/slide_count.yaml deleted file mode 100644 index 30002260c..000000000 --- a/gdcdictionary/schemas/slide_count.yaml +++ /dev/null @@ -1,100 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide_count" -title: Slide Count -type: object -namespace: http://gdc.nci.nih.gov -category: notation -program: '*' -project: '*' -description: > - Information pertaining to processed results obtained from slides; often in the form of counts. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: slides - backref: slide_counts - label: data_from - target_type: slide - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - slides - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "slide_count" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - cell_type: - description: "The type of cell being counted or measured." - type: string - cell_identifier: - description: "An alternative identifier for a given cell type." - type: string - cell_count: - description: "Raw count of a particular cell type." - type: integer - ck_signal: - description: "Numeric quantification of the CK signal." - type: number - biomarker_signal: - description: "Numeric quantification of the biomarker signal." - type: number - er_localization: - description: "Cellular localization of the endoplasmic reticulum as determined by staining." - enum: - - Nuclear - - Cytoplasmic - - Both - - None - - Not Determined - frame_identifier: - description: "Name, number, or other identifier given to the frame of the slide from which this image was taken." - type: string - relative_nuclear_size: - description: "The ratio of the single cell's nucleus size to the average of the surrounding cells." - type: number - relative_nuclear_intensity: - description: "The ratio of the single cell's nuclear staining intensity to the average of the surrounding cells." - type: number - relative_cytokeratin_intensity: - description: "The ratio of the single cell's cytokeratin staining intensity to the average of the surrounding cells." - type: number - relative_er_intensity: - description: "The ratio of the single cell's endoplasmic reticulum staining intensity to the average of the surrounding cells." - type: number - run_name: - description: "The name or identifier given to the run that was used to generate this slide count." - type: string - slides: - $ref: "_definitions.yaml#/to_many" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide_image.yaml b/gdcdictionary/schemas/slide_image.yaml deleted file mode 100644 index 50681f71e..000000000 --- a/gdcdictionary/schemas/slide_image.yaml +++ /dev/null @@ -1,109 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide_image" -title: Slide Image -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing image of a slide. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: slides - backref: slide_images - label: data_from - target_type: slide - multiplicity: many_to_one - required: false - - name: core_metadata_collections - backref: slide_images - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "slide_image" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Biospecimen - - Slide Image - - Mass Cytometry - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: - - image - - Single Cell Image - - Raw IMC Data - - Single Channel IMC Image - - Antibody Panel Added - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - description: "Classification of the slide type with respect to its experimental use." - enum: - - Diagnostic Slide - - Tissue Slide - cell_type: - description: "The type of cell being imaged or otherwised analysed." - type: string - cell_identifier: - description: "An alternative identifier for a given cell type." - type: string - cell_count: - description: "Count of the cell type being imaged or otherwise analysed." - type: integer - frame_identifier: - description: "Name, number, or other identifier given to the frame of the slide from which this image was taken." - type: string - panel_used: - description: "Name or other identifier given to the panel used during an IMC run." - type: string - protocol_used: - description: "Name or other identifier given to the protocol used during an IMC run." - type: string - run_name: - description: "Name, number, or other identifier given to the run that generated this slide image." - type: string - slides: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_aligned_reads.yaml b/gdcdictionary/schemas/submitted_aligned_reads.yaml deleted file mode 100644 index 59db76bae..000000000 --- a/gdcdictionary/schemas/submitted_aligned_reads.yaml +++ /dev/null @@ -1,95 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_aligned_reads" -title: Submitted Aligned Reads -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing aligned reads that are used as input to GDC workflows. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: read_groups - backref: submitted_aligned_reads_files # pretty ugly - label: data_from - target_type: read_group - multiplicity: one_to_many - required: false - - name: core_metadata_collections - backref: submitted_aligned_reads_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_aligned_reads" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: - - Aligned Reads - - Alignment Coordinates - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - BAM - - BED - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - enum: - - WGS - - WXS - - Low Pass WGS - - Validation - - RNA-Seq - - miRNA-Seq - - Total RNA-Seq - - DNA Panel - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_copy_number.yaml b/gdcdictionary/schemas/submitted_copy_number.yaml deleted file mode 100644 index 2bc9d772c..000000000 --- a/gdcdictionary/schemas/submitted_copy_number.yaml +++ /dev/null @@ -1,91 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_copy_number" -title: Submitted Copy Number -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing normalized copy number information from an aliquot. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_copy_number_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - exclusive: true - required: false - subgroup: - - name: aliquots - backref: submitted_copy_number_files - label: derived_from - target_type: aliquot - multiplicity: one_to_one - required: false - - name: read_groups - backref: submitted_copy_number_files - label: derived_from - target_type: read_group - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_copy_number" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: string - data_type: - term: - $ref: "_terms.yaml#/data_type" - type: string - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - type: string - aliquots: - $ref: "_definitions.yaml#/to_one" - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_methylation.yaml b/gdcdictionary/schemas/submitted_methylation.yaml deleted file mode 100644 index 10408f5f1..000000000 --- a/gdcdictionary/schemas/submitted_methylation.yaml +++ /dev/null @@ -1,86 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_methylation" -title: Submitted Methylation -type: object -namespace: https://www.bloodpac.org/ -category: data_file -program: '*' -project: '*' -description: "DNA methylation data files contain information on raw and normalized signal intensities, detection confidence and calculated beta values for methylated and unmethylated probes. DNA methylation is an epigenetic mark which can be associated with transcriptional inactivity when located in promoter regions." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_methylation_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: aliquots - backref: submitted_methylation_files - label: data_from - target_type: aliquot - multiplicity: many_to_one - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_methylation" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Methylation Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Methylation Intensity Values" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - IDAT - assay_method: - enum: - - Methylation Array - assay_instrument: - enum: - - Illumina - assay_instrument_model: - enum: - - Illumina Infinium HumanMethylation450 - - Illumina Infinium HumanMethylation450K - aliquots: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_somatic_mutation.yaml b/gdcdictionary/schemas/submitted_somatic_mutation.yaml deleted file mode 100644 index f51b502c4..000000000 --- a/gdcdictionary/schemas/submitted_somatic_mutation.yaml +++ /dev/null @@ -1,83 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_somatic_mutation" -title: Submitted Somatic Mutation -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing somatic mutation calls from a read group. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_somatic_mutations - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: read_groups - backref: submitted_somatic_mutations - label: derived_from - target_type: read_group - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_somatic_mutation" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: string - data_type: - term: - $ref: "_terms.yaml#/data_type" - type: string - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - type: string - total_variants: - description: "The total number of variants detected carrying a base change difference from the reference genome." - type: integer - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_unaligned_reads.yaml b/gdcdictionary/schemas/submitted_unaligned_reads.yaml deleted file mode 100644 index 4b72d4653..000000000 --- a/gdcdictionary/schemas/submitted_unaligned_reads.yaml +++ /dev/null @@ -1,92 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_unaligned_reads" -title: Submitted Unaligned Reads -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: "Data file containing unaligned reads that have not been GDC Harmonized." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: read_groups - backref: submitted_unaligned_reads_files # pretty ugly - label: data_from - target_type: read_group - multiplicity: many_to_one - required: false - - name: core_metadata_collections - backref: submitted_unaligned_reads_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_unaligned_reads" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Unaligned Reads" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - BAM - - FASTQ - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - enum: - - WGS - - WXS - - Low Pass WGS - - Validation - - RNA-Seq - - miRNA-Seq - - Total RNA-Seq - - DNA Panel - read_groups: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/treatment.yaml b/gdcdictionary/schemas/treatment.yaml deleted file mode 100644 index 4ed89da04..000000000 --- a/gdcdictionary/schemas/treatment.yaml +++ /dev/null @@ -1,217 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "treatment" -title: Treatment -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Record of the administration and intention of therapeutic agents provided to a patient to alter - the course of a pathologic process. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: diagnoses - backref: treatments - label: describes #need better term here - target_type: diagnosis - multiplicity: many_to_one - required: true - - - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "treatment" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - days_to_treatment: - term: - $ref: "_terms.yaml#/days_to_treatment" - type: number - - days_to_treatment_end: - term: - $ref: "_terms.yaml#/days_to_treatment_end" - type: number - - days_to_treatment_start: - term: - $ref: "_terms.yaml#/days_to_treatment_start" - type: number - - therapeutic_agents: - term: - $ref: "_terms.yaml#/therapeutic_agents" - type: string - - treatment_anatomic_site: - term: - $ref: "_terms.yaml#/treatment_anatomic_site" - enum: - - Abdomen, total - - Arm - - Ascites - - Axillary - - Body, total - - Bone - - Bone, non-spine - - Brain, focal - - Brain, whole - - Brain-C2 - - Breast - - Cervical - - Chest Wall - - Effusion - - Epitrochlear - - Eye - - Femoral - - Gastrointestinal, Colon - - Gastrointestinal, Gallbladder - - Gastrointestinal, Intestine - - Gastrointestinal, Liver - - Gastrointestinal, NOS - - Gastrointestinal, Pancreas - - Gastrointestinal, Rectum - - Gastrointestinal, Stomach - - Genitourinary, Bladder - - Genitourinary, Kidney - - Genitourinary, NOS - - Genitourinary, Prostate - - Genitourinary, Prostate and Seminal Vesicles - - Head - - Head, Face, or Neck - - Hilar - - Iliac-common - - Iliac-external - - Inguinal - - Internal Mammary Nodes - - Leg - - Lung - - Lymph Nodes - - Lymph node, distant (specify site) - - Lymph node, locoregional (specify site) - - Mantle - - Mediastinal - - Mediastinum - - Mesenteric - - Occipital - - Other - - Paraaortic - - Parametrium - - Parotid - - Pelvis - - Popliteal - - Primary tumor site - - Prostate - - Prostate Bed - - Prostate, Seminal Vesicles and Lymph Nodes - - Rectum - - Retroperitoneal - - Sacrum - - Seminal vesicles - - Shoulder - - Skin, lower extremity, local - - Skin, total - - Skin, trunk, local - - Skin, upper extremity, local - - Spine - - Spine, whole - - Splenic - - Submandibular - - Supraclavicular - - Supraclavicular/Axillary Level 3 - - Thorax - - Trunk - - Unknown - - Not Reported - - Not Allowed To Collect - - treatment_intent_type: - term: - $ref: "_terms.yaml#/treatment_intent_type" - type: string - - treatment_or_therapy: - term: - $ref: "_terms.yaml#/treatment_or_therapy" - enum: - - "yes" - - "no" - - unknown - - not reported - - treatment_outcome: - term: - $ref: "_terms.yaml#/treatment_outcome" - enum: - - Complete Response - - Partial Response - - Treatment Ongoing - - Treatment Stopped Due to Toxicity - - Unknown - - treatment_type: - term: - $ref: "_terms.yaml#/treatment_type" - enum: - - Ablation - - Chemotherapy - - Concurrent Chemoradiation - - Cryoablation - - Embolization - - Hormone Therapy - - Internal Radiation - - Immunotherapy (Including Vaccines) - - Other - - Pharmaceutical Therapy - - Radiation Therapy - - Stem Cell Treatment - - Surgery - - Targeted Molecular Therapy - - Unknown - - Not Reported - - Not Allowed To Collect - - diagnoses: - $ref: "_definitions.yaml#/to_one" - - project_id: - $ref: "_definitions.yaml#/project_id" - - # ======== Timestamps ======== - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" From 22bb1ee046b3c6bb7e3f37cac6ff1c505fbdd33f Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Thu, 21 May 2020 13:18:34 -0500 Subject: [PATCH 2/7] upgrade to new format update the travis config --- .travis.yml | 2 + gdcdictionary/schemas/_definitions.yaml | 32 +- gdcdictionary/schemas/_settings.yaml | 6 - gdcdictionary/schemas/_terms.yaml | 1841 ----------------- gdcdictionary/schemas/acknowledgement.yaml | 61 - .../schemas/aligned_reads_index.yaml | 77 - gdcdictionary/schemas/aliquot.yaml | 103 - gdcdictionary/schemas/case.yaml | 71 - gdcdictionary/schemas/clinical_test.yaml | 242 --- .../schemas/core_metadata_collection.yaml | 113 - gdcdictionary/schemas/demographic.yaml | 114 - gdcdictionary/schemas/diagnosis.yaml | 844 -------- gdcdictionary/schemas/experiment.yaml | 108 - .../schemas/experimental_metadata.yaml | 77 - gdcdictionary/schemas/exposure.yaml | 132 -- gdcdictionary/schemas/family_history.yaml | 98 - gdcdictionary/schemas/keyword.yaml | 61 - gdcdictionary/schemas/program.yaml | 41 - gdcdictionary/schemas/project.yaml | 147 -- gdcdictionary/schemas/projects/project1.yaml | 21 - gdcdictionary/schemas/publication.yaml | 62 - gdcdictionary/schemas/read_group.yaml | 225 -- gdcdictionary/schemas/read_group_qc.yaml | 133 -- gdcdictionary/schemas/sample.yaml | 686 ------ gdcdictionary/schemas/slide.yaml | 138 -- gdcdictionary/schemas/slide_count.yaml | 100 - gdcdictionary/schemas/slide_image.yaml | 109 - .../schemas/submitted_aligned_reads.yaml | 95 - .../schemas/submitted_copy_number.yaml | 91 - .../schemas/submitted_methylation.yaml | 86 - .../schemas/submitted_somatic_mutation.yaml | 83 - .../schemas/submitted_unaligned_reads.yaml | 92 - gdcdictionary/schemas/treatment.yaml | 217 -- 33 files changed, 18 insertions(+), 6290 deletions(-) delete mode 100644 gdcdictionary/schemas/_settings.yaml delete mode 100644 gdcdictionary/schemas/_terms.yaml delete mode 100644 gdcdictionary/schemas/acknowledgement.yaml delete mode 100644 gdcdictionary/schemas/aligned_reads_index.yaml delete mode 100644 gdcdictionary/schemas/aliquot.yaml delete mode 100644 gdcdictionary/schemas/case.yaml delete mode 100644 gdcdictionary/schemas/clinical_test.yaml delete mode 100644 gdcdictionary/schemas/core_metadata_collection.yaml delete mode 100644 gdcdictionary/schemas/demographic.yaml delete mode 100644 gdcdictionary/schemas/diagnosis.yaml delete mode 100644 gdcdictionary/schemas/experiment.yaml delete mode 100644 gdcdictionary/schemas/experimental_metadata.yaml delete mode 100644 gdcdictionary/schemas/exposure.yaml delete mode 100644 gdcdictionary/schemas/family_history.yaml delete mode 100644 gdcdictionary/schemas/keyword.yaml delete mode 100644 gdcdictionary/schemas/program.yaml delete mode 100644 gdcdictionary/schemas/project.yaml delete mode 100644 gdcdictionary/schemas/projects/project1.yaml delete mode 100644 gdcdictionary/schemas/publication.yaml delete mode 100644 gdcdictionary/schemas/read_group.yaml delete mode 100644 gdcdictionary/schemas/read_group_qc.yaml delete mode 100644 gdcdictionary/schemas/sample.yaml delete mode 100644 gdcdictionary/schemas/slide.yaml delete mode 100644 gdcdictionary/schemas/slide_count.yaml delete mode 100644 gdcdictionary/schemas/slide_image.yaml delete mode 100644 gdcdictionary/schemas/submitted_aligned_reads.yaml delete mode 100644 gdcdictionary/schemas/submitted_copy_number.yaml delete mode 100644 gdcdictionary/schemas/submitted_methylation.yaml delete mode 100644 gdcdictionary/schemas/submitted_somatic_mutation.yaml delete mode 100644 gdcdictionary/schemas/submitted_unaligned_reads.yaml delete mode 100644 gdcdictionary/schemas/treatment.yaml diff --git a/.travis.yml b/.travis.yml index 974c43a06..86f255299 100644 --- a/.travis.yml +++ b/.travis.yml @@ -6,6 +6,8 @@ python: before_script: - yes | python setup.py install - git clone https://github.com/uc-cdis/dictionaryutils +- git checkout feat/format_upgrade + script: - cd dictionaryutils; ./run_tests.sh; cd .. diff --git a/gdcdictionary/schemas/_definitions.yaml b/gdcdictionary/schemas/_definitions.yaml index bd91b5fdc..5208c6360 100644 --- a/gdcdictionary/schemas/_definitions.yaml +++ b/gdcdictionary/schemas/_definitions.yaml @@ -1,8 +1,8 @@ id: _definitions -UUID: +uuid: term: - $ref: "_terms.yaml#/UUID" + $ref: "_terms.yaml#/uuid" type: string pattern: "^[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}$" @@ -10,7 +10,7 @@ parent_uuids: type: array minItems: 1 items: - $ref: "#/UUID" + $ref: "#/uuid" uniqueItems: true foreign_key_project: @@ -18,11 +18,11 @@ foreign_key_project: # Allow true here because we can have other unique keys defined on # a target type additionalProperties: true - # Can either use 'id' which are Gen3 IDs (UUID) or 'code' + # Can either use 'id' which are Gen3 IDs (uuid) or 'code' # which is the user defined ID for project properties: id: - $ref: "#/UUID" + $ref: "#/uuid" code: type: string @@ -48,11 +48,11 @@ foreign_key: # Allow true here because we can have other unique keys defined on # a target type additionalProperties: True - # Can either use 'id' which are GDC IDs (UUID) or 'submitter_id' + # Can either use 'id' which are GDC IDs (uuid) or 'submitter_id' # which are user defined IDs ("submitter IDs in the backend") properties: id: - $ref: "#/UUID" + $ref: "#/uuid" submitter_id: type: string @@ -88,7 +88,7 @@ file_name: file_size: type: integer - term: + term: $ref: "_terms.yaml#/file_size" file_format: @@ -135,7 +135,7 @@ data_file_error_type: state: term: - $ref: "_terms.yaml#/state" + $ref: "_terms.yaml#/state" default: validated downloadable: - uploaded @@ -166,7 +166,7 @@ state: file_state: term: - $ref: "_terms.yaml#/file_state" + $ref: "_terms.yaml#/file_state" default: registered enum: - registered @@ -195,7 +195,7 @@ project_id: data_file_properties: id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: @@ -211,7 +211,7 @@ data_file_properties: file_size: $ref: "#/file_size" md5sum: - $ref: "#/md5sum" + $ref: "#/md5sum" file_state: $ref: "#/file_state" object_id: @@ -222,7 +222,7 @@ data_file_properties: $ref: "#/data_file_error_type" state_comment: type: string - description: > + description: > Optional comment about why the file is in the current state, mainly for invalid state. project_id: @@ -234,7 +234,7 @@ data_file_properties: workflow_properties: id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: @@ -264,14 +264,14 @@ ubiquitous_properties: type: type: string id: - $ref: "#/UUID" + $ref: "#/uuid" systemAlias: node_id submitter_id: type: - string description: > A project-specific identifier for a node. This property is the calling card/nickname/alias for - a unit of submission. It can be used in place of the UUID for identifying or recalling a node. + a unit of submission. It can be used in place of the uuid for identifying or recalling a node. state: $ref: "#/state" project_id: diff --git a/gdcdictionary/schemas/_settings.yaml b/gdcdictionary/schemas/_settings.yaml deleted file mode 100644 index d7e2171a4..000000000 --- a/gdcdictionary/schemas/_settings.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Global settings for the graph - -# Is the graph case centric, that we want -# to create a link between all children to case -# to expedite case filter on nodes -enable_case_cache: false diff --git a/gdcdictionary/schemas/_terms.yaml b/gdcdictionary/schemas/_terms.yaml deleted file mode 100644 index 0ca296bac..000000000 --- a/gdcdictionary/schemas/_terms.yaml +++ /dev/null @@ -1,1841 +0,0 @@ -id: _terms - -28s_16s_ribosomal_rna_ratio: - description: > - The 28S/18S ribosomal RNA band ratio used to assess the quality of total RNA. - termDef: - term: "28s/18s Ribosomal RNA Ratio" - source: null - cde_id: null - cde_version: null - term_url: null - -a260_a280_ratio: - description: > - Numeric value that represents the sample ratio of nucleic acid absorbance at 260 nm and 280 nm, - used to determine a measure of DNA purity. - termDef: - term: Nucleic Acid Absorbance at 260 And Absorbance at 280 DNA Purity Ratio Value - source: caDSR - cde_id: 5432595 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432595&version=1.0" - -adapter_name: # TOREVIEW - description: > - Name of the sequencing adapter. - -adapter_sequence: # TOREVIEW - description: > - Base sequence of the sequencing adapter. - -age_at_diagnosis: - description: > - Age at the time of diagnosis expressed in number of days since birth. - termDef: - term: Patient Diagnosis Age Day Value - source: caDSR - cde_id: 3225640 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225640&version=2.0" - -ajcc_clinical_m: - description: > - Extent of the distant metastasis for the cancer based on evidence obtained from clinical - assessment parameters determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Distant Metastasis M Stage - source: caDSR - cde_id: 3440331 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440331&version=1.0" - -ajcc_clinical_n: - description: > - Extent of the regional lymph node involvement for the cancer based on evidence obtained from - clinical assessment parameters determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Regional Lymph Node N Stage - source: caDSR - cde_id: 3440330 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440330&version=1.0" - -ajcc_clinical_stage: - description: > - Stage group determined from clinical information on the tumor (T), regional node (N) and - metastases (M) and by grouping cases with similar prognosis for cancer. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Group Stage - source: caDSR - cde_id: 3440332 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440332&version=1.0" - -ajcc_clinical_t: - description: > - Extent of the primary cancer based on evidence obtained from clinical assessment parameters - determined prior to treatment. - termDef: - term: Neoplasm American Joint Committee on Cancer Clinical Primary Tumor T Stage - source: caDSR - cde_id: 3440328 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440328&version=1.0" - -ajcc_pathologic_m: - description: > - Code to represent the defined absence or presence of distant spread or metastases (M) to - locations via vascular channels or lymphatics beyond the regional lymph nodes, using - criteria established by the American Joint Committee on Cancer (AJCC). - termDef: - term: American Joint Committee on Cancer Metastasis Stage Code - source: caDSR - cde_id: 3045439 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045439&version=1.0" - -ajcc_pathologic_n: - description: > - The codes that represent the stage of cancer based on the nodes present (N stage) according - to criteria based on multiple editions of the AJCC's Cancer Staging Manual. - termDef: - term: Neoplasm Disease Lymph Node Stage American Joint Committee on Cancer Code - source: caDSR - cde_id: 3203106 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203106&version=1.0" - -ajcc_pathologic_stage: - description: > - The extent of a cancer, especially whether the disease has spread from the original site to - other parts of the body based on AJCC staging criteria. - termDef: - term: Neoplasm Disease Stage American Joint Committee on Cancer Code - source: caDSR - cde_id: 3203222 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203222&version=1.0" - -ajcc_pathologic_t: - description: > - Code of pathological T (primary tumor) to define the size or contiguous extension of the - primary tumor (T), using staging criteria from the American Joint Committee on Cancer - (AJCC). - termDef: - term: American Joint Committee on Cancer Tumor Stage Code - source: caDSR - cde_id: 3045435 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045435&version=1.0" - -alcohol_history: - description: > - A response to a question that asks whether the participant has consumed at least 12 drinks of - any kind of alcoholic beverage in their lifetime. - termDef: - term: Alcohol Lifetime History Indicator - source: caDSR - cde_id: 2201918 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2201918&version=1.0" - -alcohol_intensity: - description: > - Category to describe the patient's current level of alcohol use as self-reported by the patient. - termDef: - term: Person Self-Report Alcoholic Beverage Exposure Category - source: caDSR - cde_id: 3457767 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3457767&version=1.0" - -aliquot_quantity: - description: > - The quantity in micrograms (ug) of the aliquot(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Aliquot Quantity - source: null - cde_id: null - cde_version: null - term_url: null - -aliquot_volume: - description: > - The volume in microliters (ml) of the aliquot(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Aliquot Volume - source: null - cde_id: null - cde_version: null - term_url: null - -amount: # TOREVIEW - description: > - Weight in grams or volume in mL. - -analyte_quantity: - description: > - The quantity in micrograms (ug) of the analyte(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Analyte Quantity - source: null - cde_id: null - cde_version: null - term_url: null - -analyte_type: - description: > - Text term that represents the kind of molecular specimen analyte. - termDef: - term: Molecular Specimen Type Text Name - source: caDSR - cde_id: 2513915 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2513915&version=2.0" - -analyte_type_id: - description: > - A single letter code used to identify a type of molecular analyte. - termDef: - term: Molecular Analyte Identification Code - source: caDSR - cde_id: 5432508 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432508&version=1.0" - -analyte_volume: - description: > - The volume in microliters (ml) of the analyte(s) derived from the analyte(s) shipped for - sequencing and characterization. - termDef: - term: Biospecimen Analyte Volume - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_b_symptoms: - description: > - Text term to signify whether lymphoma B-symptoms are present as noted in the patient's medical - record. - termDef: - term: Lymphoma B-Symptoms Medical Record Documented Indicator - source: caDSR - cde_id: 2902402 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2902402&version=1.0" - -ann_arbor_clinical_stage: - description: > - The classification of the clinically confirmed anatomic disease extent of lymphoma (Hodgkin's - and Non-Hodgkins) based on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Clinical Stage - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_extranodal_involvement: - description: > - Indicator that identifies whether a patient with malignant lymphoma has lymphomatous involvement - of an extranodal site. - termDef: - term: Lymphomatous Extranodal Site Involvement Indicator - source: caDSR - cde_id: 3364582 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3364582&version=1.0" - -ann_arbor_pathologic_stage: - description: > - The classification of the pathologically confirmed anatomic disease extent of lymphoma - (Hodgkin's and Non-Hodgkins) based on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Pathologic Stage - source: null - cde_id: null - cde_version: null - term_url: null - -ann_arbor_tumor_stage: - description: > - The classification of the anatomic disease extent of lymphoma (Hodgkin's and Non-Hodgkins) based - on the Ann Arbor Staging System. - termDef: - term: Ann Arbor Tumor Stage - source: null - cde_id: null - cde_version: null - term_url: null - -base_caller_name: # TOREVIEW - description: > - Name of the base caller. - -base_caller_version: # TOREVIEW - description: > - Version of the base caller. - -biomarker_name: - description: > - The name of the biomarker being tested for this specimen and set of test results. - termDef: - term: Biomarker Name - source: caDSR - cde_id: 5473 - cde_version: 11.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5473&version=2.31" - -biomarker_result: - description: > - Text term to define the results of genetic testing. - termDef: - term: Laboratory Procedure Genetic Abnormality Test Result Type - source: caDSR - cde_id: 3234680 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3234680&version=1.0" - -biomarker_test_method: - description: > - Text descriptor of a molecular analysis method used for an individual. - termDef: - term: Disease Detection Molecular Analysis Method Type - source: caDSR - cde_id: 3121575 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121575&version=1.0" - -biospecimen_anatomic_site: - description: > - Text term that represents the name of the primary disease site of the submitted tumor sample. - termDef: - term: Submitted Tumor Sample Primary Anatomic Site - source: caDSR - cde_id: 4742851 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4742851&version=1.0" - -bmi: - description: > - The body mass divided by the square of the body height expressed in units of kg/m^2. - termDef: - term: Body Mass Index (BMI) - source: caDSR - cde_id: 4973892 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4973892&version=1.0" - -burkitt_lymphoma_clinical_variant: - description: > - Burkitt's lymphoma categorization based on clinical features that differ from other forms of the - same disease. - termDef: - term: Burkitt Lymphoma Clinical Variant Type - source: caDSR - cde_id: 3770421 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3770421&version=1.0" - -cause_of_death: - description: > - Text term to identify the cause of death for a patient. - termDef: - term: Patient Death Reason - source: caDSR - cde_id: 2554674 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2554674&version=3.0" - -cea_level_preoperative: - description: > - Numeric value of the Carcinoembryonic antigen or CEA at the time before surgery. [Manually- - curated] - termDef: - term: Preoperative Carcinoembryonic Antigen Result Value - source: caDSR - cde_id: 2716510 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2716510&version=1.0" - -cigarettes_per_day: - description: > - The average number of cigarettes smoked per day. - termDef: - term: Smoking Use Average Number - source: caDSR - cde_id: 2001716 - cde_version: 4.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2001716&version=4.0" - -circumferential_resection_margin: - description: > - A value in millimeters indicating the measured length between a malignant lesion of the - colon or rectum and the nearest radial (or circumferential) border of tissue removed during - cancer surgery. - termDef: - term: Colorectal Surgical Margin Circumferential Distance Measurement - source: caDSR - cde_id: 64202 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64202&version=3.0" - -classification_of_tumor: - description: > - Text that describes the kind of disease present in the tumor specimen as related to a specific - timepoint. - termDef: - term: Tumor Tissue Disease Description Type - source: caDSR - cde_id: 3288124 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" - -colon_polyps_history: - description: > - Yes/No indicator to describe if the subject had a previous history of colon polyps as noted - in the history/physical or previous endoscopic report (s). - termDef: - term: Colon Carcinoma Polyp Occurrence Indicator - source: caDSR - cde_id: 3107197 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3107197&version=1.0" - -composition: - description: > - Text term that represents the cellular composition of the sample. - termDef: - term: Biospecimen Cellular Composition Type - source: caDSR - cde_id: 5432591 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432591&version=1.0" - -concentration: - description: > - Numeric value that represents the concentration of an analyte or aliquot extracted from the - sample or sample portion, measured in milligrams per milliliter. - termDef: - term: Biospecimen Analyte or Aliquot Extracted Concentration Milligram per Milliliter Value - source: caDSR - cde_id: 5432594 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432594&version=1.0" - -creation_datetime: - description: > - The datetime of portion creation encoded as seconds from epoch. - termDef: - term: Biospecimen Portion Creation Seconds Date/Time - source: caDSR - cde_id: 5432592 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432592&version=1.0" - -current_weight: - description: > - Numeric value that represents the current weight of the sample, measured in milligrams. - termDef: - term: Tissue Sample Current Weight Milligram Value - source: caDSR - cde_id: 5432606 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432606&version=1.0" - -data_category: # TOREVIEW - description: > - Broad categorization of the contents of the data file. - -data_file_error_type: # TOREVIEW - description: > - Type of error for the data file object. - -data_format: # TOREVIEW - description: > - Format of the data files. - -data_type: # TOREVIEW - description: > - Specific content type of the data file. - -datetime: - description: > - A combination of date and time of day in the form [-]CCYY-MM-DDThh:mm:ss[Z|(+|-)hh:mm] - -days_to_birth: - description: > - Time interval from a person's date of birth to the date of initial pathologic diagnosis, - represented as a calculated negative number of days. - termDef: - term: Person Birth Date Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008233 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008233&version=1.0" - -days_to_collection: - description: > - Time interval from the date of biospecimen collection to the date of initial pathologic - diagnosis, represented as a calculated number of days. - termDef: - term: Biospecimen Collection Date Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008340 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008340&version=1.0" - -days_to_death: - description: > - Time interval from a person's date of death to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Death Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3165475 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3165475&version=1.0" - -days_to_hiv_diagnosis: - description: > - Time interval from the date of the initial pathologic diagnosis to the date of human - immunodeficiency diagnosis, represented as a calculated number of days. - termDef: - term: Human Immunodeficiency Virus Diagnosis Subtract Initial Pathologic Diagnosis Time Duration Day Calculation Value - source: caDSR - cde_id: 4618491 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4618491&version=1.0" - -days_to_last_follow_up: - description: > - Time interval from the date of last follow up to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008273 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" - -days_to_last_known_disease_status: - description: > - Time interval from the date of last follow up to the date of initial pathologic diagnosis, - represented as a calculated number of days. - termDef: - term: Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3008273 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" - -days_to_new_event: - description: > - Time interval from the date of new tumor event including progression, recurrence and new - primary malignacies to the date of initial pathologic diagnosis, represented as a calculated - number of days. - termDef: - term: New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3392464 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" - -days_to_recurrence: - description: > - Time interval from the date of new tumor event including progression, recurrence and new primary - malignancies to the date of initial pathologic diagnosis, represented as a calculated number of - days. - termDef: - term: New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value - source: caDSR - cde_id: 3392464 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" - -days_to_sample_procurement: - description: > - The number of days from the date the patient was diagnosed to the date of the procedure that - produced the sample. - -days_to_treatment: - description: > - Number of days from date of initial pathologic diagnosis that treatment began. - termDef: - term: Days to Treatment Start - source: null - cde_id: null - cde_version: null - term_url: null - -days_to_treatment_end: - description: > - Time interval from the date of the initial pathologic diagnosis to the date of treatment end, - represented as a calculated number of days. - termDef: - term: Treatment End Subtract First Pathologic Diagnosis Day Calculation Value - source: caDSR - cde_id: 5102431 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102431&version=1.0" - -days_to_treatment_start: - description: > - Time interval from the date of the initial pathologic diagnosis to the start of treatment, - represented as a calculated number of days. - termDef: - term: Treatment Start Subtract First Pathologic Diagnosis Time Day Calculation Value - source: caDSR - cde_id: 5102411 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102411&version=1.0" - -diagnosis_pathologically_confirmed: - description: > - The histologic description of tissue or cells confirmed by a pathology review of frozen or - formalin fixed slide(s) completed after the diagnostic pathology review of the tumor sample used - to extract analyte(s). - termDef: - term: Post-Diagnostic Pathology Review Confirmation - source: null - cde_id: null - cde_version: null - term_url: null - -dlco_ref_predictive_percent: - description: > - The value, as a percentage of predicted lung volume, measuring the amount of carbon monoxide - detected in a patient's lungs. - termDef: - term: Lung Carbon Monoxide Diffusing Capability Test Assessment Predictive Value Percentage Value - source: caDSR - cde_id: 2180255 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2180255&version=1.0" - -encoding: - description: > - Version of ASCII encoding of quality values found in the file. - termDef: - term: Encoding - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -estrogen_receptor_percent_positive_ihc: - description: > - Classification to represent ER Positive results expressed as a percentage value. - termDef: - term: ER Level Cell Percentage Category - source: caDSR - cde_id: 3128341 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128341&version=1.0" - -estrogen_receptor_result_ihc: - description: > - Text term to represent the overall result of Estrogen Receptor (ER) testing. - termDef: - term: Breast Carcinoma Estrogen Receptor Status - source: caDSR - cde_id: 2957359 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957359&version=2.0" - -ethnicity: - description: > - An individual's self-described social and cultural grouping, specifically whether an individual - describes themselves as Hispanic or Latino. The provided values are based on the categories - defined by the U.S. Office of Management and Business and used by the U.S. Census Bureau. - termDef: - term: Ethnic Group Category Text - source: caDSR - cde_id: 2192217 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192217&version=2.0" - -experiment_name: # TOREVIEW - description: > - Submitter-defined name for the experiment. - -experimental_strategy: # TOREVIEW - description: > - The sequencing strategy used to generate the data file. - -fastq_name: # TOREVIEW - description: > - Names of FASTQs. - -fev1_ref_post_bronch_percent: - description: > - The percentage comparison to a normal value reference range of the volume of air that a - patient can forcibly exhale from the lungs in one second post-bronchodilator. - termDef: - term: Post Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value - source: caDSR - cde_id: 3302948 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302948&version=1.0" - -fev1_ref_pre_bronch_percent: - description: > - The percentage comparison to a normal value reference range of the volume of air that a - patient can forcibly exhale from the lungs in one second pre-bronchodilator. - termDef: - term: Pre Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value - source: caDSR - cde_id: 3302947 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302947&version=1.0" - -fev1_fvc_post_bronch_percent: - description: > - Percentage value to represent result of Forced Expiratory Volume in 1 second (FEV1) divided - by the Forced Vital Capacity (FVC) post-bronchodilator. - termDef: - term: Post Bronchodilator FEV1/FVC Percent Value - source: caDSR - cde_id: 3302956 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302956&version=1.0" - -fev1_fvc_pre_bronch_percent: - description: > - Percentage value to represent result of Forced Expiratory Volume in 1 second (FEV1) divided - by the Forced Vital Capacity (FVC) pre-bronchodilator. - termDef: - term: Pre Bronchodilator FEV1/FVC Percent Value - source: caDSR - cde_id: 3302955 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302955&version=1.0" - -figo_stage: - description: > - The extent of a cervical or endometrial cancer within the body, especially whether the - disease has spread from the original site to other parts of the body, as described by the - International Federation of Gynecology and Obstetrics (FIGO) stages. - termDef: - term: Gynecologic Tumor Grouping Cervical Endometrial FIGO 2009 Stage - source: caDSR - cde_id: 3225684 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225684&version=1.0" - -file_name: # TOREVIEW - description: > - The name (or part of a name) of a file (of any type). - -file_size: # TOREVIEW - description: > - The size of the data file (object) in bytes. - -file_state: # TOREVIEW - description: > - The current state of the data file object. - -flow_cell_barcode: # TOREVIEW - description: > - Flow Cell Barcode. - -freezing_method: - description: > - Text term that represents the method used for freezing the sample. - termDef: - term: Tissue Sample Freezing Method Type - source: caDSR - cde_id: 5432607 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432607&version=1.0" - -gender: - description: > - Text designations that identify gender. Gender is described as the assemblage of properties that - distinguish people on the basis of their societal roles. [Explanatory Comment 1: Identification - of gender is based upon self-report and may come from a form, questionnaire, interview, etc.] - termDef: - term: Person Gender Text Type - source: caDSR - cde_id: 2200604 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2200604&version=3.0" - -height: - description: > - The height of the patient in centimeters. - termDef: - term: Patient Height Measurement - source: caDSR - cde_id: 649 - cde_version: 4.1 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=649&version=4.1" - -her2_erbb2_percent_positive_ihc: - description: > - Classification to represent the number of positive HER2/ERBB2 cells in a specimen or sample. - termDef: - term: HER2 ERBB Positive Finding Cell Percentage Category - source: caDSR - cde_id: 3086980 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3086980&version=1.0" - -her2_erbb2_result_fish: - description: > - the type of outcome for HER2 as determined by an in situ hybridization (ISH) assay. - termDef: - term: Laboratory Procedure HER2/neu in situ Hybridization Outcome Type - source: caDSR - cde_id: 2854089 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2854089&version=1.0" - -her2_erbb2_result_ihc: - description: > - Text term to signify the result of the medical procedure that involves testing a sample of - blood or tissue for HER2 by histochemical localization of immunoreactive substances using - labeled antibodies as reagents. - termDef: - term: Laboratory Procedure HER2/neu Immunohistochemistry Receptor Status - source: caDSR - cde_id: 2957563 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957563&version=2.0" - -hiv_positive: - description: > - Text term to signify whether a physician has diagnosed HIV infection in a patient. - termDef: - term: Physician Diagnosed HIV Infection Personal Medical History Yes No Not Applicable Indicator - source: caDSR - cde_id: 4030799 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4030799&version=1.0" - -hpv_positive_type: - description: > - Text classification to represent the strain or type of human papillomavirus identified in an - individual. - termDef: - term: Human Papillomavirus Type - source: caDSR - cde_id: 2922649 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2922649&version=1.0" - -hpv_status: - description: > - The findings of the oncogenic HPV. - termDef: - term: Oncogenic Human Papillomavirus Result Type - source: caDSR - cde_id: 2230033 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2230033&version=1.0" - -includes_spike_ins: # TOREVIEW - description: > - Spike-in included? - -initial_weight: - description: > - Numeric value that represents the initial weight of the sample, measured in milligrams. - termDef: - term: Tissue Sample Initial Weight Milligram Value - source: caDSR - cde_id: 5432605 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432605&version=1.0" - -instrument_model: - description: > - Numeric value that represents the sample dimension that is greater than the shortest - dimension and less than the longest dimension, measured in millimeters. - termDef: - term: Tissue Sample Intermediate Dimension Millimeter Measurement - source: caDSR - cde_id: 5432604 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432604&version=1.0" - -intermediate_dimension: # TOREVIEW - description: > - Intermediate dimension of the sample, in millimeters. - -is_ffpe: - description: > - Indicator to signify whether or not the tissue sample was fixed in formalin and embedded in - paraffin (FFPE). - termDef: - term: Specimen Processing Formalin Fixed Paraffin Embedded Tissue Indicator - source: caDSR - cde_id: 4170557 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4170557&version=1.0" - -is_paired_end: # TOREVIEW - description: > - Are the reads paired end? - -last_known_disease_status: - description: > - Text term that describes the last known state or condition of an individual's neoplasm. - termDef: - term: Person Last Known Neoplasm Status - source: caDSR - cde_id: 5424231 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2759550&version=1.0" - -laterality: - description: > - For tumors in paired organs, designates the side on which the cancer originates. - termDef: - term: Primary Tumor Laterality - source: caDSR - cde_id: 827 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=827&version=3.0" - -ldh_level_at_diagnosis: - description: > - The 2 decimal place numeric laboratory value measured, assigned or computed related to the - assessment of lactate dehydrogenase in a specimen. - termDef: - term: Laboratory Procedure Lactate Dehydrogenase Result Integer::2 Decimal Place Value - source: caDSR - cde_id: 2798766 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2798766&version=1.0" - -ldh_normal_range_upper: - description: > - The top value of the range of statistical characteristics that are supposed to represent - accepted standard, non-pathological pattern for lactate dehydrogenase (units not specified). - termDef: - term: Laboratory Procedure Lactate Dehydrogenase Result Upper Limit of Normal Value - source: caDSR - cde_id: 2597015 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2597015&version=1.0" - -library_strategy: # TOREVIEW - description: > - Library strategy. - -library_selection: # TOREVIEW - description: > - Library Selection Method - -library_name: # TOREVIEW - description: > - Name of the library. - -library_preparation_kit_name: # TOREVIEW - description: > - Name of Library Preparation Kit - -library_preparation_kit_vendor: # TOREVIEW - description: > - Vendor of Library Preparation Kit - -library_preparation_kit_catalog_number: # TOREVIEW - description: > - Catalog of Library Preparation Kit - -library_preparation_kit_version: # TOREVIEW - description: > - Version of Library Preparation Kit - -library_strand: # TOREVIEW - description: > - Library stranded-ness. - -longest_dimension: - description: > - Numeric value that represents the longest dimension of the sample, measured in millimeters. - termDef: - term: Tissue Sample Longest Dimension Millimeter Measurement - source: caDSR - cde_id: 5432602 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432602&version=1.0" - -lymph_nodes_positive: - description: > - The number of lymph nodes involved with disease as determined by pathologic examination. - termDef: - term: Lymph Node(s) Positive Number - source: caDSR - cde_id: 89 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=89&version=3.0" - -lymphatic_invasion_present: - description: > - A yes/no indicator to ask if small or thin-walled vessel invasion is present, indicating - lymphatic involvement - termDef: - term: Lymphatic/Small vessel Invasion Ind - source: caDSR - cde_id: 64171 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64171&version=3.0" - -method_of_diagnosis: - description: > - The method used to initially the patient's diagnosis. - termDef: - term: Method of Diagnosis - source: null - cde_id: null - cde_version: null - term_url: null - -method_of_sample_procurement: - description: > - The method used to procure the sample used to extract analyte(s). - termDef: - term: Method of Sample Procurement - source: null - cde_id: null - cde_version: null - term_url: null - -md5sum: # TOREVIEW - description: > - The 128-bit hash value expressed as a 32 digit hexadecimal number used as a file's digital - fingerprint. - -microsatellite_instability_abnormal: - description: > - The yes/no indicator to signify the status of a tumor for microsatellite instability. - termDef: - term: Microsatellite Instability Occurrence Indicator - source: caDSR - cde_id: 3123142 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3123142&version=1.0" - -morphology: - description: > - The third edition of the International Classification of Diseases for Oncology, published in - 2000 used principally in tumor and cancer registries for coding the site (topography) and the - histology (morphology) of neoplasms. The study of the structure of the cells and their - arrangement to constitute tissues and, finally, the association among these to form organs. In - pathology, the microscopic process of identifying normal and abnormal morphologic - characteristics in tissues, by employing various cytochemical and immunocytochemical stains. A - system of numbered categories for representation of data. - termDef: - term: International Classification of Diseases for Oncology, Third Edition ICD-O-3 Histology Code - source: caDSR - cde_id: 3226275 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226275&version=1.0" - -new_event_anatomic_site: - description: > - Text term to specify the anatomic location of the return of tumor after treatment. - termDef: - term: New Neoplasm Event Occurrence Anatomic Site - source: caDSR - cde_id: 3108271 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3108271&version=2.0" - -new_event_type: - description: > - Text term to identify a new tumor event. - termDef: - term: New Neoplasm Event Type - source: caDSR - cde_id: 3119721 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3119721&version=1.0" - -normal_tumor_genotype_snp_match: - description: > - Text term that represents whether or not the genotype of the normal tumor matches or if the data - is not available. - termDef: - term: Normal Tumor Genotype Match Indicator - source: caDSR - cde_id: 4588156 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4588156&version=1.0" - -number_proliferating_cells: - description: > - Numeric value that represents the count of proliferating cells determined during pathologic - review of the sample slide(s). - termDef: - term: Pathology Review Slide Proliferating Cell Count - source: caDSR - cde_id: 5432636 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432636&version=1.0" - -oct_embedded: - description: > - Indicator of whether or not the sample was embedded in Optimal Cutting Temperature (OCT) compound. - termDef: - term: Tissue Sample Optimal Cutting Temperature Compound Embedding Indicator - source: caDSR - cde_id: 5432538 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432538&version=1.0" - -pack_years_smoked: - description: > - Numeric computed value to represent lifetime tobacco exposure defined as number of cigarettes - smoked per day x number of years smoked divided by 20. - termDef: - term: Person Cigarette Smoking History Pack Year Value - source: caDSR - cde_id: 2955385 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" - -percent_eosinophil_infiltration: - description: > - Numeric value to represent the percentage of infiltration by eosinophils in a tumor sample or - specimen. - termDef: - term: Specimen Eosinophilia Percentage Value - source: caDSR - cde_id: 2897700 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897700&version=2.0" - -percent_gc_content: - description: > - The overall %GC of all bases in all sequences. - termDef: - term: "%GC" - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -percent_granulocyte_infiltration: - description: > - Numeric value to represent the percentage of infiltration by granulocytes in a tumor sample or - specimen. - termDef: - term: Specimen Granulocyte Infiltration Percentage Value - source: caDSR - cde_id: 2897705 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897705&version=2.0" - -percent_inflam_infiltration: - description: > - Numeric value to represent local response to cellular injury, marked by capillary dilatation, - edema and leukocyte infiltration; clinically, inflammation is manifest by reddness, heat, pain, - swelling and loss of function, with the need to heal damaged tissue. - termDef: - term: Specimen Inflammation Change Percentage Value - source: caDSR - cde_id: 2897695 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897695&version=1.0" - -percent_lymphocyte_infiltration: - description: > - Numeric value to represent the percentage of infiltration by lymphocytes in a solid tissue - normal sample or specimen. - termDef: - term: Specimen Lymphocyte Infiltration Percentage Value - source: caDSR - cde_id: 2897710 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897710&version=2.0" - -percent_monocyte_infiltration: - description: > - Numeric value to represent the percentage of monocyte infiltration in a sample or specimen. - termDef: - term: Specimen Monocyte Infiltration Percentage Value - source: caDSR - cde_id: 5455535 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5455535&version=1.0" - -percent_necrosis: - description: > - Numeric value to represent the percentage of cell death in a malignant tumor sample or specimen. - termDef: - term: Malignant Neoplasm Necrosis Percentage Value - source: caDSR - cde_id: 2841237 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841237&version=1.0" - -percent_neutrophil_infiltration: - description: > - Numeric value to represent the percentage of infiltration by neutrophils in a tumor sample or - specimen. - termDef: - term: Malignant Neoplasm Neutrophil Infiltration Percentage Cell Value - source: caDSR - cde_id: 2841267 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841267&version=1.0" - -percent_normal_cells: - description: > - Numeric value to represent the percentage of normal cell content in a malignant tumor sample or - specimen. - termDef: - term: Malignant Neoplasm Normal Cell Percentage Value - source: caDSR - cde_id: 2841233 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841233&version=1.0" - -percent_stromal_cells: - description: > - Numeric value to represent the percentage of reactive cells that are present in a malignant - tumor sample or specimen but are not malignant such as fibroblasts, vascular structures, etc. - termDef: - term: Malignant Neoplasm Stromal Cell Percentage Value - source: caDSR - cde_id: 2841241 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841241&version=1.0" - -percent_tumor_cells: - description: > - Numeric value that represents the percentage of infiltration by granulocytes in a sample. - termDef: - term: Specimen Tumor Cell Percentage Value - source: caDSR - cde_id: 5432686 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432686&version=1.0" - -percent_tumor_nuclei: - description: > - Numeric value to represent the percentage of tumor nuclei in a malignant neoplasm sample or specimen. - termDef: - term: Malignant Neoplasm Neoplasm Nucleus Percentage Cell Value - source: caDSR - cde_id: 2841225 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841225&version=1.0" - -perineural_invasion_present: - description: > - a yes/no indicator to ask if perineural invasion or infiltration of tumor or cancer is - present. - termDef: - term: Tumor Perineural Invasion Ind - source: caDSR - cde_id: 64181 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64181&version=3.0" - -platform: # TOREVIEW - description: > - Name of the platform used to obtain data. - -portion_number: - description: > - Numeric value that represents the sequential number assigned to a portion of the sample. - termDef: - term: Biospecimen Portion Sequence Number - source: caDSR - cde_id: 5432711 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432711&version=1.0" - -portion_weight: - description: > - Numeric value that represents the sample portion weight, measured in milligrams. - termDef: - term: Biospecimen Portion Weight Milligram Value - source: caDSR - cde_id: 5432593 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432593&version=1.0" - -preservation_method: - description: > - Text term that represents the method used to preserve the sample. - termDef: - term: Tissue Sample Preservation Method Type - source: caDSR - cde_id: 5432521 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432521&version=1.0" - -primary_diagnosis: - description: > - Text term for the structural pattern of cancer cells used to define a microscopic diagnosis. - termDef: - term: Neoplasm Histologic Type Name - source: caDSR - cde_id: 3081934 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3081934&version=3.0" - -prior_malignancy: - description: > - Text term to describe the patient's history of prior cancer diagnosis and the spatial location - of any previous cancer occurrence. - termDef: - term: Prior Cancer Diagnosis Occurrence Description Text - source: caDSR - cde_id: 3382736 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3382736&version=2.0" - -prior_treatment: - description: > - A yes/no/unknown/not applicable indicator related to the administration of therapeutic agents - received before the body specimen was collected. - termDef: - term: Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown Not Applicable Indicator - source: caDSR - cde_id: 4231463 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" - -progesterone_receptor_percent_positive_ihc: - description: > - Classification to represent Progesterone Receptor Positive results expressed as a percentage - value. - termDef: - term: Progesterone Receptor Level Cell Percentage Category - source: caDSR - cde_id: 3128342 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128342&version=1.0" - -progesterone_receptor_result_ihc: - description: > - Text term to represent the overall result of Progresterone Receptor (PR) testing. - termDef: - term: Breast Carcinoma Progesterone Receptor Status - source: caDSR - cde_id: 2957357 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957357&version=2.0" - -progression_or_recurrence: - description: > - Yes/No/Unknown indicator to identify whether a patient has had a new tumor event - after initial treatment. - termDef: - term: New Neoplasm Event Post Initial Therapy Indicator - source: caDSR - cde_id: 3121376 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121376&version=1.0" - -project_id: # TOREVIEW - description: > - Unique ID for any specific defined piece of work that is undertaken or attempted to - meet a single requirement. - -qc_metric_state: - description: > - State classification given by FASTQC for the metric. Metric specific details about the states - are available on their website. - termDef: - term: QC Metric State - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/" - -race: - description: > - An arbitrary classification of a taxonomic group that is a division of a species. It usually - arises as a consequence of geographical isolation within a species and is characterized by - shared heredity, physical attributes and behavior, and in the case of humans, by common history, - nationality, or geographic distribution. The provided values are based on the categories defined - by the U.S. Office of Management and Business and used by the U.S. Census Bureau. - termDef: - term: Race Category Text - source: caDSR - cde_id: 2192199 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192199&version=1.0" - -read_length: # TOREVIEW - description: > - The length of the reads. - -read_group_name: # TOREVIEW - description: > - The name of the read group. - -relationship_age_at_diagnosis: - description: > - The age (in years) when the patient's relative was first diagnosed. - termDef: - term: Relative Diagnosis Age Value - source: caDSR - cde_id: 5300571 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5300571&version=1.0" - -relationship_type: - description: > - The subgroup that describes the state of connectedness between members of the unit of society - organized around kinship ties. - termDef: - term: Family Member Relationship Type - source: caDSR - cde_id: 2690165 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2690165&version=2.0" - -relative_with_cancer_history: - description: > - Indicator to signify whether or not an individual's biological relative has been diagnosed with - another type of cancer. - termDef: - term: Other Cancer Biological Relative History Indicator - source: caDSR - cde_id: 3901752 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3901752&version=1.0" - -residual_disease: - description: > - Text terms to describe the status of a tissue margin following surgical resection. - termDef: - term: Surgical Margin Resection Status - source: caDSR - cde_id: 2608702 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2608702&version=1.0" - -RIN: - description: > - A numerical assessment of the integrity of RNA based on the entire electrophoretic trace of the - RNA sample including the presence or absence of degradation products. - termDef: - term: Biospecimen RNA Integrity Number Value - source: caDSR - cde_id: 5278775 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5278775&version=1.0" - -sample_type: - description: > - Text term to describe the source of a biospecimen used for a laboratory test. - termDef: - term: Specimen Type Collection Biospecimen Type - source: caDSR - cde_id: 3111302 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3111302&version=2.0" - -sample_type_id: # TOREVIEW - description: > - The accompanying sample type id for the sample type. - -section_location: # TOREVIEW - description: > - Tissue source of the slide. - -sequencing_center: # TOREVIEW - description: > - Name of the center that provided the sequence files. - -shortest_dimension: - description: > - Numeric value that represents the shortest dimension of the sample, measured in millimeters. - termDef: - term: Tissue Sample Short Dimension Millimeter Measurement - source: caDSR - cde_id: 5432603 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432603&version=1.0" - -site_of_resection_or_biopsy: - description: > - The third edition of the International Classification of Diseases for Oncology, published in - 2000, used principally in tumor and cancer registries for coding the site (topography) and the - histology (morphology) of neoplasms. The description of an anatomical region or of a body part. - Named locations of, or within, the body. A system of numbered categories for representation of - data. - termDef: - term: International Classification of Diseases for Oncology, Third Edition ICD-O-3 Site Code - source: caDSR - cde_id: 3226281 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226281&version=1.0" - -size_selection_range: # TOREVIEW - description: > - Range of size selection. - -smoking_history: - description: > - Category describing current smoking status and smoking history as self-reported by a patient. - termDef: - term: Smoking History - source: caDSR - cde_id: 2181650 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" - -smoking_intensity: - description: > - Numeric computed value to represent lifetime tobacco exposure defined as number of cigarettes - smoked per day x number of years smoked divided by 20 - termDef: - term: Person Cigarette Smoking History Pack Year Value - source: caDSR - cde_id: 2955385 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" - -source_center: # TOREVIEW - description: > - Name of the center that provided the item. - -spectrophotometer_method: - description: > - Name of the method used to determine the concentration of purified nucleic acid within a - solution. - termDef: - term: Purification Nucleic Acid Solution Concentration Determination Method Type - source: caDSR - cde_id: 3008378 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008378&version=1.0" - -spike_ins_fasta: # TOREVIEW - description: > - Name of the FASTA file that contains the spike-in sequences. - -spike_ins_concentration: # TOREVIEW - description: > - Spike in concentration. - -state: # TOREVIEW - description: > - The current state of the object. - -target_capture_kit_name: # TOREVIEW - description: > - Name of Target Capture Kit. - -target_capture_kit_vendor: # TOREVIEW - description: > - Vendor of Target Capture Kit. - -target_capture_kit_catalog_number: # TOREVIEW - description: > - Catalog of Target Capture Kit. - -target_capture_kit_version: # TOREVIEW - description: > - Version of Target Capture Kit. - -target_capture_kit_target_region: # TOREVIEW - description: > - Target Capture Kit BED file. - -therapeutic_agents: - description: > - Text identification of the individual agent(s) used as part of a prior treatment regimen. - termDef: - term: Prior Therapy Regimen Text - source: caDSR - cde_id: 2975232 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2975232&version=1.0" - -time_between_clamping_and_freezing: - description: > - Numeric representation of the elapsed time between the surgical clamping of blood supply and - freezing of the sample, measured in minutes. - termDef: - term: Tissue Sample Clamping and Freezing Elapsed Minute Time - source: caDSR - cde_id: 5432611 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432611&version=1.0" - -time_between_excision_and_freezing: - description: > - Numeric representation of the elapsed time between the excision and freezing of the sample, - measured in minutes. - termDef: - term: Tissue Sample Excision and Freezing Elapsed Minute Time - source: caDSR - cde_id: 5432612 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432612&version=1.0" - -tissue_or_organ_of_origin: - description: > - Text term that describes the anatomic site of the tumor or disease. - termDef: - term: Tumor Disease Anatomic Site - source: caDSR - cde_id: 3427536 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3427536&version=3.0" - -tissue_type: - description: > - Text term that represents a description of the kind of tissue collected with respect to disease - status or proximity to tumor tissue. - termDef: - term: Tissue Sample Description Type - source: caDSR - cde_id: 5432687 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432687&version=1.0" - -to_trim_adapter_sequence: # TOREVIEW - description: > - Does the user suggest adapter trimming? - -tobacco_smoking_onset_year: - description: > - The year in which the participant began smoking. - termDef: - term: Started Smoking Year - source: caDSR - cde_id: 2228604 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228604&version=1.0" - -tobacco_smoking_quit_year: - description: > - The year in which the participant quit smoking. - termDef: - term: Stopped Smoking Year - source: caDSR - cde_id: 2228610 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228610&version=1.0" - -tobacco_smoking_status: - description: > - Category describing current smoking status and smoking history as self-reported by a - patient. - termDef: - term: Patient Smoking History Category - source: caDSR - cde_id: 2181650 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" - -total_sequences: - description: > - A count of the total number of sequences processed. - termDef: - term: Total Sequences - source: FastQC - cde_id: null - cde_version: null - term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" - -treatment_anatomic_site: - description: > - The anatomic site or field targeted by a treatment regimen or single agent therapy. - termDef: - term: Treatment Anatomic Site - source: null - cde_id: null - cde_version: null - term_url: null - -treatment_intent_type: - description: > - Text term to identify the reason for the administration of a treatment regimen. [Manually-curated] - termDef: - term: Treatment Regimen Intent Type - source: caDSR - cde_id: 2793511 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2793511&version=1.0" - -treatment_or_therapy: - description: > - A yes/no/unknown/not applicable indicator related to the administration of therapeutic agents - received before the body specimen was collected. - termDef: - term: Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown Not Applicable Indicator - source: caDSR - cde_id: 4231463 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" - -treatment_outcome: - description: > - Text term that describes the patient¿s final outcome after the treatment was administered. - termDef: - term: Treatment Outcome Type - source: caDSR - cde_id: 5102383 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102383&version=1.0" - -treatment_type: - description: > - Text term that describes the kind of treatment administered. - termDef: - term: Treatment Method Type - source: caDSR - cde_id: 5102381 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102381&version=1.0" - -tumor_grade: - description: > - Numeric value to express the degree of abnormality of cancer cells, a measure of differentiation - and aggressiveness. - termDef: - term: Neoplasm Histologic Grade - source: caDSR - cde_id: 2785839 - cde_version: 2.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2785839&version=2.0" - -tumor_code: # TOREVIEW - description: > - Diagnostic tumor code of the tissue sample source. - -tumor_code_id: # TOREVIEW - description: > - BCR-defined id code for the tumor sample. - -tumor_descriptor: - description: > - Text that describes the kind of disease present in the tumor specimen as related to a specific - timepoint. - termDef: - term: Tumor Tissue Disease Description Type - source: caDSR - cde_id: 3288124 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" - -tumor_stage: - description: > - The extent of a cancer in the body. Staging is usually based on the size of the tumor, whether - lymph nodes contain cancer, and whether the cancer has spread from the original site to other - parts of the body. The accepted values for tumor_stage depend on the tumor site, type, and - accepted staging system. These items should accompany the tumor_stage value as associated - metadata. - termDef: - term: Tumor Stage - source: NCIt - cde_id: C16899 - cde_version: null - term_url: "https://ncit.nci.nih.gov/ncitbrowser/pages/concept_details.jsf?dictionary=NCI%20Thesaurus&code=C16899" - -UUID: - description: > - A 128-bit identifier. Depending on the mechanism used to generate it, it is either guaranteed to - be different from all other UUIDs/GUIDs generated until 3400 AD or extremely likely to be - different. Its relatively small size lends itself well to sorting, ordering, and hashing of all - sorts, storing in databases, simple allocation, and ease of programming in general. - termDef: - term: Universally Unique Identifier - source: NCIt - cde_id: C54100 - cde_version: null - term_url: "https://ncit.nci.nih.gov/ncitbrowser/ConceptReport.jsp?dictionary=NCI_Thesaurus&version=16.02d&ns=NCI_Thesaurus&code=C54100" - -vascular_invasion_present: - description: > - The yes/no indicator to ask if large vessel or venous invasion was detected by surgery or - presence in a tumor specimen. - termDef: - term: Tumor Vascular Invasion Ind-3 - source: caDSR - cde_id: 64358 - cde_version: 3.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64358&version=3.0" - -vital_status: - description: > - The survival state of the person registered on the protocol. - termDef: - term: Patient Vital Status - source: caDSR - cde_id: 5 - cde_version: 5.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5&version=5.0" - -weight: - description: > - The weight of the patient measured in kilograms. - termDef: - term: Patient Weight Measurement - source: caDSR - cde_id: 651 - cde_version: 4.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=651&version=4.0" - -well_number: - description: > - Numeric value that represents the the well location within a plate for the analyte or - aliquot from the sample. - termDef: - term: Biospecimen Analyte or Aliquot Plate Well Number - source: caDSR - cde_id: 5432613 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432613&version=1.0" - -workflow_type: - description: > - Generic name for the workflow used to analyze a data set. - -year_of_birth: - description: > - Numeric value to represent the calendar year in which an individual was born. - termDef: - term: Year Birth Date Number - source: caDSR - cde_id: 2896954 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896954&version=1.0" - -year_of_diagnosis: - description: > - Numeric value to represent the year of an individual's initial pathologic diagnosis of cancer. - termDef: - term: Year of initial pathologic diagnosis - source: caDSR - cde_id: 2896960 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896960&version=1.0" - -year_of_death: - description: > - Numeric value to represent the year of the death of an individual. - termDef: - term: Year Death Number - source: caDSR - cde_id: 2897030 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897030&version=1.0" - -years_smoked: - description: > - Numeric value (or unknown) to represent the number of years a person has been smoking. - termDef: - term: Person Smoking Duration Year Count - source: caDSR - cde_id: 3137957 - cde_version: 1.0 - term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3137957&version=1.0" diff --git a/gdcdictionary/schemas/acknowledgement.yaml b/gdcdictionary/schemas/acknowledgement.yaml deleted file mode 100644 index cee5d3d99..000000000 --- a/gdcdictionary/schemas/acknowledgement.yaml +++ /dev/null @@ -1,61 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "acknowledgement" -title: Acknowledgement -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "Acknowledgement of an individual involved in a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: acknowledgements - label: contribute_to - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "acknowledgement" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - acknowledgee: - description: "The indvidiual or group being acknowledged by the project." - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/aligned_reads_index.yaml b/gdcdictionary/schemas/aligned_reads_index.yaml deleted file mode 100644 index e09ee3edc..000000000 --- a/gdcdictionary/schemas/aligned_reads_index.yaml +++ /dev/null @@ -1,77 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "aligned_reads_index" -title: Aligned Reads Index -type: object -namespace: http://gdc.nci.nih.gov -category: index_file -program: '*' -project: '*' -description: "Data file containing the index for a set of aligned reads." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: submitted_aligned_reads_files - backref: aligned_reads_indexes - label: derived_from - target_type: submitted_aligned_reads - multiplicity: one_to_one - required: false - - name: core_metadata_collections - backref: aligned_reads_indexes - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "aligned_reads_index" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Aligned Reads Index" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: [ "BAI" ] - submitted_aligned_reads_files: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/aliquot.yaml b/gdcdictionary/schemas/aliquot.yaml deleted file mode 100644 index 078cb17ac..000000000 --- a/gdcdictionary/schemas/aliquot.yaml +++ /dev/null @@ -1,103 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "aliquot" -title: Aliquot -type: object -category: biospecimen -program: '*' -project: '*' -description: > - Pertaining to a portion of the whole; any one of two or more samples of something, of the same - volume or weight. -additionalProperties: false -submittable: true -validators: [] - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - - samples - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -links: - - name: samples - backref: aliquots - label: derived_from - multiplicity: many_to_many - target_type: sample - required: true - -constraints: null - -# Aliquot properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - description: > - The legacy barcode used before prior to the use - UUIDs. For TCGA this is bcraliquotbarcode. - aliquot_quantity: - term: - $ref: "_terms.yaml#/aliquot_quantity" - type: number - aliquot_volume: - term: - $ref: "_terms.yaml#/aliquot_volume" - type: number - amount: - term: - $ref: "_terms.yaml#/amount" - type: number - analyte_type: - term: - $ref: "_terms.yaml#/analyte_type" - type: string - analyte_type_id: - term: - $ref: "_terms.yaml#/analyte_type_id" - enum: - - D - - E - - G - - H - - R - - S - - T - - W - - X - - Y - concentration: - term: - $ref: "_terms.yaml#/concentration" - type: number - project_id: - $ref: "_definitions.yaml#/project_id" - source_center: - term: - $ref: "_terms.yaml#/source_center" - type: string - samples: - $ref: "_definitions.yaml#/to_one" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/case.yaml b/gdcdictionary/schemas/case.yaml deleted file mode 100644 index 3db55f5a3..000000000 --- a/gdcdictionary/schemas/case.yaml +++ /dev/null @@ -1,71 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "case" -title: Case -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: > - The collection of all data related to a specific subject in the - context of a specific experiment. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: experiments - backref: cases - label: member_of - target_type: experiment - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - experiments - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -# Case properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - consent_codes: - type: array - items: - type: string - primary_site: - description: "Primary site for the case." - type: string - disease_type: - description: "Name of the disease for the case." - type: string - experiments: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/clinical_test.yaml b/gdcdictionary/schemas/clinical_test.yaml deleted file mode 100644 index 0ac0376f6..000000000 --- a/gdcdictionary/schemas/clinical_test.yaml +++ /dev/null @@ -1,242 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "clinical_test" -title: Clinical Test -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -project: '*' -program: '*' -description: > - Metadata concerning any clinical tests used in relation to a case diagnosis. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: cases - backref: clinical_tests - label: performed_for - target_type: case - multiplicity: many_to_one - required: true - - name: diagnoses - backref: clinical_tests - label: relates_to - target_type: diagnosis - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - biomarker_name - - biomarker_result - - biomarker_test_method - - cases - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "clinical_test" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - biomarker_name: - term: - $ref: "_terms.yaml#/biomarker_name" - type: string - - biomarker_result: - term: - $ref: "_terms.yaml#/biomarker_result" - enum: - - Amplification - - Gain - - Loss - - Normal - - Other - - Translocation - - Not Reported - - Not Allowed To Collect - - Pending - - biomarker_test_method: - term: - $ref: "_terms.yaml#/biomarker_test_method" - enum: - - Cytogenetics - - FISH - - IHC - - Karyotype - - NGS - - Nuclear Staining - - Other - - RT-PCR - - Southern - - Not Reported - - Not Allowed To Collect - - Pending - - cea_level_preoperative: - term: - $ref: "_terms.yaml#/cea_level_preoperative" - type: number - - dlco_ref_predictive_percent: - term: - $ref: "_terms.yaml#/dlco_ref_predictive_percent" - type: number - - estrogen_receptor_percent_positive_ihc: - term: - $ref: "_terms.yaml#/estrogen_receptor_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - estrogen_receptor_result_ihc: - term: - $ref: "_terms.yaml#/estrogen_receptor_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - fev1_ref_post_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_ref_post_bronch_percent" - type: number - - fev1_ref_pre_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_ref_pre_bronch_percent" - type: number - - fev1_fvc_post_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_fvc_post_bronch_percent" - type: number - - fev1_fvc_pre_bronch_percent: - term: - $ref: "_terms.yaml#/fev1_fvc_pre_bronch_percent" - type: number - - her2_erbb2_percent_positive_ihc: - term: - $ref: "_terms.yaml#/her2_erbb2_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - her2_erbb2_result_fish: - term: - $ref: "_terms.yaml#/her2_erbb2_result_fish" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - her2_erbb2_result_ihc: - term: - $ref: "_terms.yaml#/her2_erbb2_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - ldh_level_at_diagnosis: - term: - $ref: "_terms.yaml#/ldh_level_at_diagnosis" - type: number - - ldh_normal_range_upper: - term: - $ref: "_terms.yaml#/ldh_normal_range_upper" - type: number - - microsatellite_instability_abnormal: - term: - $ref: "_terms.yaml#/microsatellite_instability_abnormal" - enum: - - "Yes" - - "No" - - Unknown - - progesterone_receptor_percent_positive_ihc: - term: - $ref: "_terms.yaml#/progesterone_receptor_percent_positive_ihc" - enum: - - <1% - - 1-10% - - 11-20% - - 21-30% - - 31-40% - - 41-50% - - 51-60% - - 61-70% - - 71-80% - - 81-90% - - 91-100% - - progesterone_receptor_result_ihc: - term: - $ref: "_terms.yaml#/progesterone_receptor_result_ihc" - enum: - - Negative - - Not Performed - - Positive - - Unknown - - cases: - $ref: "_definitions.yaml#/to_one" - diagnoses: - $ref: "_definitions.yaml#/to_many" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/core_metadata_collection.yaml b/gdcdictionary/schemas/core_metadata_collection.yaml deleted file mode 100644 index 1a2bcebc6..000000000 --- a/gdcdictionary/schemas/core_metadata_collection.yaml +++ /dev/null @@ -1,113 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "core_metadata_collection" -title: Core Metadata Collection -type: object -namespace: https://dcp.bionimbus.org/ -category: administrative -program: '*' -project: '*' -description: > - Structured description of a collection of several dataset -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: core_metadata_collections - label: data_from - target_type: project - multiplicity: many_to_one - required: true - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -required: - - submitter_id - - type - - projects - -properties: - $ref: "_definitions.yaml#/ubiquitous_properties" - - contributor: - description: > - An entity responsible for making contributions to the resource. Examples of a Contributor include a person, an organization, or a service. Typically, the name of a Contributor should be used to indicate the entity. - type: string - - coverage: - description: > - The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant. Spatial topic and spatial applicability may be a named place or a location specified by its geographic coordinates. Temporal topic may be a named period, date, or date range. A jurisdiction may be a named administrative entity or a geographic place to which the resource applies. Recommended best practice is to use a controlled vocabulary such as the Thesaurus of Geographic Names [TGN] (http://www.getty.edu/research/tools/vocabulary/tgn/index.html). Where appropriate, named places or time periods can be used in preference to numeric identifiers such as sets of coordinates or date ranges. - type: string - - creator: - description: > - An entity primarily responsible for making the resource. Examples of a Creator include a person, an organization, or a service. Typically, the name of a Creator should be used to indicate the entity. - type: string - - date: - $ref: "_definitions.yaml#/datetime" - - description: - description: > - An account of the resource. Description may include but is not limited to: an abstract, a table of contents, a graphical representation, or a free-text account of the resource. - type: string - - format: - description: > - The file format, physical medium, or dimensions of the resource. Examples of dimensions include size and duration. Recommended best practice is to use a controlled vocabulary such as the list of Internet Media Types [MIME] (http://www.iana.org/assignments/media-types/). - type: string - - language: - description: > - A language of the resource. Recommended best practice is to use a controlled vocabulary such as RFC 4646 (http://www.ietf.org/rfc/rfc4646.txt). - type: string - - publisher: - description: > - An entity responsible for making the resource available. Examples of a Publisher include a person, an organization, or a service. Typically, the name of a Publisher should be used to indicate the entity. - type: string - - relation: - description: > - A related resource. Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system.  - type: string - - rights: - description: > - Information about rights held in and over the resource. Typically, rights information includes a statement about various property rights associated with the resource, including intellectual property rights. - type: string - - source: - description: > - A related resource from which the described resource is derived. The described resource may be derived from the related resource in whole or in part. Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system. - type: string - - subject: - description: > - The topic of the resource. Typically, the subject will be represented using keywords, key phrases, or classification codes. Recommended best practice is to use a controlled vocabulary. - type: string - - title: - description: > - A name given to the resource. Typically, a Title will be a name by which the resource is formally known. - type: string - - data_type: - description: > - The nature or genre of the resource. Recommended best practice is to use a controlled vocabulary such as the DCMI Type Vocabulary [DCMITYPE]. To describe the file format, physical medium, or dimensions of the resource, use the Format element. - type: string - - projects: - $ref: "_definitions.yaml#/to_one_project" - diff --git a/gdcdictionary/schemas/demographic.yaml b/gdcdictionary/schemas/demographic.yaml deleted file mode 100644 index ea8a2b422..000000000 --- a/gdcdictionary/schemas/demographic.yaml +++ /dev/null @@ -1,114 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "demographic" -title: Demographic -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Data for the characterization of the patient by means of segementing the population (e.g., - characterization by age, sex, or race). -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: cases - backref: demographics - label: describes - target_type: case - multiplicity: one_to_one - required: true - -required: - - submitter_id - - type - - cases - -preferred: - - year_of_death - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - type: string - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - gender: - term: - $ref: "_terms.yaml#/gender" - enum: - - female - - male - - unknown - - unspecified - - not reported - - race: - term: - $ref: "_terms.yaml#/race" - enum: - - white - - american indian or alaska native - - black or african american - - asian - - native hawaiian or other pacific islander - - other - - Unknown - - not reported - - not allowed to collect - - ethnicity: - term: - $ref: "_terms.yaml#/ethnicity" - enum: - - hispanic or latino - - not hispanic or latino - - Unknown - - not reported - - not allowed to collect - - year_of_birth: - term: - $ref: "_terms.yaml#/year_of_birth" - type: - - number - - "null" - - year_of_death: - term: - $ref: "_terms.yaml#/year_of_death" - type: number - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/diagnosis.yaml b/gdcdictionary/schemas/diagnosis.yaml deleted file mode 100644 index 28c424081..000000000 --- a/gdcdictionary/schemas/diagnosis.yaml +++ /dev/null @@ -1,844 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "diagnosis" -title: Diagnosis -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Data from the investigation, analysis and recognition of the presence and nature of disease, - condition, or injury from expressed signs and symptoms; also, the scientific determination of any - kind; the concise results of such an investigation. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: cases - backref: diagnoses - label: describes - target_type: case - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - age_at_diagnosis - - days_to_last_follow_up - - vital_status - - primary_diagnosis - - morphology - - tissue_or_organ_of_origin - - site_of_resection_or_biopsy - - classification_of_tumor - - tumor_stage - - tumor_grade - - progression_or_recurrence - - days_to_recurrence - - days_to_last_known_disease_status - - last_known_disease_status - -preferred: - - days_to_birth - - site_of_resection_or_biopsy - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - type: string - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - age_at_diagnosis: - term: - $ref: "_terms.yaml#/age_at_diagnosis" - type: - - number - - "null" - maximum: 32872 - minimum: 0 - - ajcc_clinical_m: - term: - $ref: "_terms.yaml#/ajcc_clinical_m" - enum: - - M0 - - M1 - - M1a - - M1b - - M1c - - MX - - cM0 (i+) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_n: - term: - $ref: "_terms.yaml#/ajcc_clinical_n" - enum: - - N0 - - N0 (i+) - - N0 (i-) - - N0 (mol+) - - N0 (mol-) - - N1 - - N1a - - N1b - - N1bI - - N1bII - - N1bIII - - N1bIV - - N1c - - N1mi - - N2 - - N2a - - N2b - - N2c - - N3 - - N3a - - N3b - - N3c - - N4 - - NX - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_stage: - term: - $ref: "_terms.yaml#/ajcc_clinical_stage" - enum: - - Stage 0 - - Stage 0a - - Stage 0is - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB Cervix - - Stage IB1 - - Stage IB2 - - Stage II - - Stage II Cervix - - Stage IIA - - Stage IIA Cervix - - Stage IIB - - Stage IIC - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IS - - Stage IV - - Stage IVA - - Stage IVB - - Stage IVC - - Stage Tis - - Stage X - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_clinical_t: - term: - $ref: "_terms.yaml#/ajcc_clinical_t" - enum: - - T0 - - T1 - - T1a - - T1a1 - - T1a2 - - T1b - - T1b1 - - T1b2 - - T1c - - T1mi - - T2 - - T2a - - T2a1 - - T2a2 - - T2b - - T2c - - T2d - - T3 - - T3a - - T3b - - T3c - - T3d - - T4 - - T4a - - T4b - - T4c - - T4d - - T4e - - TX - - Ta - - Tis - - Tis (DCIS) - - Tis (LCIS) - - Tis (Paget's) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_m: - term: - $ref: "_terms.yaml#/ajcc_pathologic_m" - enum: - - M0 - - M1 - - M1a - - M1b - - M1c - - M2 - - MX - - cM0 (i+) - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_n: - term: - $ref: "_terms.yaml#/ajcc_pathologic_n" - enum: - - N0 - - N0 (i+) - - N0 (i-) - - N0 (mol+) - - N0 (mol-) - - N1 - - N1a - - N1b - - N1bI - - N1bII - - N1bIII - - N1bIV - - N1c - - N1mi - - N2 - - N2a - - N2b - - N2c - - N3 - - N3a - - N3b - - N3c - - N4 - - NX - - Unknown - - Not Reported - - Not Allowed To Collect - - ajcc_pathologic_stage: - term: - $ref: "_terms.yaml#/ajcc_pathologic_stage" - enum: - - Stage 0 - - Stage 0a - - Stage 0is - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB1 - - Stage IB2 - - Stage IC - - Stage II - - Stage IIA - - Stage IIA1 - - Stage IIA2 - - Stage IIB - - Stage IIC - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IV - - Stage IVA - - Stage IVB - - Stage IVC - - Stage Tis - - Stage X - - ajcc_pathologic_t: - term: - $ref: "_terms.yaml#/ajcc_pathologic_t" - enum: - - T0 - - T1 - - T1a - - T1a1 - - T1a2 - - T1b - - T1b1 - - T1b2 - - T1c - - T1mi - - T2 - - T2a - - T2a1 - - T2a2 - - T2b - - T2c - - T2d - - T3 - - T3a - - T3b - - T3c - - T3d - - T4 - - T4a - - T4b - - T4c - - T4d - - T4e - - TX - - Ta - - Tis - - Tis (DCIS) - - Tis (LCIS) - - Tis (Paget's) - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_b_symptoms: - term: - $ref: "_terms.yaml#/ann_arbor_b_symptoms" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_clinical_stage: - term: - $ref: "_terms.yaml#/ann_arbor_clinical_stage" - enum: - - Stage I - - Stage II - - Stage III - - Stage IV - - ann_arbor_extranodal_involvement: - term: - $ref: "_terms.yaml#/ann_arbor_extranodal_involvement" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - ann_arbor_pathologic_stage: - term: - $ref: "_terms.yaml#/ann_arbor_pathologic_stage" - enum: - - Stage I - - Stage II - - Stage III - - Stage IV - - burkitt_lymphoma_clinical_variant: - term: - $ref: "_terms.yaml#/burkitt_lymphoma_clinical_variant" - enum: - - "Endemic" - - "Immunodeficiency-associated, adult" - - "Immunodeficiency-associated, pediatric" - - "Sporadic, adult" - - "Sporadic, pediatric" - - Unknown - - Not Reported - - Not Allowed To Collect - - cause_of_death: - term: - $ref: "_terms.yaml#/cause_of_death" - enum: - - Cancer Related - - Not Cancer Related - - Unknown - - circumferential_resection_margin: - term: - $ref: "_terms.yaml#/circumferential_resection_margin" - type: number - - classification_of_tumor: - term: - $ref: "_terms.yaml#/classification_of_tumor" - enum: - - primary - - metastasis - - recurrence - - other - - Unknown - - not reported - - Not Allowed To Collect - - colon_polyps_history: - term: - $ref: "_terms.yaml#/colon_polyps_history" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - days_to_birth: - term: - $ref: "_terms.yaml#/days_to_birth" - type: - - number - - "null" - maximum: 0 - minimum: -32872 - - days_to_death: - term: - $ref: "_terms.yaml#/days_to_death" - type: number - maximum: 32872 - minimum: 0 - - days_to_hiv_diagnosis: - term: - $ref: "_terms.yaml#/days_to_hiv_diagnosis" - type: - - number - - "null" - - days_to_last_follow_up: - term: - $ref: "_terms.yaml#/days_to_last_follow_up" - type: - - number - - "null" - - days_to_last_known_disease_status: - term: - $ref: "_terms.yaml#/days_to_last_known_disease_status" - type: - - number - - "null" - - days_to_new_event: - term: - $ref: "_terms.yaml#/days_to_new_event" - type: - - number - - "null" - - days_to_recurrence: - term: - $ref: "_terms.yaml#/days_to_recurrence" - type: - - number - - "null" - - figo_stage: - term: - $ref: "_terms.yaml#/figo_stage" - enum: - - Stage 0 - - Stage I - - Stage IA - - Stage IA1 - - Stage IA2 - - Stage IB - - Stage IB1 - - Stage IB2 - - Stage IC - - Stage II - - Stage IIA - - Stage IIA1 - - Stage IIA2 - - Stage IIB - - Stage III - - Stage IIIA - - Stage IIIB - - Stage IIIC - - Stage IIIC1 - - Stage IIIC2 - - Stage IV - - Stage IVA - - Stage IVB - - Unknown - - Not Reported - - Not Allowed To Collect - - hiv_positive: - term: - $ref: "_terms.yaml#/hiv_positive" - enum: - - "Yes" - - "No" - - Unknown - - hpv_positive_type: - term: - $ref: "_terms.yaml#/hpv_positive_type" - enum: - - HPV 16 - - HPV 18 - - Other HPV type(s) - - Unknown - - hpv_status: - term: - $ref: "_terms.yaml#/hpv_status" - enum: - - Negative - - Positive - - Unknown - - last_known_disease_status: - term: - $ref: "_terms.yaml#/last_known_disease_status" - enum: - - Distant met recurrence/progression - - Loco-regional recurrence/progression - - Biochemical evidence of disease without structural correlate - - Tumor free - - Unknown tumor status - - With tumor - - not reported - - Not Allowed To Collect - - laterality: - term: - $ref: "_terms.yaml#/laterality" - enum: - - Bilateral - - Left - - Right - - Unknown - - ldh_level_at_diagnosis: - term: - $ref: "_terms.yaml#/ldh_level_at_diagnosis" - type: - - number - - "null" - - ldh_normal_range_upper: - term: - $ref: "_terms.yaml#/ldh_normal_range_upper" - type: - - number - - "null" - - lymph_nodes_positive: - term: - $ref: "_terms.yaml#/lymph_nodes_positive" - type: integer - - lymphatic_invasion_present: - term: - $ref: "_terms.yaml#/lymphatic_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - method_of_diagnosis: - term: - $ref: "_terms.yaml#/method_of_diagnosis" - enum: - - Autopsy - - Biopsy - - Blood Draw - - Bone Marrow Aspirate - - Core Biopsy - - Cytology - - Debulking - - Diagnostic Imaging - - Excisional Biopsy - - Fine Needle Aspiration - - Incisional Biopsy - - Laparoscopy - - Laparotomy - - Other - - Surgical Resection - - Ultrasound Guided Biopsy - - Unknown - - Not Reported - - Not Allowed To Collect - - morphology: - term: - $ref: "_terms.yaml#/morphology" - type: string - - new_event_anatomic_site: - term: - $ref: "_terms.yaml#/new_event_anatomic_site" - enum: - - Abdomen - - Adrenal - - Anus - - Appendix - - Ascites/Peritoneum - - Axillary lymph nodes - - Bladder - - Bone - - Bone Marrow - - Brain - - Breast - - Cervical lymph nodes - - Cervix - - Colon - - Conjunctiva - - Contralateral Pleura - - Distant Metastasis - - Epididymis - - Epidural - - Epitrochlear lymph nodes - - Esophagus - - Extremities - - Femoral lymph nodes - - Gallbladder - - Gastrointestinal/Abdominal - - Head & Neck - - Heart - - Hilar lymph nodes - - Hypopharynx - - Iliac Lymph Node - - Iliac-common lymph nodes - - Iliac-external lymph nodes - - Inguinal lymph nodes - - Intraocular - - Ipsilateral Chest Cavity - - Ipsilateral Chest Wall - - Ipsilateral Lymph Nodes - - Ipsilateral Pleura - - Kidney - - Large Intestine - - Larynx - - Leptomeninges - - Liver - - Lung - - Lymph Node Only - - Lymph Node(s) - - Mandible - - Maxilla - - Mediastinal Soft Tissue - - Mediastinal lymph nodes - - Mediastinal/Intra-thoracic - - Mesenteric lymph nodes - - Nasal Soft Tissue - - Nasopharynx - - No Known Extranodal Involvement - - Non-regional / Distant Lymph Nodes - - Not Applicable - - Occipital lymph nodes - - Oral Cavity - - Oropharynx - - Other - - Other Extranodal Site - - Other, specify - - Ovary - - Pancreas - - Paraaortic lymph nodes - - Parotid Gland - - Parotid lymph nodes - - Pelvis - - Peri-orbital Soft Tissue - - Pericardium - - Perihilar Lymph Node - - Peripheral Blood - - Peritoneal Surfaces - - Pleura/Pleural Effusion - - Popliteal lymph nodes - - Prostate - - Pulmonary - - Rectum - - Renal Pelvis - - Retroperitoneal lymph nodes - - Retroperitoneum - - Salivary Gland - - Sinus - - Skin - - Small Intestine - - Soft Tissue - - Splenic lymph nodes - - Stomach - - Submandibular lymph nodes - - Supraclavicular lymph nodes - - Testes - - Thyroid - - Trunk - - Tumor Bed - - Ureter - - Urethra - - Uterus - - Vulva - - Unknown - - Not Reported - - Not Allowed To Collect - - new_event_type: - term: - $ref: "_terms.yaml#/new_event_type" - enum: - - Biochemical Evidence of Disease - - Both Locoregional and Distant Metastasis - - Distant Metastasis - - Extrahepatic Recurrence - - Intrahepatic Recurrence - - Intrapleural Progression - - Locoregional (Urothelial tumor event) - - Locoregional Disease - - Locoregional Recurrence - - Metachronous Testicular Tumor - - Metastatic - - New Primary Tumor - - New primary Melanoma - - No New Tumor Event - - Not Applicable - - Progression of Disease - - Recurrence - - Regional Lymph Node - - Unknown - - Not Reported - - Not Allowed To Collect - - perineural_invasion_present: - term: - $ref: "_terms.yaml#/perineural_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - primary_diagnosis: - term: - $ref: "_terms.yaml#/primary_diagnosis" - type: string - - prior_malignancy: - term: - $ref: "_terms.yaml#/prior_malignancy" - enum: - - "yes" - - "no" - - unknown - - not reported - - Not Allowed To Collect - - prior_treatment: - term: - $ref: "_terms.yaml#/prior_treatment" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - progression_or_recurrence: - term: - $ref: "_terms.yaml#/progression_or_recurrence" - enum: - - "yes" - - "no" - - unknown - - not reported - - Not Allowed To Collect - - residual_disease: - term: - $ref: "_terms.yaml#/residual_disease" - enum: - - R0 - - R1 - - R2 - - RX - - site_of_resection_or_biopsy: - term: - $ref: "_terms.yaml#/site_of_resection_or_biopsy" - type: string - - tissue_or_organ_of_origin: - term: - $ref: "_terms.yaml#/tissue_or_organ_of_origin" - type: string - - tumor_grade: - term: - $ref: "_terms.yaml#/tumor_grade" - type: string - - tumor_stage: - term: - $ref: "_terms.yaml#/tumor_stage" - type: string - - vascular_invasion_present: - term: - $ref: "_terms.yaml#/vascular_invasion_present" - enum: - - "Yes" - - "No" - - Unknown - - Not Reported - - Not Allowed To Collect - - vital_status: - term: - $ref: "_terms.yaml#/vital_status" - enum: - - alive - - dead - - lost to follow-up - - unknown - - not reported - - Not Allowed To Collect - - pending # this is from TARGET RT clinical data - - year_of_diagnosis: - term: - $ref: "_terms.yaml#/year_of_diagnosis" - type: - - number - - "null" - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/experiment.yaml b/gdcdictionary/schemas/experiment.yaml deleted file mode 100644 index b60cd0682..000000000 --- a/gdcdictionary/schemas/experiment.yaml +++ /dev/null @@ -1,108 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "experiment" -title: Experiment -type: object -namespace: http://bloodprofilingatlas.org/bpa/ -category: administrative -program: '*' -project: '*' -description: > - A coordinated set of actions and observations designed to generate data, with the ultimate goal - of discovery or hypothesis testing. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: projects - backref: experiments - label: performed_for - target_type: project - multiplicity: many_to_one - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "experiment" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - number_experimental_group: - description: "The number denoting this experiment's place within the group within the whole." - type: - - integer - number_samples_per_experimental_group: - description: "The number of samples contained within this experimental group." - type: - - integer - experimental_description: - description: "A brief description of the experiment being performed." - type: - - string - experimental_intent: - description: "Summary of the goals the experiment is designed to discover." - type: - - string - associated_experiment: - description: "The submitter_id for any experiment with which this experiment is associated, paired, or matched." - type: - - string - type_of_sample: - description: "String indicator identifying the types of samples as contrived or clinical." - type: - - string - type_of_specimen: - description: "Broad description of the specimens used in the experiment." - type: - - string - marker_panel_description: - description: "Brief description of the marker panel used in this experiment." - type: string - somatic_mutations_identified: - description: "Are somatic mutations identified for this experiment?" - type: boolean - indels_identified: - description: "Are indels identified in this experiment?" - type: boolean - copy_numbers_identified: - description: "Are copy number variations identified in this experiment?" - type: boolean - type_of_data: - description: "Is the data raw or processed?" - enum: - - Raw - - Processed - data_description: - description: "Brief description of the data being provided for this experiment." - type: string - projects: - $ref: "_definitions.yaml#/to_one_project" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/experimental_metadata.yaml b/gdcdictionary/schemas/experimental_metadata.yaml deleted file mode 100644 index cd4f321a5..000000000 --- a/gdcdictionary/schemas/experimental_metadata.yaml +++ /dev/null @@ -1,77 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "experimental_metadata" -title: Experimental Metadata -type: object -namespace: http://gdc.nci.nih.gov -category: metadata_file -project: '*' -program: '*' -description: > - Data file containing the metadata for the experiment performed. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: experiment_metadata_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: experiments - backref: experiment_metadata_files - label: derived_from - target_type: experiment - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "experimental_metadata" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: - - string - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Experimental Metadata" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: - - string - experiments: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/exposure.yaml b/gdcdictionary/schemas/exposure.yaml deleted file mode 100644 index 76cfe72c9..000000000 --- a/gdcdictionary/schemas/exposure.yaml +++ /dev/null @@ -1,132 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "exposure" -title: Exposure -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Clinically relevant patient information not immediately resulting from genetic predispositions. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: cases - backref: exposures - label: describes - target_type: case - multiplicity: many_to_one - required: true - -preferred: - - cigarettes_per_day - - years_smoked - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "exposure" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - alcohol_history: - term: - $ref: "_terms.yaml#/alcohol_history" - type: string - - alcohol_intensity: - term: - $ref: "_terms.yaml#/alcohol_intensity" - type: string - - bmi: - term: - $ref: "_terms.yaml#/bmi" - type: number - - cigarettes_per_day: - term: - $ref: "_terms.yaml#/cigarettes_per_day" - type: number - - height: - term: - $ref: "_terms.yaml#/height" - type: number - - pack_years_smoked: - term: - $ref: "_terms.yaml#/pack_years_smoked" - type: number - - tobacco_smoking_onset_year: - term: - $ref: "_terms.yaml#/tobacco_smoking_onset_year" - type: integer - - tobacco_smoking_quit_year: - term: - $ref: "_terms.yaml#/tobacco_smoking_quit_year" - type: integer - - tobacco_smoking_status: - term: - $ref: "_terms.yaml#/tobacco_smoking_status" - enum: - - "1" - - "2" - - "3" - - "4" - - "5" - - "6" - - "7" - - Unknown - - Not Reported - - Not Allowed To Collect - - weight: - term: - $ref: "_terms.yaml#/weight" - type: number - - years_smoked: - term: - $ref: "_terms.yaml#/years_smoked" - type: number - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/family_history.yaml b/gdcdictionary/schemas/family_history.yaml deleted file mode 100644 index add3a1523..000000000 --- a/gdcdictionary/schemas/family_history.yaml +++ /dev/null @@ -1,98 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "family_history" -title: Family History -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Record of a patient's background regarding cancer events of blood relatives. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: cases - backref: family_histories - label: describes - target_type: case - multiplicity: many_to_one - required: true - - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "family_history" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - relative_with_cancer_history: - term: - $ref: "_terms.yaml#/relative_with_cancer_history" - enum: - - "yes" - - "no" - - unknown - - not reported - - relationship_type: - term: - $ref: "_terms.yaml#/relationship_type" - type: string - - relationship_gender: - term: - $ref: "_terms.yaml#/gender" - enum: - - female - - male - - unknown - - unspecified - - not reported - - relationship_age_at_diagnosis: - term: - $ref: "_terms.yaml#/relationship_age_at_diagnosis" - type: number - - relationship_primary_diagnosis: - term: - $ref: "_terms.yaml#/primary_diagnosis" - type: string - - cases: - $ref: "_definitions.yaml#/to_one" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/keyword.yaml b/gdcdictionary/schemas/keyword.yaml deleted file mode 100644 index 99a3a050f..000000000 --- a/gdcdictionary/schemas/keyword.yaml +++ /dev/null @@ -1,61 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "keyword" -title: Keyword -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "A keyword for a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: keywords - label: describe - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "keyword" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - keyword_name: - description: "The name of the keyword." - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/program.yaml b/gdcdictionary/schemas/program.yaml deleted file mode 100644 index 4504f8572..000000000 --- a/gdcdictionary/schemas/program.yaml +++ /dev/null @@ -1,41 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "program" -title: Program -type: object -category: administrative -program: '*' -project: '*' -description: > - A broad framework of goals to be achieved. (NCIt C52647) -additionalProperties: false -submittable: false -validators: null - -systemProperties: - - id - -required: - - name - - dbgap_accession_number - -uniqueKeys: - - [id] - - [name] - -links: [] - -# Program is the root entity and so it is the only entity -# without a project or parents. -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - name: - type: string - description: "Full name/title of the program." - dbgap_accession_number: - type: string - description: "The dbgap accession number provided for the program." diff --git a/gdcdictionary/schemas/project.yaml b/gdcdictionary/schemas/project.yaml deleted file mode 100644 index dc21d32f5..000000000 --- a/gdcdictionary/schemas/project.yaml +++ /dev/null @@ -1,147 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "project" -title: Project -type: object -program: '*' -project: '*' -category: administrative -description: > - Any specifically defined piece of work that is undertaken or attempted to meet a single - requirement. (NCIt C47885) -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - state - - released - - releasable - - intended_release_date - -required: - - code - - name - - dbgap_accession_number - - programs - -uniqueKeys: - - [ id ] - - [ code ] - -links: - - name: programs - backref: projects - label: member_of - target_type: program - multiplicity: many_to_one - required: true - -constraints: null - -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - description: "UUID for the project." # TOREVIEW - name: - type: string - description: "Display name/brief description for the project." # TOREVIEW - code: - type: string - description: "Unique identifier for the project." - investigator_name: - description: "Name of the principal investigator for the project." - type: string - investigator_affiliation: - description: "The investigator's affiliation with respect to a research institution." - type: string - date_collected: - description: "The date or date range in which the project data was collected." - type: string - availability_type: - description: "Is the project open or restricted?" - enum: - - Open - - Restricted - availability_mechanism: - description: "Mechanism by which the project will be made avilable." - type: string - support_source: - description: "The name of source providing support/grant resources." - type: string - support_id: - description: "The ID of the source providing support/grant resources." - type: string - programs: - $ref: "_definitions.yaml#/to_one" - description: > - Indicates that the project is logically part of the indicated project. - state: - description: | - The possible states a project can be in. All but `open` are - equivalent to some type of locked state. - default: open - enum: - # open: the only state users can perform 'upload' actions - # possible actions in `open`: - # - upload (no state change) - # - review -> review - # - release (project.released -> true) - - open - - # locked: admin has locked project for review - # possible actions in `locked`: - # - open -> open - # - submit -> submitted - # - release (project.released -> true) - - review - - # submitted: An admin has submitted project, it is locked against - # upload. - # possible actions in `submitted`: - # - process -> processing - # - release (project.released -> true) - - submitted - - # processing: The system is processing data in the project and - # is locked against upload and submission - # - (system transition to open) - # - release (project.released -> true) - - processing - - - # closed: The closed state is introduced to replace the - # ``legacy`` state and means that no further action - # can be taken on the project - # - (system transition to open) - # - release (project.released -> true) - - closed - - # DEPRECATED(2016-03-01): synonymous with closed. included for - # backwards compatibility - - legacy - - released: - description: | - To release a project is to tell the GDC to include all submitted - entities in the next GDC index. - default: false - type: boolean - - releasable: - description: | - A project can only be released by the user when `releasable` is true. - default: false - type: boolean - - intended_release_date: - description: Tracks a Project's intended release date. - type: string - format: date-time - dbgap_accession_number: - type: string - description: "The dbgap accession number provided for the project." diff --git a/gdcdictionary/schemas/projects/project1.yaml b/gdcdictionary/schemas/projects/project1.yaml deleted file mode 100644 index c5d141abe..000000000 --- a/gdcdictionary/schemas/projects/project1.yaml +++ /dev/null @@ -1,21 +0,0 @@ -##################################################################### -# Project 1 specific overrides -##################################################################### - -$schema: "http://json-schema.org/draft-04/schema#" - -##################################################################### -# Aliquot -##################################################################### - -id: "aliquot" -program: 'program1' -project: 'project1' -required: - - submitter_aliquot_id - - parents - - project_1_specific_thing - -properties: - project_1_specific_thing: -type: string diff --git a/gdcdictionary/schemas/publication.yaml b/gdcdictionary/schemas/publication.yaml deleted file mode 100644 index 2feb6a1ab..000000000 --- a/gdcdictionary/schemas/publication.yaml +++ /dev/null @@ -1,62 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "publication" -title: Publication -type: object -namespace: http://gdc.nci.nih.gov -category: administrative -program: '*' -project: '*' -description: "Publication for a project." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: projects - backref: publications - label: refers_to - target_type: project - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - projects - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "publication" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - pmid: - type: string - doi: - type: string - projects: - $ref: "_definitions.yaml#/to_many_project" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/read_group.yaml b/gdcdictionary/schemas/read_group.yaml deleted file mode 100644 index d1a8bdd4b..000000000 --- a/gdcdictionary/schemas/read_group.yaml +++ /dev/null @@ -1,225 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "read_group" -title: Read Group -type: object -description: "Sequencing reads from one lane of an NGS experiment." -namespace: http://gdc.nci.nih.gov -category: biospecimen -project: '*' -program: '*' -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: aliquots - label: derived_from - target_type: aliquot - multiplicity: many_to_one - required: true - backref: read_groups - -required: - - type - - submitter_id - - aliquots - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - id: - $ref: "_definitions.yaml#/UUID" - project_id: - $ref: "_definitions.yaml#/project_id" - submitter_id: - type: string - state: - $ref: "_definitions.yaml#/state" - type: - enum: [ "read_group" ] - experiment_name: - term: - $ref: "_terms.yaml#/experiment_name" - type: string - sequencing_center: - term: - $ref: "_terms.yaml#/sequencing_center" - type: string - sequencing_date: - $ref: "_definitions.yaml#/datetime" - platform: - term: - $ref: "_terms.yaml#/platform" - enum: - - Illumina - - SOLiD - - LS454 - - Ion Torrent - - Complete Genomics - - PacBio - - Other - instrument_model: - terms: - $ref: "_terms.yaml#/instrument_model" - enum: - - 454 GS FLX Titanium - - AB SOLiD 4 - - AB SOLiD 2 - - AB SOLiD 3 - - Complete Genomics - - Illumina HiSeq X Ten - - Illumina HiSeq X Five - - Illumina Genome Analyzer II - - Illumina Genome Analyzer IIx - - Illumina HiSeq 2000 - - Illumina HiSeq 2500 - - Illumina HiSeq 4000 - - Illumina MiSeq - - Illumina NextSeq - - Ion Torrent PGM - - Ion Torrent Proton - - PacBio RS - - Ion S5 XL System, Ion 530 Chip - - Other - library_strategy: - term: - $ref: "_terms.yaml#/library_strategy" - enum: - - WGS - - WXS - - RNA-Seq - - ChIP-Seq - - miRNA-Seq - - Bisulfite-Seq - - Validation - - Amplicon - - Other - RIN: - term: - $ref: "_terms.yaml#/RIN" - type: number - flow_cell_barcode: - term: - $ref: "_terms.yaml#/flow_cell_barcode" - type: string - includes_spike_ins: - term: - $ref: "_terms.yaml#/includes_spike_ins" - type: boolean - spike_ins_fasta: - term: - $ref: "_terms.yaml#/spike_ins_fasta" - type: string - spike_ins_concentration: - term: - $ref: "_terms.yaml#/spike_ins_concentration" - type: string - library_selection: - term: - $ref: "_terms.yaml#/library_selection" - enum: - - Hybrid_Selection - - PCR - - Affinity_Enrichment - - Poly-T_Enrichment - - RNA_Depletion - - Other - library_preparation_kit_name: - term: - $ref: "_terms.yaml#/library_preparation_kit_name" - type: string - library_preparation_kit_vendor: - term: - $ref: "_terms.yaml#/library_preparation_kit_vendor" - type: string - library_preparation_kit_catalog_number: - term: - $ref: "_terms.yaml#/library_preparation_kit_catalog_number" - type: string - library_preparation_kit_version: - term: - $ref: "_terms.yaml#/library_preparation_kit_version" - type: string - library_name: - term: - $ref: "_terms.yaml#/library_name" - type: string - target_capture_kit_name: # conditionally required for WXS etc - term: - $ref: "_terms.yaml#/target_capture_kit_name" - type: string - target_capture_kit_vendor: - term: - $ref: "_terms.yaml#/target_capture_kit_vendor" - type: string - target_capture_kit_catalog_number: - term: - $ref: "_terms.yaml#/target_capture_kit_catalog_number" - type: string - target_capture_kit_version: - term: - $ref: "_terms.yaml#/target_capture_kit_version" - type: string - target_capture_kit_target_region: - term: - $ref: "_terms.yaml#/target_capture_kit_target_region" - type: string - size_selection_range: - term: - $ref: "_terms.yaml#/size_selection_range" - type: string - adapter_name: - term: - $ref: "_terms.yaml#/adapter_name" - type: string - adapter_sequence: - term: - $ref: "_terms.yaml#/adapter_sequence" - type: string - to_trim_adapter_sequence: - term: - $ref: "_terms.yaml#/to_trim_adapter_sequence" - type: boolean - library_strand: - term: - $ref: "_terms.yaml#/library_strand" - enum: - - Unstranded - - First_Stranded - - Second_Stranded - base_caller_name: - term: - $ref: "_terms.yaml#/base_caller_name" - type: string - base_caller_version: - term: - $ref: "_terms.yaml#/base_caller_version" - type: string - is_paired_end: - term: - $ref: "_terms.yaml#/is_paired_end" - type: boolean - read_length: - type: integer - read_group_name: # it may be good to assign UUID to read group - description: "Read Group Name" - type: string - barcoding_applied: - description: "True/False: was barcoding applied?" - type: boolean - aliquots: - $ref: "_definitions.yaml#/to_one" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/read_group_qc.yaml b/gdcdictionary/schemas/read_group_qc.yaml deleted file mode 100644 index 9b235528c..000000000 --- a/gdcdictionary/schemas/read_group_qc.yaml +++ /dev/null @@ -1,133 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "read_group_qc" -title: Read Group QC -type: object -namespace: http://gdc.nci.nih.gov -category: notation -project: '*' -program: '*' -description: "GDC QC run metadata." -additionalProperties: false -submittable: false -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - exclusive: true - required: true - subgroup: - - name: submitted_aligned_reads_files - backref: read_group_qcs - label: data_from - target_type: submitted_aligned_reads - multiplicity: one_to_one - required: false - - name: submitted_unaligned_reads_files - backref: read_group_qcs - label: data_from - target_type: submitted_unaligned_reads - multiplicity: one_to_many - required: false - - name: read_groups - label: generated_from - target_type: read_group - multiplicity: many_to_one - required: true - backref: read_group_qcs - -required: - - submitter_id - - workflow_link - - type - - percent_gc_content - - encoding - - total_sequences - - basic_statistics - - per_base_sequence_quality - - per_tile_sequence_quality - - per_sequence_quality_score - - per_base_sequence_content - - per_sequence_gc_content - - per_base_n_content - - sequence_length_distribution - - sequence_duplication_levels - - overrepresented_sequences - - adapter_content - - kmer_content - - read_groups - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/workflow_properties" - type: - enum: [ "read_group_qc" ] - workflow_type: - term: - $ref: "_terms.yaml#/workflow_type" - enum: [ "Read Group Quality Control" ] - fastq_name: - term: - $ref: "_terms.yaml#/file_name" - type: string - percent_aligned: - description: "The percent of reads with at least one reported alignment." - type: integer - minimum: 0 - maximum: 100 - percent_gc_content: - term: - $ref: "_terms.yaml#/percent_gc_content" - type: integer - minimum: 0 - maximum: 100 - encoding: - term: - $ref: "_terms.yaml#/encoding" - type: string - total_aligned_reads: - description: "The total number of reads with at least one reported alignment." - type: integer - total_sequences: - term: - $ref: "_terms.yaml#/total_sequences" - type: integer - basic_statistics: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_sequence_quality: - $ref: "_definitions.yaml#/qc_metrics_state" - per_tile_sequence_quality: - $ref: "_definitions.yaml#/qc_metrics_state" - per_sequence_quality_score: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_sequence_content: - $ref: "_definitions.yaml#/qc_metrics_state" - per_sequence_gc_content: - $ref: "_definitions.yaml#/qc_metrics_state" - per_base_n_content: - $ref: "_definitions.yaml#/qc_metrics_state" - sequence_length_distribution: - $ref: "_definitions.yaml#/qc_metrics_state" - sequence_duplication_levels: - $ref: "_definitions.yaml#/qc_metrics_state" - overrepresented_sequences: - $ref: "_definitions.yaml#/qc_metrics_state" - adapter_content: - $ref: "_definitions.yaml#/qc_metrics_state" - kmer_content: - $ref: "_definitions.yaml#/qc_metrics_state" - submitted_aligned_reads_files: - $ref: "_definitions.yaml#/to_one" - submitted_unaligned_reads_files: - $ref: "_definitions.yaml#/to_many" - read_groups: - $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/sample.yaml b/gdcdictionary/schemas/sample.yaml deleted file mode 100644 index 7680e5cb3..000000000 --- a/gdcdictionary/schemas/sample.yaml +++ /dev/null @@ -1,686 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "sample" -title: Sample -type: object -namespace: http://gdc.nci.nih.gov -category: biospecimen -program: '*' -project: '*' -description: > - Any material sample taken from a biological entity for testing, diagnostic, propagation, treatment - or research purposes, including a sample obtained from a living organism or taken from the - biological object after halting of all its life functions. Biospecimen can contain one or more - components including but not limited to cellular molecules, cells, tissues, organs, body fluids, - embryos, and body excretory products. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - - cases - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -links: - - name: cases - backref: samples - label: derived_from - target_type: case - multiplicity: many_to_one #not sure - required: true - - name: diagnoses - backref: samples - label: related_to - target_type: diagnosis - multiplicity: many_to_one - required: false - -# Sample properties: keep TCGA-specific fields -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - description: > - The legacy barcode used before prior to the use UUIDs, varies by project. - For TCGA this is bcrsamplebarcode. - biospecimen_anatomic_site: - term: - $ref: "_terms.yaml#/biospecimen_anatomic_site" - enum: - - Abdomen - - Abdominal Wall - - Acetabulum - - Adenoid - - Adipose - - Adrenal - - Alveolar Ridge - - Amniotic Fluid - - Ampulla Of Vater - - Anal Sphincter - - Ankle - - Anorectum - - Antecubital Fossa - - Antrum - - Anus - - Aorta - - Aortic Body - - Appendix - - Aqueous Fluid - - Arm - - Artery - - Ascending Colon - - Ascending Colon Hepatic Flexure - - Auditory Canal - - Autonomic Nervous System - - Axilla - - Back - - Bile Duct - - Bladder - - Blood - - Blood Vessel - - Bone - - Bone Marrow - - Bowel - - Brain - - Brain Stem - - Breast - - Broad Ligament - - Bronchiole - - Bronchus - - Brow - - Buccal Cavity - - Buccal Mucosa - - Buttock - - Calf - - Capillary - - Cardia - - Carina - - Carotid Artery - - Carotid Body - - Cartilage - - Cecum - - Cell-Line - - Central Nervous System - - Cerebellum - - Cerebral Cortex - - Cerebrospinal Fluid - - Cerebrum - - Cervical Spine - - Cervix - - Chest - - Chest Wall - - Chin - - Clavicle - - Clitoris - - Colon - - Colon - Mucosa Only - - Common Duct - - Conjunctiva - - Connective Tissue - - Dermal - - Descending Colon - - Diaphragm - - Duodenum - - Ear - - Ear Canal - - Ear, Pinna (External) - - Effusion - - Elbow - - Endocrine Gland - - Epididymis - - Epidural Space - - Esophagogastric Junction - - Esophagus - - Esophagus - Mucosa Only - - Eye - - Fallopian Tube - - Femoral Artery - - Femoral Vein - - Femur - - Fibroblasts - - Fibula - - Finger - - Floor Of Mouth - - Fluid - - Foot - - Forearm - - Forehead - - Foreskin - - Frontal Cortex - - Frontal Lobe - - Fundus Of Stomach - - Gallbladder - - Ganglia - - Gastroesophageal Junction - - Gastrointestinal Tract - - Groin - - Gum - - Hand - - Hard Palate - - Head & Neck - - Head - Face Or Neck, Nos - - Heart - - Hepatic - - Hepatic Duct - - Hepatic Vein - - Hip - - Hippocampus - - Humerus - - Hypopharynx - - Ileum - - Ilium - - Index Finger - - Ischium - - Islet Cells - - Jaw - - Jejunum - - Joint - - Kidney - - Knee - - Lacrimal Gland - - Large Bowel - - Laryngopharynx - - Larynx - - Leg - - Leptomeninges - - Ligament - - Lip - - Liver - - Lumbar Spine - - Lung - - Lymph Node - - Lymph Node(s) Axilla - - Lymph Node(s) Cervical - - Lymph Node(s) Distant - - Lymph Node(s) Epitrochlear - - Lymph Node(s) Femoral - - Lymph Node(s) Hilar - - Lymph Node(s) Iliac-Common - - Lymph Node(s) Iliac-External - - Lymph Node(s) Inguinal - - Lymph Node(s) Internal Mammary - - Lymph Node(s) Mammary - - Lymph Node(s) Mesenteric - - Lymph Node(s) Occipital - - Lymph Node(s) Paraaortic - - Lymph Node(s) Parotid - - Lymph Node(s) Pelvic - - Lymph Node(s) Popliteal - - Lymph Node(s) Regional - - Lymph Node(s) Retroperitoneal - - Lymph Node(s) Scalene - - Lymph Node(s) Splenic - - Lymph Node(s) Subclavicular - - Lymph Node(s) Submandibular - - Lymph Node(s) Supraclavicular - - Lymph Nodes(s) Mediastinal - - Mandible - - Maxilla - - Mediastinal Soft Tissue - - Mediastinum - - Mesentery - - Mesothelium - - Middle Finger - - Mitochondria - - Muscle - - Nails - - Nasal Cavity - - Nasal Soft Tissue - - Nasopharynx - - Neck - - Nerve - - Nerve(s) Cranial - - Occipital Cortex - - Ocular Orbits - - Omentum - - Oral Cavity - - Oral Cavity - Mucosa Only - - Oropharynx - - Other - - Ovary - - Palate - - Pancreas - - Paraspinal Ganglion - - Parathyroid - - Parotid Gland - - Patella - - Pelvis - - Penis - - Pericardium - - Periorbital Soft Tissue - - Peritoneal Cavity - - Peritoneum - - Pharynx - - Pineal - - Pineal Gland - - Pituitary Gland - - Placenta - - Pleura - - Popliteal Fossa - - Prostate - - Pylorus - - Rectosigmoid Junction - - Rectum - - Retina - - Retro-Orbital Region - - Retroperitoneum - - Rib - - Ring Finger - - Round Ligament - - Sacrum - - Salivary Gland - - Scalp - - Scapula - - Sciatic Nerve - - Scrotum - - Seminal Vesicle - - Shoulder - - Sigmoid Colon - - Sinus - - Sinus(es), Maxillary - - Skeletal Muscle - - Skin - - Skull - - Small Bowel - - Small Bowel - Mucosa Only - - Small Finger - - Soft Tissue - - Spinal Column - - Spinal Cord - - Spleen - - Splenic Flexure - - Sternum - - Stomach - - Stomach - Mucosa Only - - Subcutaneous Tissue - - Synovium - - Temporal Cortex - - Tendon - - Testis - - Thigh - - Thoracic Spine - - Thorax - - Throat - - Thumb - - Thymus - - Thyroid - - Tibia - - Tongue - - Tonsil - - Tonsil (Pharyngeal) - - Trachea / Major Bronchi - - Transverse Colon - - Trunk - - Umbilical Cord - - Ureter - - Urethra - - Urinary Tract - - Uterus - - Uvula - - Vagina - - Vas Deferens - - Vein - - Venous - - Vertebra - - Vulva - - White Blood Cells - - Wrist - - Unknown - - Not Reported - - Not Allowed To Collect - composition: - term: - $ref: "_terms.yaml#/composition" - enum: - - Buccal Cells - - Buffy Coat - - Bone Marrow Components - - Bone Marrow Components NOS - - Control Analyte - - Cell - - Circulating Tumor Cell (CTC) - - Derived Cell Line - - EBV Immortalized - - Fibroblasts from Bone Marrow Normal - - Granulocytes - - Human Original Cells - - Lymphocytes - - Mononuclear Cells from Bone Marrow Normal - - Peripheral Blood Components NOS - - Peripheral Blood Nucleated Cells - - Pleural Effusion - - Plasma - - Peripheral Whole Blood - - Serum - - Saliva - - Sputum - - Solid Tissue - - Whole Bone Marrow - - Unknown - - Not Reported - - Not Allowed To Collect - current_weight: - term: - $ref: "_terms.yaml#/current_weight" - type: number - days_to_collection: - term: - $ref: "_terms.yaml#/days_to_collection" - type: integer - days_to_sample_procurement: - term: - $ref: "_terms.yaml#/days_to_sample_procurement" - type: integer - diagnosis_pathologically_confirmed: - term: - ref: "_terms.yaml#/diagnosis_pathologically_confirmed" - enum: - - "Yes" - - "No" - - Unknown - freezing_method: - term: - $ref: "_terms.yaml#/freezing_method" - type: string - initial_weight: - term: - $ref: "_terms.yaml#/initial_weight" - type: number - intermediate_dimension: - terms: - $ref: "_terms.yaml#/intermediate_dimension" - type: string - is_ffpe: - term: - $ref: "_terms.yaml#/is_ffpe" - type: boolean - longest_dimension: - terms: - $ref: "_terms.yaml#/longest_dimension" - type: string - method_of_sample_procurement: - term: - $ref: "_terms.yaml#/method_of_sample_procurement" - enum: - - Abdomino-perineal Resection of Rectum - - Anterior Resection of Rectum - - Aspirate - - Biopsy - - Blood Draw - - Bone Marrow Aspirate - - Core Biopsy - - Cystectomy - - Endo Rectal Tumor Resection - - Endoscopic Biopsy - - Endoscopic Mucosal Resection (EMR) - - Enucleation - - Excisional Biopsy - - Fine Needle Aspiration - - Full Hysterectomy - - Gross Total Resection - - Hand Assisted Laparoscopic Radical Nephrectomy - - Hysterectomy NOS - - Incisional Biopsy - - Indeterminant - - Laparoscopic Biopsy - - Laparoscopic Partial Nephrectomy - - Laparoscopic Radical Nephrectomy - - Laparoscopic Radical Prostatectomy with Robotics - - Laparoscopic Radical Prostatectomy without Robotics - - Left Hemicolectomy - - Lobectomy - - Local Resection (Exoresection; wall resection) - - Lumpectomy - - Modified Radical Mastectomy - - Needle Biopsy - - Open Craniotomy - - Open Partial Nephrectomy - - Open Radical Nephrectomy - - Open Radical Prostatectomy - - Orchiectomy - - Other - - Other Surgical Resection - - Pan-Procto Colectomy - - Pneumonectomy - - Right Hemicolectomy - - Sigmoid Colectomy - - Simple Mastectomy - - Subtotal Resection - - Surgical Resection - - Thoracoscopic Biopsy - - Total Colectomy - - Total Mastectomy - - Transplant - - Transurethral resection (TURBT) - - Transverse Colectomy - - Tumor Resection - - Wedge Resection - - Unknown - - Not Reported - - Not Allowed To Collect - oct_embedded: - term: - $ref: "_terms.yaml#/oct_embedded" - type: string - preservation_method: - term: - $ref: "_terms.yaml#/preservation_method" - enum: - - Cryopreserved - - FFPE - - Fresh - - OCT - - Snap Frozen - - Frozen - - Unknown - - Not Reported - - Not Allowed To Collect - sample_type: - description: "Characterization of the sample as either clinical or contrived." - enum: - - Additional Metastatic - - Additional - New Primary - - Blood Derived Cancer - Bone Marrow, Post-treatment - - Blood Derived Cancer - Peripheral Blood, Post-treatment - - Blood Derived Normal - - Bone Marrow Normal - - Buccal Cell Normal - - Cell Line Derived Xenograft Tissue - - Cell Lines - - cfDNA - - Circulating Tumor Cell (CTC) - - Control Analyte - - Clinical - - Contrived - - ctDNA - - DNA - - EBV Immortalized Normal - - FFPE Recurrent - - FFPE Scrolls - - Fibroblasts from Bone Marrow Normal - - GenomePlex (Rubicon) Amplified DNA - - Granulocytes - - Human Tumor Original Cells - - Metastatic - - Mononuclear Cells from Bone Marrow Normal - - Primary Blood Derived Cancer - Peripheral Blood - - Recurrent Blood Derived Cancer - Peripheral Blood - - Pleural Effusion - - Primary Blood Derived Cancer - Bone Marrow - - Primary Tumor - - Primary Xenograft Tissue - - Post neo-adjuvant therapy - - Recurrent Blood Derived Cancer - Bone Marrow - - Recurrent Tumor - - Repli-G (Qiagen) DNA - - Repli-G X (Qiagen) DNA - - RNA - - Slides - - Solid Tissue Normal - - Total RNA - - Xenograft Tissue - - Unknown - - Not Reported - - Not Allowed To Collect - sample_type_id: - term: - $ref: "_terms.yaml#/sample_type_id" - enum: - - '01' - - '02' - - '03' - - '04' - - '05' - - '06' - - '07' - - '08' - - '09' - - '10' - - '11' - - '12' - - '13' - - '14' - - '15' - - '16' - - '20' - - '40' - - '41' - - '42' - - '50' - - '60' - - '61' - - '99' - sample_volume: - description: "The volume of the sample in mL." - type: number - shortest_dimension: - term: - $ref: "_terms.yaml#/shortest_dimension" - type: string - time_between_clamping_and_freezing: - term: - $ref: "_terms.yaml#/time_between_clamping_and_freezing" - type: string - time_between_excision_and_freezing: - term: - $ref: "_terms.yaml#/time_between_excision_and_freezing" - type: string - tissue_type: - term: - $ref: "_terms.yaml#/tissue_type" - enum: - - Tumor - - Normal - - Abnormal - - Peritumoral - - Contrived - - Unknown - - Not Reported - - Not Allowed To Collect - tumor_code: - term: - $ref: "_terms.yaml#/tumor_code" - enum: - - Non cancerous tissue - - Diffuse Large B-Cell Lymphoma (DLBCL) - - Lung Cancer (all types) - - Lung Adenocarcinoma - - Non-small Cell Lung Carcinoma (NSCLC) - - Colon Cancer (all types) - - Breast Cancer (all types) - - Cervical Cancer (all types) - - Anal Cancer (all types) - - Acute lymphoblastic leukemia (ALL) - - Acute myeloid leukemia (AML) - - Induction Failure AML (AML-IF) - - Neuroblastoma (NBL) - - Osteosarcoma (OS) - - Ewing sarcoma - - Wilms tumor (WT) - - Clear cell sarcoma of the kidney (CCSK) - - Rhabdoid tumor (kidney) (RT) - - CNS, ependymoma - - CNS, glioblastoma (GBM) - - CNS, rhabdoid tumor - - CNS, low grade glioma (LGG) - - CNS, medulloblastoma - - CNS, other - - NHL, anaplastic large cell lymphoma - - NHL, Burkitt lymphoma (BL) - - Rhabdomyosarcoma - - Soft tissue sarcoma, non-rhabdomyosarcoma - - Castration-Resistant Prostate Cancer (CRPC) - - Prostate Cancer - - Hepatocellular Carcinoma (HCC) - tumor_code_id: - term: - $ref: "_terms.yaml#/tumor_code_id" - enum: - - "00" - - "01" - - "02" - - "03" - - "04" - - "10" - - "20" - - "21" - - "30" - - "40" - - "41" - - "50" - - "51" - - "52" - - "60" - - "61" - - "62" - - "63" - - "64" - - "65" - - "70" - - "71" - - "80" - - "81" - tumor_descriptor: - term: - $ref: "_terms.yaml#/tumor_descriptor" - enum: - - Metastatic - - Not Applicable - - Primary - - Recurrence - - Xenograft - - NOS - - Unknown - - Not Reported - - Not Allowed To Collect - description: "A description of the tumor from which the sample was derived." # TOREVIEW - cases: - $ref: "_definitions.yaml#/to_one" - diagnoses: - $ref: "_definitions.yaml#/to_one" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide.yaml b/gdcdictionary/schemas/slide.yaml deleted file mode 100644 index 2812c2d0f..000000000 --- a/gdcdictionary/schemas/slide.yaml +++ /dev/null @@ -1,138 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide" -title: Slide -type: object -namespace: http://gdc.nci.nih.gov -category: biospecimen -program: '*' -project: '*' -description: > - A digital image, microscopic or otherwise, of any sample, portion, or sub-part thereof. (GDC) -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -links: - - name: samples - backref: slides - label: derived_from - target_type: sample - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - samples - -uniqueKeys: - - [id] - - [project_id, submitter_id] - -# slide properties -properties: - type: - type: string - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - apoptotic_concentration: - description: "The concentration, in cells/mL, of apoptotic cells in the slide blood." - type: number - ctc_concentration: - description: "The concentration, in cells/mL, of traditional CTC cells (intact and enlarged cell and nucleus, cytokeratin positive, and CD45 negative) in the slide blood." - type: number - ctc_low_concentration: - description: "The concentration, in cells/mL, of CTC-low cells (those with low cytokeratin levels compared to traditional CTCs) in the slide blood." - type: number - ctc_small_concentration: - description: "The concentration, in cells/mL, of CTC-small cells (those with a small nuclear and cellular size relative to traditional CTCs) in the slide blood." - type: number - section_location: - term: - $ref: "_terms.yaml#/section_location" - type: string - methanol_added: - description: "True/False indicator for if methanol was used in the slide preparation process." - type: boolean - number_proliferating_cells: - term: - $ref: "_terms.yaml#/number_proliferating_cells" - type: integer - number_nucleated_cells: - description: "The total number of nucleated cells identified on the slide." - type: integer - percent_tumor_cells: - term: - $ref: "_terms.yaml#/percent_tumor_cells" - type: number - percent_tumor_nuclei: - term: - $ref: "_terms.yaml#/percent_tumor_nuclei" - type: number - percent_normal_cells: - term: - $ref: "_terms.yaml#/percent_normal_cells" - type: number - percent_necrosis: - term: - $ref: "_terms.yaml#/percent_necrosis" - type: number - percent_stromal_cells: - term: - $ref: "_terms.yaml#/percent_stromal_cells" - type: number - percent_inflam_infiltration: - term: - $ref: "_terms.yaml#/percent_inflam_infiltration" - type: number - percent_lymphocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_lymphocyte_infiltration" - type: number - percent_monocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_monocyte_infiltration" - type: number - percent_granulocyte_infiltration: - term: - $ref: "_terms.yaml#/percent_granulocyte_infiltration" - type: number - percent_neutrophil_infiltration: - term: - $ref: "_terms.yaml#/percent_neutrophil_infiltration" - type: number - percent_eosinophil_infiltration: - term: - $ref: "_terms.yaml#/percent_eosinophil_infiltration" - type: number - run_datetime: - $ref: "_definitions.yaml#/datetime" - run_name: - description: "Name, number, or other identifier given to this slide's run." - type: string - slide_identifier: - description: "Unique identifier given to the this slide." - type: string - samples: - $ref: "_definitions.yaml#/to_many" - project_id: - $ref: "_definitions.yaml#/project_id" - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide_count.yaml b/gdcdictionary/schemas/slide_count.yaml deleted file mode 100644 index 30002260c..000000000 --- a/gdcdictionary/schemas/slide_count.yaml +++ /dev/null @@ -1,100 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide_count" -title: Slide Count -type: object -namespace: http://gdc.nci.nih.gov -category: notation -program: '*' -project: '*' -description: > - Information pertaining to processed results obtained from slides; often in the form of counts. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - -links: - - name: slides - backref: slide_counts - label: data_from - target_type: slide - multiplicity: many_to_many - required: true - -required: - - submitter_id - - type - - slides - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - type: - enum: [ "slide_count" ] - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - state: - $ref: "_definitions.yaml#/state" - submitter_id: - type: - - string - - "null" - cell_type: - description: "The type of cell being counted or measured." - type: string - cell_identifier: - description: "An alternative identifier for a given cell type." - type: string - cell_count: - description: "Raw count of a particular cell type." - type: integer - ck_signal: - description: "Numeric quantification of the CK signal." - type: number - biomarker_signal: - description: "Numeric quantification of the biomarker signal." - type: number - er_localization: - description: "Cellular localization of the endoplasmic reticulum as determined by staining." - enum: - - Nuclear - - Cytoplasmic - - Both - - None - - Not Determined - frame_identifier: - description: "Name, number, or other identifier given to the frame of the slide from which this image was taken." - type: string - relative_nuclear_size: - description: "The ratio of the single cell's nucleus size to the average of the surrounding cells." - type: number - relative_nuclear_intensity: - description: "The ratio of the single cell's nuclear staining intensity to the average of the surrounding cells." - type: number - relative_cytokeratin_intensity: - description: "The ratio of the single cell's cytokeratin staining intensity to the average of the surrounding cells." - type: number - relative_er_intensity: - description: "The ratio of the single cell's endoplasmic reticulum staining intensity to the average of the surrounding cells." - type: number - run_name: - description: "The name or identifier given to the run that was used to generate this slide count." - type: string - slides: - $ref: "_definitions.yaml#/to_many" - project_id: - type: string - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" diff --git a/gdcdictionary/schemas/slide_image.yaml b/gdcdictionary/schemas/slide_image.yaml deleted file mode 100644 index 50681f71e..000000000 --- a/gdcdictionary/schemas/slide_image.yaml +++ /dev/null @@ -1,109 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "slide_image" -title: Slide Image -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing image of a slide. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: slides - backref: slide_images - label: data_from - target_type: slide - multiplicity: many_to_one - required: false - - name: core_metadata_collections - backref: slide_images - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "slide_image" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Biospecimen - - Slide Image - - Mass Cytometry - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: - - image - - Single Cell Image - - Raw IMC Data - - Single Channel IMC Image - - Antibody Panel Added - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - description: "Classification of the slide type with respect to its experimental use." - enum: - - Diagnostic Slide - - Tissue Slide - cell_type: - description: "The type of cell being imaged or otherwised analysed." - type: string - cell_identifier: - description: "An alternative identifier for a given cell type." - type: string - cell_count: - description: "Count of the cell type being imaged or otherwise analysed." - type: integer - frame_identifier: - description: "Name, number, or other identifier given to the frame of the slide from which this image was taken." - type: string - panel_used: - description: "Name or other identifier given to the panel used during an IMC run." - type: string - protocol_used: - description: "Name or other identifier given to the protocol used during an IMC run." - type: string - run_name: - description: "Name, number, or other identifier given to the run that generated this slide image." - type: string - slides: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_aligned_reads.yaml b/gdcdictionary/schemas/submitted_aligned_reads.yaml deleted file mode 100644 index 59db76bae..000000000 --- a/gdcdictionary/schemas/submitted_aligned_reads.yaml +++ /dev/null @@ -1,95 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_aligned_reads" -title: Submitted Aligned Reads -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing aligned reads that are used as input to GDC workflows. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: read_groups - backref: submitted_aligned_reads_files # pretty ugly - label: data_from - target_type: read_group - multiplicity: one_to_many - required: false - - name: core_metadata_collections - backref: submitted_aligned_reads_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_aligned_reads" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: - - Aligned Reads - - Alignment Coordinates - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - BAM - - BED - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - enum: - - WGS - - WXS - - Low Pass WGS - - Validation - - RNA-Seq - - miRNA-Seq - - Total RNA-Seq - - DNA Panel - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_copy_number.yaml b/gdcdictionary/schemas/submitted_copy_number.yaml deleted file mode 100644 index 2bc9d772c..000000000 --- a/gdcdictionary/schemas/submitted_copy_number.yaml +++ /dev/null @@ -1,91 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_copy_number" -title: Submitted Copy Number -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing normalized copy number information from an aliquot. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_copy_number_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - exclusive: true - required: false - subgroup: - - name: aliquots - backref: submitted_copy_number_files - label: derived_from - target_type: aliquot - multiplicity: one_to_one - required: false - - name: read_groups - backref: submitted_copy_number_files - label: derived_from - target_type: read_group - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_copy_number" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: string - data_type: - term: - $ref: "_terms.yaml#/data_type" - type: string - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - type: string - aliquots: - $ref: "_definitions.yaml#/to_one" - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_methylation.yaml b/gdcdictionary/schemas/submitted_methylation.yaml deleted file mode 100644 index 10408f5f1..000000000 --- a/gdcdictionary/schemas/submitted_methylation.yaml +++ /dev/null @@ -1,86 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_methylation" -title: Submitted Methylation -type: object -namespace: https://www.bloodpac.org/ -category: data_file -program: '*' -project: '*' -description: "DNA methylation data files contain information on raw and normalized signal intensities, detection confidence and calculated beta values for methylated and unmethylated probes. DNA methylation is an epigenetic mark which can be associated with transcriptional inactivity when located in promoter regions." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_methylation_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: aliquots - backref: submitted_methylation_files - label: data_from - target_type: aliquot - multiplicity: many_to_one - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_methylation" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Methylation Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Methylation Intensity Values" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - IDAT - assay_method: - enum: - - Methylation Array - assay_instrument: - enum: - - Illumina - assay_instrument_model: - enum: - - Illumina Infinium HumanMethylation450 - - Illumina Infinium HumanMethylation450K - aliquots: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_somatic_mutation.yaml b/gdcdictionary/schemas/submitted_somatic_mutation.yaml deleted file mode 100644 index f51b502c4..000000000 --- a/gdcdictionary/schemas/submitted_somatic_mutation.yaml +++ /dev/null @@ -1,83 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_somatic_mutation" -title: Submitted Somatic Mutation -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: > - Data file containing somatic mutation calls from a read group. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: core_metadata_collections - backref: submitted_somatic_mutations - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - - name: read_groups - backref: submitted_somatic_mutations - label: derived_from - target_type: read_group - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - data_format - - md5sum - - data_category - - data_type - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_somatic_mutation" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - type: string - data_type: - term: - $ref: "_terms.yaml#/data_type" - type: string - data_format: - term: - $ref: "_terms.yaml#/data_format" - type: string - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - type: string - total_variants: - description: "The total number of variants detected carrying a base change difference from the reference genome." - type: integer - read_groups: - $ref: "_definitions.yaml#/to_many" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_unaligned_reads.yaml b/gdcdictionary/schemas/submitted_unaligned_reads.yaml deleted file mode 100644 index 4b72d4653..000000000 --- a/gdcdictionary/schemas/submitted_unaligned_reads.yaml +++ /dev/null @@ -1,92 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "submitted_unaligned_reads" -title: Submitted Unaligned Reads -type: object -namespace: http://gdc.nci.nih.gov -category: data_file -program: '*' -project: '*' -description: "Data file containing unaligned reads that have not been GDC Harmonized." -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - created_datetime - - updated_datetime - - state - - file_state - - error_type - -links: - - exclusive: false - required: true - subgroup: - - name: read_groups - backref: submitted_unaligned_reads_files # pretty ugly - label: data_from - target_type: read_group - multiplicity: many_to_one - required: false - - name: core_metadata_collections - backref: submitted_unaligned_reads_files - label: data_from - target_type: core_metadata_collection - multiplicity: many_to_many - required: false - -required: - - submitter_id - - type - - file_name - - file_size - - md5sum - - data_category - - data_type - - data_format - - experimental_strategy - -uniqueKeys: - - [ id ] - - [ project_id, submitter_id ] - -properties: - $ref: "_definitions.yaml#/data_file_properties" - type: - enum: [ "submitted_unaligned_reads" ] - data_category: - term: - $ref: "_terms.yaml#/data_category" - enum: - - Sequencing Data - - Sequencing Reads - - Raw Sequencing Data - data_type: - term: - $ref: "_terms.yaml#/data_type" - enum: [ "Unaligned Reads" ] - data_format: - term: - $ref: "_terms.yaml#/data_format" - enum: - - BAM - - FASTQ - experimental_strategy: - term: - $ref: "_terms.yaml#/experimental_strategy" - enum: - - WGS - - WXS - - Low Pass WGS - - Validation - - RNA-Seq - - miRNA-Seq - - Total RNA-Seq - - DNA Panel - read_groups: - $ref: "_definitions.yaml#/to_one" - core_metadata_collections: - $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/treatment.yaml b/gdcdictionary/schemas/treatment.yaml deleted file mode 100644 index 4ed89da04..000000000 --- a/gdcdictionary/schemas/treatment.yaml +++ /dev/null @@ -1,217 +0,0 @@ -$schema: "http://json-schema.org/draft-04/schema#" - -id: "treatment" -title: Treatment -type: object -namespace: http://gdc.nci.nih.gov -category: clinical -program: '*' -project: '*' -description: > - Record of the administration and intention of therapeutic agents provided to a patient to alter - the course of a pathologic process. -additionalProperties: false -submittable: true -validators: null - -systemProperties: - - id - - project_id - - state - - created_datetime - - updated_datetime - -required: - - submitter_id - - type - -links: - - name: diagnoses - backref: treatments - label: describes #need better term here - target_type: diagnosis - multiplicity: many_to_one - required: true - - - -uniqueKeys: - #unclear if want submitter ID for clinical - - [id] - - [project_id, submitter_id] - -properties: - type: - enum: [ "treatment" ] - - id: - $ref: "_definitions.yaml#/UUID" - systemAlias: node_id - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - type: - - string - - "null" - - days_to_treatment: - term: - $ref: "_terms.yaml#/days_to_treatment" - type: number - - days_to_treatment_end: - term: - $ref: "_terms.yaml#/days_to_treatment_end" - type: number - - days_to_treatment_start: - term: - $ref: "_terms.yaml#/days_to_treatment_start" - type: number - - therapeutic_agents: - term: - $ref: "_terms.yaml#/therapeutic_agents" - type: string - - treatment_anatomic_site: - term: - $ref: "_terms.yaml#/treatment_anatomic_site" - enum: - - Abdomen, total - - Arm - - Ascites - - Axillary - - Body, total - - Bone - - Bone, non-spine - - Brain, focal - - Brain, whole - - Brain-C2 - - Breast - - Cervical - - Chest Wall - - Effusion - - Epitrochlear - - Eye - - Femoral - - Gastrointestinal, Colon - - Gastrointestinal, Gallbladder - - Gastrointestinal, Intestine - - Gastrointestinal, Liver - - Gastrointestinal, NOS - - Gastrointestinal, Pancreas - - Gastrointestinal, Rectum - - Gastrointestinal, Stomach - - Genitourinary, Bladder - - Genitourinary, Kidney - - Genitourinary, NOS - - Genitourinary, Prostate - - Genitourinary, Prostate and Seminal Vesicles - - Head - - Head, Face, or Neck - - Hilar - - Iliac-common - - Iliac-external - - Inguinal - - Internal Mammary Nodes - - Leg - - Lung - - Lymph Nodes - - Lymph node, distant (specify site) - - Lymph node, locoregional (specify site) - - Mantle - - Mediastinal - - Mediastinum - - Mesenteric - - Occipital - - Other - - Paraaortic - - Parametrium - - Parotid - - Pelvis - - Popliteal - - Primary tumor site - - Prostate - - Prostate Bed - - Prostate, Seminal Vesicles and Lymph Nodes - - Rectum - - Retroperitoneal - - Sacrum - - Seminal vesicles - - Shoulder - - Skin, lower extremity, local - - Skin, total - - Skin, trunk, local - - Skin, upper extremity, local - - Spine - - Spine, whole - - Splenic - - Submandibular - - Supraclavicular - - Supraclavicular/Axillary Level 3 - - Thorax - - Trunk - - Unknown - - Not Reported - - Not Allowed To Collect - - treatment_intent_type: - term: - $ref: "_terms.yaml#/treatment_intent_type" - type: string - - treatment_or_therapy: - term: - $ref: "_terms.yaml#/treatment_or_therapy" - enum: - - "yes" - - "no" - - unknown - - not reported - - treatment_outcome: - term: - $ref: "_terms.yaml#/treatment_outcome" - enum: - - Complete Response - - Partial Response - - Treatment Ongoing - - Treatment Stopped Due to Toxicity - - Unknown - - treatment_type: - term: - $ref: "_terms.yaml#/treatment_type" - enum: - - Ablation - - Chemotherapy - - Concurrent Chemoradiation - - Cryoablation - - Embolization - - Hormone Therapy - - Internal Radiation - - Immunotherapy (Including Vaccines) - - Other - - Pharmaceutical Therapy - - Radiation Therapy - - Stem Cell Treatment - - Surgery - - Targeted Molecular Therapy - - Unknown - - Not Reported - - Not Allowed To Collect - - diagnoses: - $ref: "_definitions.yaml#/to_one" - - project_id: - $ref: "_definitions.yaml#/project_id" - - # ======== Timestamps ======== - created_datetime: - $ref: "_definitions.yaml#/datetime" - updated_datetime: - $ref: "_definitions.yaml#/datetime" From 6d15e479d7a460d32596cb3660b8c350b86be26b Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Thu, 21 May 2020 16:14:27 -0500 Subject: [PATCH 3/7] add dir --- .travis.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.travis.yml b/.travis.yml index 86f255299..0196e399c 100644 --- a/.travis.yml +++ b/.travis.yml @@ -6,7 +6,7 @@ python: before_script: - yes | python setup.py install - git clone https://github.com/uc-cdis/dictionaryutils -- git checkout feat/format_upgrade +- cd dictionaryutils; git checkout feat/format_upgrade; cd .. script: From 8f0983ead92f1ece4a2d07283df3fce7bcedd78e Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Fri, 22 May 2020 02:30:57 -0500 Subject: [PATCH 4/7] updated yamls --- gdcdictionary/schemas/_settings.yaml | 6 + gdcdictionary/schemas/_terms.yaml | 2553 +++++++++++++++++ gdcdictionary/schemas/acknowledgement.yaml | 77 + .../schemas/aligned_reads_index.yaml | 89 + gdcdictionary/schemas/aliquot.yaml | 120 + gdcdictionary/schemas/case.yaml | 88 + gdcdictionary/schemas/clinical_test.yaml | 253 ++ .../schemas/core_metadata_collection.yaml | 145 + gdcdictionary/schemas/demographic.yaml | 119 + gdcdictionary/schemas/diagnosis.yaml | 848 ++++++ gdcdictionary/schemas/experiment.yaml | 142 + .../schemas/experimental_metadata.yaml | 85 + gdcdictionary/schemas/exposure.yaml | 137 + gdcdictionary/schemas/family_history.yaml | 106 + gdcdictionary/schemas/keyword.yaml | 77 + gdcdictionary/schemas/program.yaml | 47 + gdcdictionary/schemas/project.yaml | 139 + gdcdictionary/schemas/projects/project1.yaml | 21 + gdcdictionary/schemas/publication.yaml | 78 + gdcdictionary/schemas/read_group.yaml | 276 ++ gdcdictionary/schemas/read_group_qc.yaml | 175 ++ gdcdictionary/schemas/sample.yaml | 723 +++++ gdcdictionary/schemas/slide.yaml | 185 ++ gdcdictionary/schemas/slide_count.yaml | 144 + gdcdictionary/schemas/slide_image.yaml | 136 + .../schemas/submitted_aligned_reads.yaml | 105 + .../schemas/submitted_copy_number.yaml | 89 + .../schemas/submitted_methylation.yaml | 103 + .../schemas/submitted_somatic_mutation.yaml | 96 + .../schemas/submitted_unaligned_reads.yaml | 104 + gdcdictionary/schemas/treatment.yaml | 221 ++ 31 files changed, 7487 insertions(+) create mode 100644 gdcdictionary/schemas/_settings.yaml create mode 100644 gdcdictionary/schemas/_terms.yaml create mode 100644 gdcdictionary/schemas/acknowledgement.yaml create mode 100644 gdcdictionary/schemas/aligned_reads_index.yaml create mode 100644 gdcdictionary/schemas/aliquot.yaml create mode 100644 gdcdictionary/schemas/case.yaml create mode 100644 gdcdictionary/schemas/clinical_test.yaml create mode 100644 gdcdictionary/schemas/core_metadata_collection.yaml create mode 100644 gdcdictionary/schemas/demographic.yaml create mode 100644 gdcdictionary/schemas/diagnosis.yaml create mode 100644 gdcdictionary/schemas/experiment.yaml create mode 100644 gdcdictionary/schemas/experimental_metadata.yaml create mode 100644 gdcdictionary/schemas/exposure.yaml create mode 100644 gdcdictionary/schemas/family_history.yaml create mode 100644 gdcdictionary/schemas/keyword.yaml create mode 100644 gdcdictionary/schemas/program.yaml create mode 100644 gdcdictionary/schemas/project.yaml create mode 100644 gdcdictionary/schemas/projects/project1.yaml create mode 100644 gdcdictionary/schemas/publication.yaml create mode 100644 gdcdictionary/schemas/read_group.yaml create mode 100644 gdcdictionary/schemas/read_group_qc.yaml create mode 100644 gdcdictionary/schemas/sample.yaml create mode 100644 gdcdictionary/schemas/slide.yaml create mode 100644 gdcdictionary/schemas/slide_count.yaml create mode 100644 gdcdictionary/schemas/slide_image.yaml create mode 100644 gdcdictionary/schemas/submitted_aligned_reads.yaml create mode 100644 gdcdictionary/schemas/submitted_copy_number.yaml create mode 100644 gdcdictionary/schemas/submitted_methylation.yaml create mode 100644 gdcdictionary/schemas/submitted_somatic_mutation.yaml create mode 100644 gdcdictionary/schemas/submitted_unaligned_reads.yaml create mode 100644 gdcdictionary/schemas/treatment.yaml diff --git a/gdcdictionary/schemas/_settings.yaml b/gdcdictionary/schemas/_settings.yaml new file mode 100644 index 000000000..d7e2171a4 --- /dev/null +++ b/gdcdictionary/schemas/_settings.yaml @@ -0,0 +1,6 @@ +# Global settings for the graph + +# Is the graph case centric, that we want +# to create a link between all children to case +# to expedite case filter on nodes +enable_case_cache: false diff --git a/gdcdictionary/schemas/_terms.yaml b/gdcdictionary/schemas/_terms.yaml new file mode 100644 index 000000000..442940b4b --- /dev/null +++ b/gdcdictionary/schemas/_terms.yaml @@ -0,0 +1,2553 @@ + +id: _terms + +28s_16s_ribosomal_rna_ratio: + common: + description: >- + The 28S/18S ribosomal RNA band ratio used to assess the quality of total RNA. + termDef: + term: >- + 28s/18s Ribosomal RNA Ratio + source: + cde_id: + cde_version: + term_url: + +a260_a280_ratio: + common: + description: >- + Numeric value that represents the sample ratio of nucleic acid absorbance at + 260 nm and 280 nm, used to determine a measure of DNA purity. + termDef: + term: >- + Nucleic Acid Absorbance at 260 And Absorbance at 280 DNA Purity Ratio Value + source: caDSR + cde_id: 5432595 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432595&version=1.0" + +adapter_name: + common: + description: >- + Name of the sequencing adapter. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +adapter_sequence: + common: + description: >- + Base sequence of the sequencing adapter. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +age_at_diagnosis: + common: + description: >- + Age at the time of diagnosis expressed in number of days since birth. + termDef: + term: >- + Patient Diagnosis Age Day Value + source: caDSR + cde_id: 3225640 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225640&version=2.0" + +ajcc_clinical_m: + common: + description: >- + Extent of the distant metastasis for the cancer based on evidence obtained from + clinical assessment parameters determined prior to treatment. + termDef: + term: >- + Neoplasm American Joint Committee on Cancer Clinical Distant Metastasis M + Stage + source: caDSR + cde_id: 3440331 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440331&version=1.0" + +ajcc_clinical_n: + common: + description: >- + Extent of the regional lymph node involvement for the cancer based on evidence + obtained from clinical assessment parameters determined prior to treatment. + termDef: + term: >- + Neoplasm American Joint Committee on Cancer Clinical Regional Lymph Node N + Stage + source: caDSR + cde_id: 3440330 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440330&version=1.0" + +ajcc_clinical_stage: + common: + description: >- + Stage group determined from clinical information on the tumor (T), regional + node (N) and metastases (M) and by grouping cases with similar prognosis for + cancer. + termDef: + term: >- + Neoplasm American Joint Committee on Cancer Clinical Group Stage + source: caDSR + cde_id: 3440332 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440332&version=1.0" + +ajcc_clinical_t: + common: + description: >- + Extent of the primary cancer based on evidence obtained from clinical assessment + parameters determined prior to treatment. + termDef: + term: >- + Neoplasm American Joint Committee on Cancer Clinical Primary Tumor T Stage + source: caDSR + cde_id: 3440328 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3440328&version=1.0" + +ajcc_pathologic_m: + common: + description: >- + Code to represent the defined absence or presence of distant spread or metastases + (M) to locations via vascular channels or lymphatics beyond the regional lymph + nodes, using criteria established by the American Joint Committee on Cancer + (AJCC). + termDef: + term: >- + American Joint Committee on Cancer Metastasis Stage Code + source: caDSR + cde_id: 3045439 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045439&version=1.0" + +ajcc_pathologic_n: + common: + description: >- + The codes that represent the stage of cancer based on the nodes present (N stage) + according to criteria based on multiple editions of the AJCC's Cancer Staging + Manual. + termDef: + term: >- + Neoplasm Disease Lymph Node Stage American Joint Committee on Cancer Code + source: caDSR + cde_id: 3203106 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203106&version=1.0" + +ajcc_pathologic_stage: + common: + description: >- + The extent of a cancer, especially whether the disease has spread from the original + site to other parts of the body based on AJCC staging criteria. + termDef: + term: >- + Neoplasm Disease Stage American Joint Committee on Cancer Code + source: caDSR + cde_id: 3203222 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3203222&version=1.0" + +ajcc_pathologic_t: + common: + description: >- + Code of pathological T (primary tumor) to define the size or contiguous extension + of the primary tumor (T), using staging criteria from the American Joint Committee + on Cancer (AJCC). + termDef: + term: >- + American Joint Committee on Cancer Tumor Stage Code + source: caDSR + cde_id: 3045435 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3045435&version=1.0" + +alcohol_history: + common: + description: >- + A response to a question that asks whether the participant has consumed at least + 12 drinks of any kind of alcoholic beverage in their lifetime. + termDef: + term: >- + Alcohol Lifetime History Indicator + source: caDSR + cde_id: 2201918 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2201918&version=1.0" + +alcohol_intensity: + common: + description: >- + Category to describe the patient's current level of alcohol use as self-reported + by the patient. + termDef: + term: >- + Person Self-Report Alcoholic Beverage Exposure Category + source: caDSR + cde_id: 3457767 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3457767&version=1.0" + +aliquot_quantity: + common: + description: >- + The quantity in micrograms (ug) of the aliquot(s) derived from the analyte(s) + shipped for sequencing and characterization. + termDef: + term: >- + Biospecimen Aliquot Quantity + source: + cde_id: + cde_version: + term_url: + +aliquot_volume: + common: + description: >- + The volume in microliters (ml) of the aliquot(s) derived from the analyte(s) + shipped for sequencing and characterization. + termDef: + term: >- + Biospecimen Aliquot Volume + source: + cde_id: + cde_version: + term_url: + +amount: + common: + description: >- + Weight in grams or volume in mL. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +analyte_quantity: + common: + description: >- + The quantity in micrograms (ug) of the analyte(s) derived from the analyte(s) + shipped for sequencing and characterization. + termDef: + term: >- + Biospecimen Analyte Quantity + source: + cde_id: + cde_version: + term_url: + +analyte_type: + common: + description: >- + Text term that represents the kind of molecular specimen analyte. + termDef: + term: >- + Molecular Specimen Type Text Name + source: caDSR + cde_id: 2513915 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2513915&version=2.0" + +analyte_type_id: + common: + description: >- + A single letter code used to identify a type of molecular analyte. + termDef: + term: >- + Molecular Analyte Identification Code + source: caDSR + cde_id: 5432508 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432508&version=1.0" + +analyte_volume: + common: + description: >- + The volume in microliters (ml) of the analyte(s) derived from the analyte(s) + shipped for sequencing and characterization. + termDef: + term: >- + Biospecimen Analyte Volume + source: + cde_id: + cde_version: + term_url: + +ann_arbor_b_symptoms: + common: + description: >- + Text term to signify whether lymphoma B-symptoms are present as noted in the + patient's medical record. + termDef: + term: >- + Lymphoma B-Symptoms Medical Record Documented Indicator + source: caDSR + cde_id: 2902402 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2902402&version=1.0" + +ann_arbor_clinical_stage: + common: + description: >- + The classification of the clinically confirmed anatomic disease extent of lymphoma + (Hodgkin's and Non-Hodgkins) based on the Ann Arbor Staging System. + termDef: + term: >- + Ann Arbor Clinical Stage + source: + cde_id: + cde_version: + term_url: + +ann_arbor_extranodal_involvement: + common: + description: >- + Indicator that identifies whether a patient with malignant lymphoma has lymphomatous + involvement of an extranodal site. + termDef: + term: >- + Lymphomatous Extranodal Site Involvement Indicator + source: caDSR + cde_id: 3364582 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3364582&version=1.0" + +ann_arbor_pathologic_stage: + common: + description: >- + The classification of the pathologically confirmed anatomic disease extent of + lymphoma (Hodgkin's and Non-Hodgkins) based on the Ann Arbor Staging System. + termDef: + term: >- + Ann Arbor Pathologic Stage + source: + cde_id: + cde_version: + term_url: + +ann_arbor_tumor_stage: + common: + description: >- + The classification of the anatomic disease extent of lymphoma (Hodgkin's and + Non-Hodgkins) based on the Ann Arbor Staging System. + termDef: + term: >- + Ann Arbor Tumor Stage + source: + cde_id: + cde_version: + term_url: + +base_caller_name: + common: + description: >- + Name of the base caller. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +base_caller_version: + common: + description: >- + Version of the base caller. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +biomarker_name: + common: + description: >- + The name of the biomarker being tested for this specimen and set of test results. + termDef: + term: >- + Biomarker Name + source: caDSR + cde_id: 5473 + cde_version: 11.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5473&version=2.31" + +biomarker_result: + common: + description: >- + Text term to define the results of genetic testing. + termDef: + term: >- + Laboratory Procedure Genetic Abnormality Test Result Type + source: caDSR + cde_id: 3234680 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3234680&version=1.0" + +biomarker_test_method: + common: + description: >- + Text descriptor of a molecular analysis method used for an individual. + termDef: + term: >- + Disease Detection Molecular Analysis Method Type + source: caDSR + cde_id: 3121575 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121575&version=1.0" + +biospecimen_anatomic_site: + common: + description: >- + Text term that represents the name of the primary disease site of the submitted + tumor sample. + termDef: + term: >- + Submitted Tumor Sample Primary Anatomic Site + source: caDSR + cde_id: 4742851 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4742851&version=1.0" + +bmi: + common: + description: >- + The body mass divided by the square of the body height expressed in units of + kg/m^2. + termDef: + term: >- + Body Mass Index (BMI) + source: caDSR + cde_id: 4973892 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4973892&version=1.0" + +burkitt_lymphoma_clinical_variant: + common: + description: >- + Burkitt's lymphoma categorization based on clinical features that differ from + other forms of the same disease. + termDef: + term: >- + Burkitt Lymphoma Clinical Variant Type + source: caDSR + cde_id: 3770421 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3770421&version=1.0" + +cause_of_death: + common: + description: >- + Text term to identify the cause of death for a patient. + termDef: + term: >- + Patient Death Reason + source: caDSR + cde_id: 2554674 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2554674&version=3.0" + +cea_level_preoperative: + common: + description: >- + Numeric value of the Carcinoembryonic antigen or CEA at the time before surgery. + [Manually- curated] + termDef: + term: >- + Preoperative Carcinoembryonic Antigen Result Value + source: caDSR + cde_id: 2716510 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2716510&version=1.0" + +cigarettes_per_day: + common: + description: >- + The average number of cigarettes smoked per day. + termDef: + term: >- + Smoking Use Average Number + source: caDSR + cde_id: 2001716 + cde_version: 4.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2001716&version=4.0" + +circumferential_resection_margin: + common: + description: >- + A value in millimeters indicating the measured length between a malignant lesion + of the colon or rectum and the nearest radial (or circumferential) border of + tissue removed during cancer surgery. + termDef: + term: >- + Colorectal Surgical Margin Circumferential Distance Measurement + source: caDSR + cde_id: 64202 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64202&version=3.0" + +classification_of_tumor: + common: + description: >- + Text that describes the kind of disease present in the tumor specimen as related + to a specific timepoint. + termDef: + term: >- + Tumor Tissue Disease Description Type + source: caDSR + cde_id: 3288124 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" + +colon_polyps_history: + common: + description: >- + Yes/No indicator to describe if the subject had a previous history of colon + polyps as noted in the history/physical or previous endoscopic report (s). + termDef: + term: >- + Colon Carcinoma Polyp Occurrence Indicator + source: caDSR + cde_id: 3107197 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3107197&version=1.0" + +composition: + common: + description: >- + Text term that represents the cellular composition of the sample. + termDef: + term: >- + Biospecimen Cellular Composition Type + source: caDSR + cde_id: 5432591 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432591&version=1.0" + +concentration: + common: + description: >- + Numeric value that represents the concentration of an analyte or aliquot extracted + from the sample or sample portion, measured in milligrams per milliliter. + termDef: + term: >- + Biospecimen Analyte or Aliquot Extracted Concentration Milligram per Milliliter + Value + source: caDSR + cde_id: 5432594 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432594&version=1.0" + +creation_datetime: + common: + description: >- + The datetime of portion creation encoded as seconds from epoch. + termDef: + term: >- + Biospecimen Portion Creation Seconds Date/Time + source: caDSR + cde_id: 5432592 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432592&version=1.0" + +current_weight: + common: + description: >- + Numeric value that represents the current weight of the sample, measured in + milligrams. + termDef: + term: >- + Tissue Sample Current Weight Milligram Value + source: caDSR + cde_id: 5432606 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432606&version=1.0" + +data_category: + common: + description: >- + Broad categorization of the contents of the data file. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +data_file_error_type: + common: + description: >- + Type of error for the data file object. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +data_format: + common: + description: >- + Format of the data files. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +data_type: + common: + description: >- + Specific content type of the data file. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +datetime: + common: + description: >- + A combination of date and time of day in the form [-]CCYY-MM-DDThh:mm:ss[Z|(+|-)hh:mm] + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +days_to_birth: + common: + description: >- + Time interval from a person's date of birth to the date of initial pathologic + diagnosis, represented as a calculated negative number of days. + termDef: + term: >- + Person Birth Date Less Initial Pathologic Diagnosis Date Calculated Day Value + source: caDSR + cde_id: 3008233 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008233&version=1.0" + +days_to_collection: + common: + description: >- + Time interval from the date of biospecimen collection to the date of initial + pathologic diagnosis, represented as a calculated number of days. + termDef: + term: >- + Biospecimen Collection Date Less Initial Pathologic Diagnosis Date Calculated + Day Value + source: caDSR + cde_id: 3008340 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008340&version=1.0" + +days_to_death: + common: + description: >- + Time interval from a person's date of death to the date of initial pathologic + diagnosis, represented as a calculated number of days. + termDef: + term: >- + Death Less Initial Pathologic Diagnosis Date Calculated Day Value + source: caDSR + cde_id: 3165475 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3165475&version=1.0" + +days_to_hiv_diagnosis: + common: + description: >- + Time interval from the date of the initial pathologic diagnosis to the date + of human immunodeficiency diagnosis, represented as a calculated number of days. + termDef: + term: >- + Human Immunodeficiency Virus Diagnosis Subtract Initial Pathologic Diagnosis + Time Duration Day Calculation Value + source: caDSR + cde_id: 4618491 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4618491&version=1.0" + +days_to_last_follow_up: + common: + description: >- + Time interval from the date of last follow up to the date of initial pathologic + diagnosis, represented as a calculated number of days. + termDef: + term: >- + Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated + Day Value + source: caDSR + cde_id: 3008273 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" + +days_to_last_known_disease_status: + common: + description: >- + Time interval from the date of last follow up to the date of initial pathologic + diagnosis, represented as a calculated number of days. + termDef: + term: >- + Last Communication Contact Less Initial Pathologic Diagnosis Date Calculated + Day Value + source: caDSR + cde_id: 3008273 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008273&version=1.0" + +days_to_new_event: + common: + description: >- + Time interval from the date of new tumor event including progression, recurrence + and new primary malignacies to the date of initial pathologic diagnosis, represented + as a calculated number of days. + termDef: + term: >- + New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value + source: caDSR + cde_id: 3392464 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" + +days_to_recurrence: + common: + description: >- + Time interval from the date of new tumor event including progression, recurrence + and new primary malignancies to the date of initial pathologic diagnosis, represented + as a calculated number of days. + termDef: + term: >- + New Tumor Event Less Initial Pathologic Diagnosis Date Calculated Day Value + source: caDSR + cde_id: 3392464 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3392464&version=1.0" + +days_to_sample_procurement: + common: + description: >- + The number of days from the date the patient was diagnosed to the date of the + procedure that produced the sample. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +days_to_treatment: + common: + description: >- + Number of days from date of initial pathologic diagnosis that treatment began. + termDef: + term: >- + Days to Treatment Start + source: + cde_id: + cde_version: + term_url: + +days_to_treatment_end: + common: + description: >- + Time interval from the date of the initial pathologic diagnosis to the date + of treatment end, represented as a calculated number of days. + termDef: + term: >- + Treatment End Subtract First Pathologic Diagnosis Day Calculation Value + source: caDSR + cde_id: 5102431 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102431&version=1.0" + +days_to_treatment_start: + common: + description: >- + Time interval from the date of the initial pathologic diagnosis to the start + of treatment, represented as a calculated number of days. + termDef: + term: >- + Treatment Start Subtract First Pathologic Diagnosis Time Day Calculation Value + source: caDSR + cde_id: 5102411 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102411&version=1.0" + +diagnosis_pathologically_confirmed: + common: + description: >- + The histologic description of tissue or cells confirmed by a pathology review + of frozen or formalin fixed slide(s) completed after the diagnostic pathology + review of the tumor sample used to extract analyte(s). + termDef: + term: >- + Post-Diagnostic Pathology Review Confirmation + source: + cde_id: + cde_version: + term_url: + +dlco_ref_predictive_percent: + common: + description: >- + The value, as a percentage of predicted lung volume, measuring the amount of + carbon monoxide detected in a patient's lungs. + termDef: + term: >- + Lung Carbon Monoxide Diffusing Capability Test Assessment Predictive Value + Percentage Value + source: caDSR + cde_id: 2180255 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2180255&version=1.0" + +encoding: + common: + description: >- + Version of ASCII encoding of quality values found in the file. + termDef: + term: >- + Encoding + source: FastQC + cde_id: + cde_version: + term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" + +estrogen_receptor_percent_positive_ihc: + common: + description: >- + Classification to represent ER Positive results expressed as a percentage value. + termDef: + term: >- + ER Level Cell Percentage Category + source: caDSR + cde_id: 3128341 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128341&version=1.0" + +estrogen_receptor_result_ihc: + common: + description: >- + Text term to represent the overall result of Estrogen Receptor (ER) testing. + termDef: + term: >- + Breast Carcinoma Estrogen Receptor Status + source: caDSR + cde_id: 2957359 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957359&version=2.0" + +ethnicity: + common: + description: >- + An individual's self-described social and cultural grouping, specifically whether + an individual describes themselves as Hispanic or Latino. The provided values + are based on the categories defined by the U.S. Office of Management and Business + and used by the U.S. Census Bureau. + termDef: + term: >- + Ethnic Group Category Text + source: caDSR + cde_id: 2192217 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192217&version=2.0" + +experiment_name: + common: + description: >- + Submitter-defined name for the experiment. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +experimental_strategy: + common: + description: >- + The sequencing strategy used to generate the data file. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +fastq_name: + common: + description: >- + Names of FASTQs. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +fev1_ref_post_bronch_percent: + common: + description: >- + The percentage comparison to a normal value reference range of the volume of + air that a patient can forcibly exhale from the lungs in one second post-bronchodilator. + termDef: + term: >- + Post Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value + source: caDSR + cde_id: 3302948 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302948&version=1.0" + +fev1_ref_pre_bronch_percent: + common: + description: >- + The percentage comparison to a normal value reference range of the volume of + air that a patient can forcibly exhale from the lungs in one second pre-bronchodilator. + termDef: + term: >- + Pre Bronchodilator Lung Forced Expiratory Volume 1 Test Lab Percentage Value + source: caDSR + cde_id: 3302947 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302947&version=1.0" + +fev1_fvc_post_bronch_percent: + common: + description: >- + Percentage value to represent result of Forced Expiratory Volume in 1 second + (FEV1) divided by the Forced Vital Capacity (FVC) post-bronchodilator. + termDef: + term: >- + Post Bronchodilator FEV1/FVC Percent Value + source: caDSR + cde_id: 3302956 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302956&version=1.0" + +fev1_fvc_pre_bronch_percent: + common: + description: >- + Percentage value to represent result of Forced Expiratory Volume in 1 second + (FEV1) divided by the Forced Vital Capacity (FVC) pre-bronchodilator. + termDef: + term: >- + Pre Bronchodilator FEV1/FVC Percent Value + source: caDSR + cde_id: 3302955 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3302955&version=1.0" + +figo_stage: + common: + description: >- + The extent of a cervical or endometrial cancer within the body, especially whether + the disease has spread from the original site to other parts of the body, as + described by the International Federation of Gynecology and Obstetrics (FIGO) + stages. + termDef: + term: >- + Gynecologic Tumor Grouping Cervical Endometrial FIGO 2009 Stage + source: caDSR + cde_id: 3225684 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3225684&version=1.0" + +file_name: + common: + description: >- + The name (or part of a name) of a file (of any type). + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +file_size: + common: + description: >- + The size of the data file (object) in bytes. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +file_state: + common: + description: >- + The current state of the data file object. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +flow_cell_barcode: + common: + description: >- + Flow Cell Barcode. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +freezing_method: + common: + description: >- + Text term that represents the method used for freezing the sample. + termDef: + term: >- + Tissue Sample Freezing Method Type + source: caDSR + cde_id: 5432607 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432607&version=1.0" + +gender: + common: + description: >- + Text designations that identify gender. Gender is described as the assemblage + of properties that distinguish people on the basis of their societal roles. + [Explanatory Comment 1: Identification of gender is based upon self-report and + may come from a form, questionnaire, interview, etc.] + termDef: + term: >- + Person Gender Text Type + source: caDSR + cde_id: 2200604 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2200604&version=3.0" + +height: + common: + description: >- + The height of the patient in centimeters. + termDef: + term: >- + Patient Height Measurement + source: caDSR + cde_id: 649 + cde_version: 4.1 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=649&version=4.1" + +her2_erbb2_percent_positive_ihc: + common: + description: >- + Classification to represent the number of positive HER2/ERBB2 cells in a specimen + or sample. + termDef: + term: >- + HER2 ERBB Positive Finding Cell Percentage Category + source: caDSR + cde_id: 3086980 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3086980&version=1.0" + +her2_erbb2_result_fish: + common: + description: >- + the type of outcome for HER2 as determined by an in situ hybridization (ISH) + assay. + termDef: + term: >- + Laboratory Procedure HER2/neu in situ Hybridization Outcome Type + source: caDSR + cde_id: 2854089 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2854089&version=1.0" + +her2_erbb2_result_ihc: + common: + description: >- + Text term to signify the result of the medical procedure that involves testing + a sample of blood or tissue for HER2 by histochemical localization of immunoreactive + substances using labeled antibodies as reagents. + termDef: + term: >- + Laboratory Procedure HER2/neu Immunohistochemistry Receptor Status + source: caDSR + cde_id: 2957563 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957563&version=2.0" + +hiv_positive: + common: + description: >- + Text term to signify whether a physician has diagnosed HIV infection in a patient. + termDef: + term: >- + Physician Diagnosed HIV Infection Personal Medical History Yes No Not Applicable + Indicator + source: caDSR + cde_id: 4030799 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4030799&version=1.0" + +hpv_positive_type: + common: + description: >- + Text classification to represent the strain or type of human papillomavirus + identified in an individual. + termDef: + term: >- + Human Papillomavirus Type + source: caDSR + cde_id: 2922649 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2922649&version=1.0" + +hpv_status: + common: + description: >- + The findings of the oncogenic HPV. + termDef: + term: >- + Oncogenic Human Papillomavirus Result Type + source: caDSR + cde_id: 2230033 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2230033&version=1.0" + +includes_spike_ins: + common: + description: >- + Spike-in included? + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +initial_weight: + common: + description: >- + Numeric value that represents the initial weight of the sample, measured in + milligrams. + termDef: + term: >- + Tissue Sample Initial Weight Milligram Value + source: caDSR + cde_id: 5432605 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432605&version=1.0" + +instrument_model: + common: + description: >- + Numeric value that represents the sample dimension that is greater than the + shortest dimension and less than the longest dimension, measured in millimeters. + termDef: + term: >- + Tissue Sample Intermediate Dimension Millimeter Measurement + source: caDSR + cde_id: 5432604 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432604&version=1.0" + +intermediate_dimension: + common: + description: >- + Intermediate dimension of the sample, in millimeters. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +is_ffpe: + common: + description: >- + Indicator to signify whether or not the tissue sample was fixed in formalin + and embedded in paraffin (FFPE). + termDef: + term: >- + Specimen Processing Formalin Fixed Paraffin Embedded Tissue Indicator + source: caDSR + cde_id: 4170557 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4170557&version=1.0" + +is_paired_end: + common: + description: >- + Are the reads paired end? + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +last_known_disease_status: + common: + description: >- + Text term that describes the last known state or condition of an individual's + neoplasm. + termDef: + term: >- + Person Last Known Neoplasm Status + source: caDSR + cde_id: 5424231 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2759550&version=1.0" + +laterality: + common: + description: >- + For tumors in paired organs, designates the side on which the cancer originates. + termDef: + term: >- + Primary Tumor Laterality + source: caDSR + cde_id: 827 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=827&version=3.0" + +ldh_level_at_diagnosis: + common: + description: >- + The 2 decimal place numeric laboratory value measured, assigned or computed + related to the assessment of lactate dehydrogenase in a specimen. + termDef: + term: >- + Laboratory Procedure Lactate Dehydrogenase Result Integer::2 Decimal Place + Value + source: caDSR + cde_id: 2798766 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2798766&version=1.0" + +ldh_normal_range_upper: + common: + description: >- + The top value of the range of statistical characteristics that are supposed + to represent accepted standard, non-pathological pattern for lactate dehydrogenase + (units not specified). + termDef: + term: >- + Laboratory Procedure Lactate Dehydrogenase Result Upper Limit of Normal Value + source: caDSR + cde_id: 2597015 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2597015&version=1.0" + +library_strategy: + common: + description: >- + Library strategy. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_selection: + common: + description: >- + Library Selection Method + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_name: + common: + description: >- + Name of the library. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_preparation_kit_name: + common: + description: >- + Name of Library Preparation Kit + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_preparation_kit_vendor: + common: + description: >- + Vendor of Library Preparation Kit + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_preparation_kit_catalog_number: + common: + description: >- + Catalog of Library Preparation Kit + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_preparation_kit_version: + common: + description: >- + Version of Library Preparation Kit + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +library_strand: + common: + description: >- + Library stranded-ness. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +longest_dimension: + common: + description: >- + Numeric value that represents the longest dimension of the sample, measured + in millimeters. + termDef: + term: >- + Tissue Sample Longest Dimension Millimeter Measurement + source: caDSR + cde_id: 5432602 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432602&version=1.0" + +lymph_nodes_positive: + common: + description: >- + The number of lymph nodes involved with disease as determined by pathologic + examination. + termDef: + term: >- + Lymph Node(s) Positive Number + source: caDSR + cde_id: 89 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=89&version=3.0" + +lymphatic_invasion_present: + common: + description: >- + A yes/no indicator to ask if small or thin-walled vessel invasion is present, + indicating lymphatic involvement + termDef: + term: >- + Lymphatic/Small vessel Invasion Ind + source: caDSR + cde_id: 64171 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64171&version=3.0" + +method_of_diagnosis: + common: + description: >- + The method used to initially the patient's diagnosis. + termDef: + term: >- + Method of Diagnosis + source: + cde_id: + cde_version: + term_url: + +method_of_sample_procurement: + common: + description: >- + The method used to procure the sample used to extract analyte(s). + termDef: + term: >- + Method of Sample Procurement + source: + cde_id: + cde_version: + term_url: + +md5sum: + common: + description: >- + The 128-bit hash value expressed as a 32 digit hexadecimal number used as a + file's digital fingerprint. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +microsatellite_instability_abnormal: + common: + description: >- + The yes/no indicator to signify the status of a tumor for microsatellite instability. + termDef: + term: >- + Microsatellite Instability Occurrence Indicator + source: caDSR + cde_id: 3123142 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3123142&version=1.0" + +morphology: + common: + description: >- + The third edition of the International Classification of Diseases for Oncology, + published in 2000 used principally in tumor and cancer registries for coding + the site (topography) and the histology (morphology) of neoplasms. The study + of the structure of the cells and their arrangement to constitute tissues and, + finally, the association among these to form organs. In pathology, the microscopic + process of identifying normal and abnormal morphologic characteristics in tissues, + by employing various cytochemical and immunocytochemical stains. A system of + numbered categories for representation of data. + termDef: + term: >- + International Classification of Diseases for Oncology, Third Edition ICD-O-3 + Histology Code + source: caDSR + cde_id: 3226275 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226275&version=1.0" + +new_event_anatomic_site: + common: + description: >- + Text term to specify the anatomic location of the return of tumor after treatment. + termDef: + term: >- + New Neoplasm Event Occurrence Anatomic Site + source: caDSR + cde_id: 3108271 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3108271&version=2.0" + +new_event_type: + common: + description: >- + Text term to identify a new tumor event. + termDef: + term: >- + New Neoplasm Event Type + source: caDSR + cde_id: 3119721 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3119721&version=1.0" + +normal_tumor_genotype_snp_match: + common: + description: >- + Text term that represents whether or not the genotype of the normal tumor matches + or if the data is not available. + termDef: + term: >- + Normal Tumor Genotype Match Indicator + source: caDSR + cde_id: 4588156 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4588156&version=1.0" + +number_proliferating_cells: + common: + description: >- + Numeric value that represents the count of proliferating cells determined during + pathologic review of the sample slide(s). + termDef: + term: >- + Pathology Review Slide Proliferating Cell Count + source: caDSR + cde_id: 5432636 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432636&version=1.0" + +oct_embedded: + common: + description: >- + Indicator of whether or not the sample was embedded in Optimal Cutting Temperature + (OCT) compound. + termDef: + term: >- + Tissue Sample Optimal Cutting Temperature Compound Embedding Indicator + source: caDSR + cde_id: 5432538 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432538&version=1.0" + +pack_years_smoked: + common: + description: >- + Numeric computed value to represent lifetime tobacco exposure defined as number + of cigarettes smoked per day x number of years smoked divided by 20. + termDef: + term: >- + Person Cigarette Smoking History Pack Year Value + source: caDSR + cde_id: 2955385 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" + +percent_eosinophil_infiltration: + common: + description: >- + Numeric value to represent the percentage of infiltration by eosinophils in + a tumor sample or specimen. + termDef: + term: >- + Specimen Eosinophilia Percentage Value + source: caDSR + cde_id: 2897700 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897700&version=2.0" + +percent_gc_content: + common: + description: >- + The overall %GC of all bases in all sequences. + termDef: + term: >- + %GC + source: FastQC + cde_id: + cde_version: + term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" + +percent_granulocyte_infiltration: + common: + description: >- + Numeric value to represent the percentage of infiltration by granulocytes in + a tumor sample or specimen. + termDef: + term: >- + Specimen Granulocyte Infiltration Percentage Value + source: caDSR + cde_id: 2897705 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897705&version=2.0" + +percent_inflam_infiltration: + common: + description: >- + Numeric value to represent local response to cellular injury, marked by capillary + dilatation, edema and leukocyte infiltration; clinically, inflammation is manifest + by reddness, heat, pain, swelling and loss of function, with the need to heal + damaged tissue. + termDef: + term: >- + Specimen Inflammation Change Percentage Value + source: caDSR + cde_id: 2897695 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897695&version=1.0" + +percent_lymphocyte_infiltration: + common: + description: >- + Numeric value to represent the percentage of infiltration by lymphocytes in + a solid tissue normal sample or specimen. + termDef: + term: >- + Specimen Lymphocyte Infiltration Percentage Value + source: caDSR + cde_id: 2897710 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897710&version=2.0" + +percent_monocyte_infiltration: + common: + description: >- + Numeric value to represent the percentage of monocyte infiltration in a sample + or specimen. + termDef: + term: >- + Specimen Monocyte Infiltration Percentage Value + source: caDSR + cde_id: 5455535 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5455535&version=1.0" + +percent_necrosis: + common: + description: >- + Numeric value to represent the percentage of cell death in a malignant tumor + sample or specimen. + termDef: + term: >- + Malignant Neoplasm Necrosis Percentage Value + source: caDSR + cde_id: 2841237 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841237&version=1.0" + +percent_neutrophil_infiltration: + common: + description: >- + Numeric value to represent the percentage of infiltration by neutrophils in + a tumor sample or specimen. + termDef: + term: >- + Malignant Neoplasm Neutrophil Infiltration Percentage Cell Value + source: caDSR + cde_id: 2841267 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841267&version=1.0" + +percent_normal_cells: + common: + description: >- + Numeric value to represent the percentage of normal cell content in a malignant + tumor sample or specimen. + termDef: + term: >- + Malignant Neoplasm Normal Cell Percentage Value + source: caDSR + cde_id: 2841233 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841233&version=1.0" + +percent_stromal_cells: + common: + description: >- + Numeric value to represent the percentage of reactive cells that are present + in a malignant tumor sample or specimen but are not malignant such as fibroblasts, + vascular structures, etc. + termDef: + term: >- + Malignant Neoplasm Stromal Cell Percentage Value + source: caDSR + cde_id: 2841241 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841241&version=1.0" + +percent_tumor_cells: + common: + description: >- + Numeric value that represents the percentage of infiltration by granulocytes + in a sample. + termDef: + term: >- + Specimen Tumor Cell Percentage Value + source: caDSR + cde_id: 5432686 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432686&version=1.0" + +percent_tumor_nuclei: + common: + description: >- + Numeric value to represent the percentage of tumor nuclei in a malignant neoplasm + sample or specimen. + termDef: + term: >- + Malignant Neoplasm Neoplasm Nucleus Percentage Cell Value + source: caDSR + cde_id: 2841225 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2841225&version=1.0" + +perineural_invasion_present: + common: + description: >- + a yes/no indicator to ask if perineural invasion or infiltration of tumor or + cancer is present. + termDef: + term: >- + Tumor Perineural Invasion Ind + source: caDSR + cde_id: 64181 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64181&version=3.0" + +platform: + common: + description: >- + Name of the platform used to obtain data. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +portion_number: + common: + description: >- + Numeric value that represents the sequential number assigned to a portion of + the sample. + termDef: + term: >- + Biospecimen Portion Sequence Number + source: caDSR + cde_id: 5432711 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432711&version=1.0" + +portion_weight: + common: + description: >- + Numeric value that represents the sample portion weight, measured in milligrams. + termDef: + term: >- + Biospecimen Portion Weight Milligram Value + source: caDSR + cde_id: 5432593 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432593&version=1.0" + +preservation_method: + common: + description: >- + Text term that represents the method used to preserve the sample. + termDef: + term: >- + Tissue Sample Preservation Method Type + source: caDSR + cde_id: 5432521 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432521&version=1.0" + +primary_diagnosis: + common: + description: >- + Text term for the structural pattern of cancer cells used to define a microscopic + diagnosis. + termDef: + term: >- + Neoplasm Histologic Type Name + source: caDSR + cde_id: 3081934 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3081934&version=3.0" + +prior_malignancy: + common: + description: >- + Text term to describe the patient's history of prior cancer diagnosis and the + spatial location of any previous cancer occurrence. + termDef: + term: >- + Prior Cancer Diagnosis Occurrence Description Text + source: caDSR + cde_id: 3382736 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3382736&version=2.0" + +prior_treatment: + common: + description: >- + A yes/no/unknown/not applicable indicator related to the administration of therapeutic + agents received before the body specimen was collected. + termDef: + term: >- + Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown + Not Applicable Indicator + source: caDSR + cde_id: 4231463 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" + +progesterone_receptor_percent_positive_ihc: + common: + description: >- + Classification to represent Progesterone Receptor Positive results expressed + as a percentage value. + termDef: + term: >- + Progesterone Receptor Level Cell Percentage Category + source: caDSR + cde_id: 3128342 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3128342&version=1.0" + +progesterone_receptor_result_ihc: + common: + description: >- + Text term to represent the overall result of Progresterone Receptor (PR) testing. + termDef: + term: >- + Breast Carcinoma Progesterone Receptor Status + source: caDSR + cde_id: 2957357 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2957357&version=2.0" + +progression_or_recurrence: + common: + description: >- + Yes/No/Unknown indicator to identify whether a patient has had a new tumor event + after initial treatment. + termDef: + term: >- + New Neoplasm Event Post Initial Therapy Indicator + source: caDSR + cde_id: 3121376 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3121376&version=1.0" + +project_id: + common: + description: >- + Unique ID for any specific defined piece of work that is undertaken or attempted + to meet a single requirement. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +qc_metric_state: + common: + description: >- + State classification given by FASTQC for the metric. Metric specific details + about the states are available on their website. + termDef: + term: >- + QC Metric State + source: FastQC + cde_id: + cde_version: + term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/" + +race: + common: + description: >- + An arbitrary classification of a taxonomic group that is a division of a species. + It usually arises as a consequence of geographical isolation within a species + and is characterized by shared heredity, physical attributes and behavior, and + in the case of humans, by common history, nationality, or geographic distribution. + The provided values are based on the categories defined by the U.S. Office of + Management and Business and used by the U.S. Census Bureau. + termDef: + term: >- + Race Category Text + source: caDSR + cde_id: 2192199 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2192199&version=1.0" + +read_length: + common: + description: >- + The length of the reads. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +read_group_name: + common: + description: >- + The name of the read group. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +relationship_age_at_diagnosis: + common: + description: >- + The age (in years) when the patient's relative was first diagnosed. + termDef: + term: >- + Relative Diagnosis Age Value + source: caDSR + cde_id: 5300571 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5300571&version=1.0" + +relationship_type: + common: + description: >- + The subgroup that describes the state of connectedness between members of the + unit of society organized around kinship ties. + termDef: + term: >- + Family Member Relationship Type + source: caDSR + cde_id: 2690165 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2690165&version=2.0" + +relative_with_cancer_history: + common: + description: >- + Indicator to signify whether or not an individual's biological relative has + been diagnosed with another type of cancer. + termDef: + term: >- + Other Cancer Biological Relative History Indicator + source: caDSR + cde_id: 3901752 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3901752&version=1.0" + +residual_disease: + common: + description: >- + Text terms to describe the status of a tissue margin following surgical resection. + termDef: + term: >- + Surgical Margin Resection Status + source: caDSR + cde_id: 2608702 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2608702&version=1.0" + +rin: + common: + description: >- + A numerical assessment of the integrity of RNA based on the entire electrophoretic + trace of the RNA sample including the presence or absence of degradation products. + termDef: + term: >- + Biospecimen RNA Integrity Number Value + source: caDSR + cde_id: 5278775 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5278775&version=1.0" + +sample_type: + common: + description: >- + Text term to describe the source of a biospecimen used for a laboratory test. + termDef: + term: >- + Specimen Type Collection Biospecimen Type + source: caDSR + cde_id: 3111302 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3111302&version=2.0" + +sample_type_id: + common: + description: >- + The accompanying sample type id for the sample type. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +section_location: + common: + description: >- + Tissue source of the slide. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +sequencing_center: + common: + description: >- + Name of the center that provided the sequence files. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +shortest_dimension: + common: + description: >- + Numeric value that represents the shortest dimension of the sample, measured + in millimeters. + termDef: + term: >- + Tissue Sample Short Dimension Millimeter Measurement + source: caDSR + cde_id: 5432603 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432603&version=1.0" + +site_of_resection_or_biopsy: + common: + description: >- + The third edition of the International Classification of Diseases for Oncology, + published in 2000, used principally in tumor and cancer registries for coding + the site (topography) and the histology (morphology) of neoplasms. The description + of an anatomical region or of a body part. Named locations of, or within, the + body. A system of numbered categories for representation of data. + termDef: + term: >- + International Classification of Diseases for Oncology, Third Edition ICD-O-3 + Site Code + source: caDSR + cde_id: 3226281 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3226281&version=1.0" + +size_selection_range: + common: + description: >- + Range of size selection. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +smoking_history: + common: + description: >- + Category describing current smoking status and smoking history as self-reported + by a patient. + termDef: + term: >- + Smoking History + source: caDSR + cde_id: 2181650 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" + +smoking_intensity: + common: + description: >- + Numeric computed value to represent lifetime tobacco exposure defined as number + of cigarettes smoked per day x number of years smoked divided by 20 + termDef: + term: >- + Person Cigarette Smoking History Pack Year Value + source: caDSR + cde_id: 2955385 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2955385&version=1.0" + +source_center: + common: + description: >- + Name of the center that provided the item. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +spectrophotometer_method: + common: + description: >- + Name of the method used to determine the concentration of purified nucleic acid + within a solution. + termDef: + term: >- + Purification Nucleic Acid Solution Concentration Determination Method Type + source: caDSR + cde_id: 3008378 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3008378&version=1.0" + +spike_ins_fasta: + common: + description: >- + Name of the FASTA file that contains the spike-in sequences. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +spike_ins_concentration: + common: + description: >- + Spike in concentration. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +state: + common: + description: >- + The current state of the object. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +target_capture_kit_name: + common: + description: >- + Name of Target Capture Kit. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +target_capture_kit_vendor: + common: + description: >- + Vendor of Target Capture Kit. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +target_capture_kit_catalog_number: + common: + description: >- + Catalog of Target Capture Kit. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +target_capture_kit_version: + common: + description: >- + Version of Target Capture Kit. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +target_capture_kit_target_region: + common: + description: >- + Target Capture Kit BED file. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +therapeutic_agents: + common: + description: >- + Text identification of the individual agent(s) used as part of a prior treatment + regimen. + termDef: + term: >- + Prior Therapy Regimen Text + source: caDSR + cde_id: 2975232 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2975232&version=1.0" + +time_between_clamping_and_freezing: + common: + description: >- + Numeric representation of the elapsed time between the surgical clamping of + blood supply and freezing of the sample, measured in minutes. + termDef: + term: >- + Tissue Sample Clamping and Freezing Elapsed Minute Time + source: caDSR + cde_id: 5432611 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432611&version=1.0" + +time_between_excision_and_freezing: + common: + description: >- + Numeric representation of the elapsed time between the excision and freezing + of the sample, measured in minutes. + termDef: + term: >- + Tissue Sample Excision and Freezing Elapsed Minute Time + source: caDSR + cde_id: 5432612 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432612&version=1.0" + +tissue_or_organ_of_origin: + common: + description: >- + Text term that describes the anatomic site of the tumor or disease. + termDef: + term: >- + Tumor Disease Anatomic Site + source: caDSR + cde_id: 3427536 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3427536&version=3.0" + +tissue_type: + common: + description: >- + Text term that represents a description of the kind of tissue collected with + respect to disease status or proximity to tumor tissue. + termDef: + term: >- + Tissue Sample Description Type + source: caDSR + cde_id: 5432687 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432687&version=1.0" + +to_trim_adapter_sequence: + common: + description: >- + Does the user suggest adapter trimming? + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +tobacco_smoking_onset_year: + common: + description: >- + The year in which the participant began smoking. + termDef: + term: >- + Started Smoking Year + source: caDSR + cde_id: 2228604 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228604&version=1.0" + +tobacco_smoking_quit_year: + common: + description: >- + The year in which the participant quit smoking. + termDef: + term: >- + Stopped Smoking Year + source: caDSR + cde_id: 2228610 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2228610&version=1.0" + +tobacco_smoking_status: + common: + description: >- + Category describing current smoking status and smoking history as self-reported + by a patient. + termDef: + term: >- + Patient Smoking History Category + source: caDSR + cde_id: 2181650 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2181650&version=1.0" + +total_sequences: + common: + description: >- + A count of the total number of sequences processed. + termDef: + term: >- + Total Sequences + source: FastQC + cde_id: + cde_version: + term_url: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/3%20Analysis%20Modules/1%20Basic%20Statistics.html" + +treatment_anatomic_site: + common: + description: >- + The anatomic site or field targeted by a treatment regimen or single agent therapy. + termDef: + term: >- + Treatment Anatomic Site + source: + cde_id: + cde_version: + term_url: + +treatment_intent_type: + common: + description: >- + Text term to identify the reason for the administration of a treatment regimen. + [Manually-curated] + termDef: + term: >- + Treatment Regimen Intent Type + source: caDSR + cde_id: 2793511 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2793511&version=1.0" + +treatment_or_therapy: + common: + description: >- + A yes/no/unknown/not applicable indicator related to the administration of therapeutic + agents received before the body specimen was collected. + termDef: + term: >- + Therapeutic Procedure Prior Specimen Collection Administered Yes No Unknown + Not Applicable Indicator + source: caDSR + cde_id: 4231463 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=4231463&version=1.0" + +treatment_outcome: + common: + description: >- + Text term that describes the patient¿s final outcome after the treatment was + administered. + termDef: + term: >- + Treatment Outcome Type + source: caDSR + cde_id: 5102383 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102383&version=1.0" + +treatment_type: + common: + description: >- + Text term that describes the kind of treatment administered. + termDef: + term: >- + Treatment Method Type + source: caDSR + cde_id: 5102381 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5102381&version=1.0" + +tumor_grade: + common: + description: >- + Numeric value to express the degree of abnormality of cancer cells, a measure + of differentiation and aggressiveness. + termDef: + term: >- + Neoplasm Histologic Grade + source: caDSR + cde_id: 2785839 + cde_version: 2.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2785839&version=2.0" + +tumor_code: + common: + description: >- + Diagnostic tumor code of the tissue sample source. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +tumor_code_id: + common: + description: >- + BCR-defined id code for the tumor sample. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +tumor_descriptor: + common: + description: >- + Text that describes the kind of disease present in the tumor specimen as related + to a specific timepoint. + termDef: + term: >- + Tumor Tissue Disease Description Type + source: caDSR + cde_id: 3288124 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3288124&version=1.0" + +tumor_stage: + common: + description: >- + The extent of a cancer in the body. Staging is usually based on the size of + the tumor, whether lymph nodes contain cancer, and whether the cancer has spread + from the original site to other parts of the body. The accepted values for tumor_stage + depend on the tumor site, type, and accepted staging system. These items should + accompany the tumor_stage value as associated metadata. + termDef: + term: >- + Tumor Stage + source: NCIt + cde_id: C16899 + cde_version: + term_url: "https://ncit.nci.nih.gov/ncitbrowser/pages/concept_details.jsf?dictionary=NCI%20Thesaurus&code=C16899" + +uuid: + common: + description: >- + A 128-bit identifier. Depending on the mechanism used to generate it, it is + either guaranteed to be different from all other UUIDs/GUIDs generated until + 3400 AD or extremely likely to be different. Its relatively small size lends + itself well to sorting, ordering, and hashing of all sorts, storing in databases, + simple allocation, and ease of programming in general. + termDef: + term: >- + Universally Unique Identifier + source: NCIt + cde_id: C54100 + cde_version: + term_url: "https://ncit.nci.nih.gov/ncitbrowser/ConceptReport.jsp?dictionary=NCI_Thesaurus&version=16.02d&ns=NCI_Thesaurus&code=C54100" + +vascular_invasion_present: + common: + description: >- + The yes/no indicator to ask if large vessel or venous invasion was detected + by surgery or presence in a tumor specimen. + termDef: + term: >- + Tumor Vascular Invasion Ind-3 + source: caDSR + cde_id: 64358 + cde_version: 3.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=64358&version=3.0" + +vital_status: + common: + description: >- + The survival state of the person registered on the protocol. + termDef: + term: >- + Patient Vital Status + source: caDSR + cde_id: 5 + cde_version: 5.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5&version=5.0" + +weight: + common: + description: >- + The weight of the patient measured in kilograms. + termDef: + term: >- + Patient Weight Measurement + source: caDSR + cde_id: 651 + cde_version: 4.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=651&version=4.0" + +well_number: + common: + description: >- + Numeric value that represents the the well location within a plate for the analyte + or aliquot from the sample. + termDef: + term: >- + Biospecimen Analyte or Aliquot Plate Well Number + source: caDSR + cde_id: 5432613 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=5432613&version=1.0" + +workflow_type: + common: + description: >- + Generic name for the workflow used to analyze a data set. + termDef: + term: + source: + cde_id: + cde_version: + term_url: + +year_of_birth: + common: + description: >- + Numeric value to represent the calendar year in which an individual was born. + termDef: + term: >- + Year Birth Date Number + source: caDSR + cde_id: 2896954 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896954&version=1.0" + +year_of_diagnosis: + common: + description: >- + Numeric value to represent the year of an individual's initial pathologic diagnosis + of cancer. + termDef: + term: >- + Year of initial pathologic diagnosis + source: caDSR + cde_id: 2896960 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2896960&version=1.0" + +year_of_death: + common: + description: >- + Numeric value to represent the year of the death of an individual. + termDef: + term: >- + Year Death Number + source: caDSR + cde_id: 2897030 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=2897030&version=1.0" + +years_smoked: + common: + description: >- + Numeric value (or unknown) to represent the number of years a person has been + smoking. + termDef: + term: >- + Person Smoking Duration Year Count + source: caDSR + cde_id: 3137957 + cde_version: 1.0 + term_url: "https://cdebrowser.nci.nih.gov/CDEBrowser/search?elementDetails=9&FirstTimer=0&PageId=ElementDetailsGroup&publicId=3137957&version=1.0" diff --git a/gdcdictionary/schemas/acknowledgement.yaml b/gdcdictionary/schemas/acknowledgement.yaml new file mode 100644 index 000000000..03a2a31f1 --- /dev/null +++ b/gdcdictionary/schemas/acknowledgement.yaml @@ -0,0 +1,77 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "acknowledgement" +title: Acknowledgement +type: object +namespace: http://gdc.nci.nih.gov +category: administrative +program: '*' +project: '*' +description: >- + Acknowledgement of an individual involved in a project. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: projects + backref: acknowledgements + label: contribute_to + target_type: project + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - projects + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - acknowledgement + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + acknowledgee: + description: >- + The indvidiual or group being acknowledged by the project. + type: string + + project_id: + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + projects: + $ref: "_definitions.yaml#/to_many_project" diff --git a/gdcdictionary/schemas/aligned_reads_index.yaml b/gdcdictionary/schemas/aligned_reads_index.yaml new file mode 100644 index 000000000..39adda687 --- /dev/null +++ b/gdcdictionary/schemas/aligned_reads_index.yaml @@ -0,0 +1,89 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "aligned_reads_index" +title: Aligned Reads Index +type: object +namespace: http://gdc.nci.nih.gov +category: index_file +program: '*' +project: '*' +description: >- + Data file containing the index for a set of aligned reads. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: submitted_aligned_reads_files + backref: aligned_reads_indexes + label: derived_from + target_type: submitted_aligned_reads + multiplicity: one_to_one + required: false + - name: core_metadata_collections + backref: aligned_reads_indexes + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - md5sum + - data_category + - data_type + - data_format + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - aligned_reads_index + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Sequencing Data + - Sequencing Reads + - Raw Sequencing Data + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Aligned Reads Index + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - BAI + + submitted_aligned_reads_files: + $ref: "_definitions.yaml#/to_one" + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/aliquot.yaml b/gdcdictionary/schemas/aliquot.yaml new file mode 100644 index 000000000..7ebecea81 --- /dev/null +++ b/gdcdictionary/schemas/aliquot.yaml @@ -0,0 +1,120 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "aliquot" +title: Aliquot +type: object +namespace: null +category: biospecimen +program: '*' +project: '*' +description: >- + Pertaining to a portion of the whole; any one of two or more samples of something, + of the same volume or weight. +additionalProperties: false +submittable: true +validators: '[]' + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: samples + backref: aliquots + label: derived_from + target_type: sample + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - samples + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + description: >- + The legacy barcode used before prior to the use UUIDs. For TCGA this is bcraliquotbarcode. + oneOf: + - type: string + - type: "null" + + aliquot_quantity: + $ref: + - "_terms.yaml#/aliquot_quantity/common" + type: number + + aliquot_volume: + $ref: + - "_terms.yaml#/aliquot_volume/common" + type: number + + amount: + $ref: + - "_terms.yaml#/amount/common" + type: number + + analyte_type: + $ref: + - "_terms.yaml#/analyte_type/common" + type: string + + analyte_type_id: + $ref: + - "_terms.yaml#/analyte_type_id/common" + enum: + - D + - E + - G + - H + - R + - S + - T + - W + - X + - Y + + concentration: + $ref: + - "_terms.yaml#/concentration/common" + type: number + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + source_center: + $ref: + - "_terms.yaml#/source_center/common" + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + samples: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/case.yaml b/gdcdictionary/schemas/case.yaml new file mode 100644 index 000000000..928063027 --- /dev/null +++ b/gdcdictionary/schemas/case.yaml @@ -0,0 +1,88 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "case" +title: Case +type: object +namespace: http://gdc.nci.nih.gov +category: administrative +program: '*' +project: '*' +description: >- + The collection of all data related to a specific subject in the context of a specific + experiment. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - name: experiments + backref: cases + label: member_of + target_type: experiment + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + - experiments + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + consent_codes: + type: array + items: + type: string + + primary_site: + description: >- + Primary site for the case. + type: string + + disease_type: + description: >- + Name of the disease for the case. + type: string + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + experiments: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/clinical_test.yaml b/gdcdictionary/schemas/clinical_test.yaml new file mode 100644 index 000000000..49d28cf9f --- /dev/null +++ b/gdcdictionary/schemas/clinical_test.yaml @@ -0,0 +1,253 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "clinical_test" +title: Clinical Test +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Metadata concerning any clinical tests used in relation to a case diagnosis. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - name: cases + backref: clinical_tests + label: performed_for + target_type: case + multiplicity: many_to_one + required: true + - name: diagnoses + backref: clinical_tests + label: relates_to + target_type: diagnosis + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - biomarker_name + - biomarker_result + - biomarker_test_method + - cases + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - clinical_test + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + biomarker_name: + $ref: + - "_terms.yaml#/biomarker_name/common" + type: string + + biomarker_result: + $ref: + - "_terms.yaml#/biomarker_result/common" + enum: + - Amplification + - Gain + - Loss + - Normal + - Other + - Translocation + - Not Reported + - Not Allowed To Collect + - Pending + + biomarker_test_method: + $ref: + - "_terms.yaml#/biomarker_test_method/common" + enum: + - Cytogenetics + - FISH + - IHC + - Karyotype + - NGS + - Nuclear Staining + - Other + - RT-PCR + - Southern + - Not Reported + - Not Allowed To Collect + - Pending + + cea_level_preoperative: + $ref: + - "_terms.yaml#/cea_level_preoperative/common" + type: number + + dlco_ref_predictive_percent: + $ref: + - "_terms.yaml#/dlco_ref_predictive_percent/common" + type: number + + estrogen_receptor_percent_positive_ihc: + $ref: + - "_terms.yaml#/estrogen_receptor_percent_positive_ihc/common" + enum: + - <1% + - 1-10% + - 11-20% + - 21-30% + - 31-40% + - 41-50% + - 51-60% + - 61-70% + - 71-80% + - 81-90% + - 91-100% + + estrogen_receptor_result_ihc: + $ref: + - "_terms.yaml#/estrogen_receptor_result_ihc/common" + enum: + - Negative + - Not Performed + - Positive + - Unknown + + fev1_ref_post_bronch_percent: + $ref: + - "_terms.yaml#/fev1_ref_post_bronch_percent/common" + type: number + + fev1_ref_pre_bronch_percent: + $ref: + - "_terms.yaml#/fev1_ref_pre_bronch_percent/common" + type: number + + fev1_fvc_post_bronch_percent: + $ref: + - "_terms.yaml#/fev1_fvc_post_bronch_percent/common" + type: number + + fev1_fvc_pre_bronch_percent: + $ref: + - "_terms.yaml#/fev1_fvc_pre_bronch_percent/common" + type: number + + her2_erbb2_percent_positive_ihc: + $ref: + - "_terms.yaml#/her2_erbb2_percent_positive_ihc/common" + enum: + - <1% + - 1-10% + - 11-20% + - 21-30% + - 31-40% + - 41-50% + - 51-60% + - 61-70% + - 71-80% + - 81-90% + - 91-100% + + her2_erbb2_result_fish: + $ref: + - "_terms.yaml#/her2_erbb2_result_fish/common" + enum: + - Negative + - Not Performed + - Positive + - Unknown + + her2_erbb2_result_ihc: + $ref: + - "_terms.yaml#/her2_erbb2_result_ihc/common" + enum: + - Negative + - Not Performed + - Positive + - Unknown + + ldh_level_at_diagnosis: + $ref: + - "_terms.yaml#/ldh_level_at_diagnosis/common" + type: number + + ldh_normal_range_upper: + $ref: + - "_terms.yaml#/ldh_normal_range_upper/common" + type: number + + microsatellite_instability_abnormal: + $ref: + - "_terms.yaml#/microsatellite_instability_abnormal/common" + enum: + - "Yes" + - "No" + - Unknown + + progesterone_receptor_percent_positive_ihc: + $ref: + - "_terms.yaml#/progesterone_receptor_percent_positive_ihc/common" + enum: + - <1% + - 1-10% + - 11-20% + - 21-30% + - 31-40% + - 41-50% + - 51-60% + - 61-70% + - 71-80% + - 81-90% + - 91-100% + + progesterone_receptor_result_ihc: + $ref: + - "_terms.yaml#/progesterone_receptor_result_ihc/common" + enum: + - Negative + - Not Performed + - Positive + - Unknown + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" + + diagnoses: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/core_metadata_collection.yaml b/gdcdictionary/schemas/core_metadata_collection.yaml new file mode 100644 index 000000000..a185faae6 --- /dev/null +++ b/gdcdictionary/schemas/core_metadata_collection.yaml @@ -0,0 +1,145 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "core_metadata_collection" +title: Core Metadata Collection +type: object +namespace: https://dcp.bionimbus.org/ +category: administrative +program: '*' +project: '*' +description: >- + Structured description of a collection of several dataset +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: projects + backref: core_metadata_collections + label: data_from + target_type: project + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + - projects + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/ubiquitous_properties" + + contributor: + description: >- + An entity responsible for making contributions to the resource. Examples of + a Contributor include a person, an organization, or a service. Typically, the + name of a Contributor should be used to indicate the entity. + type: string + + coverage: + description: >- + The spatial or temporal topic of the resource, the spatial applicability of + the resource, or the jurisdiction under which the resource is relevant. Spatial + topic and spatial applicability may be a named place or a location specified + by its geographic coordinates. Temporal topic may be a named period, date, or + date range. A jurisdiction may be a named administrative entity or a geographic + place to which the resource applies. Recommended best practice is to use a controlled + vocabulary such as the Thesaurus of Geographic Names [TGN] (http://www.getty.edu/research/tools/vocabulary/tgn/index.html). + Where appropriate, named places or time periods can be used in preference to + numeric identifiers such as sets of coordinates or date ranges. + type: string + + creator: + description: >- + An entity primarily responsible for making the resource. Examples of a Creator + include a person, an organization, or a service. Typically, the name of a Creator + should be used to indicate the entity. + type: string + + date: + $ref: + - "_definitions.yaml#/datetime" + + description: + description: >- + An account of the resource. Description may include but is not limited to: an + abstract, a table of contents, a graphical representation, or a free-text account + of the resource. + type: string + + format: + description: >- + The file format, physical medium, or dimensions of the resource. Examples of + dimensions include size and duration. Recommended best practice is to use a + controlled vocabulary such as the list of Internet Media Types [MIME] (http://www.iana.org/assignments/media-types/). + type: string + + language: + description: >- + A language of the resource. Recommended best practice is to use a controlled + vocabulary such as RFC 4646 (http://www.ietf.org/rfc/rfc4646.txt). + type: string + + publisher: + description: >- + An entity responsible for making the resource available. Examples of a Publisher + include a person, an organization, or a service. Typically, the name of a Publisher + should be used to indicate the entity. + type: string + + relation: + description: >- + A related resource. Recommended best practice is to identify the related resource + by means of a string conforming to a formal identification system. + type: string + + rights: + description: >- + Information about rights held in and over the resource. Typically, rights information + includes a statement about various property rights associated with the resource, + including intellectual property rights. + type: string + + source: + description: >- + A related resource from which the described resource is derived. The described + resource may be derived from the related resource in whole or in part. Recommended + best practice is to identify the related resource by means of a string conforming + to a formal identification system. + type: string + + subject: + description: >- + The topic of the resource. Typically, the subject will be represented using + keywords, key phrases, or classification codes. Recommended best practice is + to use a controlled vocabulary. + type: string + + title: + description: >- + A name given to the resource. Typically, a Title will be a name by which the + resource is formally known. + type: string + + data_type: + description: >- + The nature or genre of the resource. Recommended best practice is to use a controlled + vocabulary such as the DCMI Type Vocabulary [DCMITYPE]. To describe the file + format, physical medium, or dimensions of the resource, use the Format element. + type: string + + projects: + $ref: "_definitions.yaml#/to_one_project" diff --git a/gdcdictionary/schemas/demographic.yaml b/gdcdictionary/schemas/demographic.yaml new file mode 100644 index 000000000..7bd1b1af9 --- /dev/null +++ b/gdcdictionary/schemas/demographic.yaml @@ -0,0 +1,119 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "demographic" +title: Demographic +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Data for the characterization of the patient by means of segementing the population + (e.g., characterization by age, sex, or race). +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: cases + backref: demographics + label: describes + target_type: case + multiplicity: one_to_one + required: true + +required: + - submitter_id + - type + - cases + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + gender: + $ref: + - "_terms.yaml#/gender/common" + enum: + - female + - male + - unknown + - unspecified + - not reported + + race: + $ref: + - "_terms.yaml#/race/common" + enum: + - white + - american indian or alaska native + - black or african american + - asian + - native hawaiian or other pacific islander + - other + - Unknown + - not reported + - not allowed to collect + + ethnicity: + $ref: + - "_terms.yaml#/ethnicity/common" + enum: + - hispanic or latino + - not hispanic or latino + - Unknown + - not reported + - not allowed to collect + + year_of_birth: + $ref: + - "_terms.yaml#/year_of_birth/common" + oneOf: + - type: number + - type: "null" + + year_of_death: + $ref: + - "_terms.yaml#/year_of_death/common" + type: number + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/diagnosis.yaml b/gdcdictionary/schemas/diagnosis.yaml new file mode 100644 index 000000000..28ae602a5 --- /dev/null +++ b/gdcdictionary/schemas/diagnosis.yaml @@ -0,0 +1,848 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "diagnosis" +title: Diagnosis +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Data from the investigation, analysis and recognition of the presence and nature + of disease, condition, or injury from expressed signs and symptoms; also, the scientific + determination of any kind; the concise results of such an investigation. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: cases + backref: diagnoses + label: describes + target_type: case + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + - age_at_diagnosis + - days_to_last_follow_up + - vital_status + - primary_diagnosis + - morphology + - tissue_or_organ_of_origin + - site_of_resection_or_biopsy + - classification_of_tumor + - tumor_stage + - tumor_grade + - progression_or_recurrence + - days_to_recurrence + - days_to_last_known_disease_status + - last_known_disease_status + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + age_at_diagnosis: + $ref: + - "_terms.yaml#/age_at_diagnosis/common" + oneOf: + - type: number + maximum: 32872 + minimum: 0 + - type: "null" + + ajcc_clinical_m: + $ref: + - "_terms.yaml#/ajcc_clinical_m/common" + enum: + - M0 + - M1 + - M1a + - M1b + - M1c + - MX + - cM0 (i+) + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_clinical_n: + $ref: + - "_terms.yaml#/ajcc_clinical_n/common" + enum: + - N0 + - N0 (i+) + - N0 (i-) + - N0 (mol+) + - N0 (mol-) + - N1 + - N1a + - N1b + - N1bI + - N1bII + - N1bIII + - N1bIV + - N1c + - N1mi + - N2 + - N2a + - N2b + - N2c + - N3 + - N3a + - N3b + - N3c + - N4 + - NX + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_clinical_stage: + $ref: + - "_terms.yaml#/ajcc_clinical_stage/common" + enum: + - Stage 0 + - Stage 0a + - Stage 0is + - Stage I + - Stage IA + - Stage IA1 + - Stage IA2 + - Stage IB + - Stage IB Cervix + - Stage IB1 + - Stage IB2 + - Stage II + - Stage II Cervix + - Stage IIA + - Stage IIA Cervix + - Stage IIB + - Stage IIC + - Stage III + - Stage IIIA + - Stage IIIB + - Stage IIIC + - Stage IS + - Stage IV + - Stage IVA + - Stage IVB + - Stage IVC + - Stage Tis + - Stage X + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_clinical_t: + $ref: + - "_terms.yaml#/ajcc_clinical_t/common" + enum: + - T0 + - T1 + - T1a + - T1a1 + - T1a2 + - T1b + - T1b1 + - T1b2 + - T1c + - T1mi + - T2 + - T2a + - T2a1 + - T2a2 + - T2b + - T2c + - T2d + - T3 + - T3a + - T3b + - T3c + - T3d + - T4 + - T4a + - T4b + - T4c + - T4d + - T4e + - TX + - Ta + - Tis + - Tis (DCIS) + - Tis (LCIS) + - Tis (Paget's) + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_pathologic_m: + $ref: + - "_terms.yaml#/ajcc_pathologic_m/common" + enum: + - M0 + - M1 + - M1a + - M1b + - M1c + - M2 + - MX + - cM0 (i+) + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_pathologic_n: + $ref: + - "_terms.yaml#/ajcc_pathologic_n/common" + enum: + - N0 + - N0 (i+) + - N0 (i-) + - N0 (mol+) + - N0 (mol-) + - N1 + - N1a + - N1b + - N1bI + - N1bII + - N1bIII + - N1bIV + - N1c + - N1mi + - N2 + - N2a + - N2b + - N2c + - N3 + - N3a + - N3b + - N3c + - N4 + - NX + - Unknown + - Not Reported + - Not Allowed To Collect + + ajcc_pathologic_stage: + $ref: + - "_terms.yaml#/ajcc_pathologic_stage/common" + enum: + - Stage 0 + - Stage 0a + - Stage 0is + - Stage I + - Stage IA + - Stage IA1 + - Stage IA2 + - Stage IB + - Stage IB1 + - Stage IB2 + - Stage IC + - Stage II + - Stage IIA + - Stage IIA1 + - Stage IIA2 + - Stage IIB + - Stage IIC + - Stage III + - Stage IIIA + - Stage IIIB + - Stage IIIC + - Stage IV + - Stage IVA + - Stage IVB + - Stage IVC + - Stage Tis + - Stage X + + ajcc_pathologic_t: + $ref: + - "_terms.yaml#/ajcc_pathologic_t/common" + enum: + - T0 + - T1 + - T1a + - T1a1 + - T1a2 + - T1b + - T1b1 + - T1b2 + - T1c + - T1mi + - T2 + - T2a + - T2a1 + - T2a2 + - T2b + - T2c + - T2d + - T3 + - T3a + - T3b + - T3c + - T3d + - T4 + - T4a + - T4b + - T4c + - T4d + - T4e + - TX + - Ta + - Tis + - Tis (DCIS) + - Tis (LCIS) + - Tis (Paget's) + - Unknown + - Not Reported + - Not Allowed To Collect + + ann_arbor_b_symptoms: + $ref: + - "_terms.yaml#/ann_arbor_b_symptoms/common" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + - Not Allowed To Collect + + ann_arbor_clinical_stage: + $ref: + - "_terms.yaml#/ann_arbor_clinical_stage/common" + enum: + - Stage I + - Stage II + - Stage III + - Stage IV + + ann_arbor_extranodal_involvement: + $ref: + - "_terms.yaml#/ann_arbor_extranodal_involvement/common" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + - Not Allowed To Collect + + ann_arbor_pathologic_stage: + $ref: + - "_terms.yaml#/ann_arbor_pathologic_stage/common" + enum: + - Stage I + - Stage II + - Stage III + - Stage IV + + burkitt_lymphoma_clinical_variant: + $ref: + - "_terms.yaml#/burkitt_lymphoma_clinical_variant/common" + enum: + - Endemic + - Immunodeficiency-associated, adult + - Immunodeficiency-associated, pediatric + - Sporadic, adult + - Sporadic, pediatric + - Unknown + - Not Reported + - Not Allowed To Collect + + cause_of_death: + $ref: + - "_terms.yaml#/cause_of_death/common" + enum: + - Cancer Related + - Not Cancer Related + - Unknown + + circumferential_resection_margin: + $ref: + - "_terms.yaml#/circumferential_resection_margin/common" + type: number + + classification_of_tumor: + $ref: + - "_terms.yaml#/classification_of_tumor/common" + enum: + - primary + - metastasis + - recurrence + - other + - Unknown + - not reported + - Not Allowed To Collect + + colon_polyps_history: + $ref: + - "_terms.yaml#/colon_polyps_history/common" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + - Not Allowed To Collect + + days_to_birth: + $ref: + - "_terms.yaml#/days_to_birth/common" + oneOf: + - type: number + maximum: 0 + minimum: -32872 + - type: "null" + + days_to_death: + $ref: + - "_terms.yaml#/days_to_death/common" + type: number + maximum: 32872 + minimum: 0 + + days_to_hiv_diagnosis: + $ref: + - "_terms.yaml#/days_to_hiv_diagnosis/common" + oneOf: + - type: number + - type: "null" + + days_to_last_follow_up: + $ref: + - "_terms.yaml#/days_to_last_follow_up/common" + oneOf: + - type: number + - type: "null" + + days_to_last_known_disease_status: + $ref: + - "_terms.yaml#/days_to_last_known_disease_status/common" + oneOf: + - type: number + - type: "null" + + days_to_new_event: + $ref: + - "_terms.yaml#/days_to_new_event/common" + oneOf: + - type: number + - type: "null" + + days_to_recurrence: + $ref: + - "_terms.yaml#/days_to_recurrence/common" + oneOf: + - type: number + - type: "null" + + figo_stage: + $ref: + - "_terms.yaml#/figo_stage/common" + enum: + - Stage 0 + - Stage I + - Stage IA + - Stage IA1 + - Stage IA2 + - Stage IB + - Stage IB1 + - Stage IB2 + - Stage IC + - Stage II + - Stage IIA + - Stage IIA1 + - Stage IIA2 + - Stage IIB + - Stage III + - Stage IIIA + - Stage IIIB + - Stage IIIC + - Stage IIIC1 + - Stage IIIC2 + - Stage IV + - Stage IVA + - Stage IVB + - Unknown + - Not Reported + - Not Allowed To Collect + + hiv_positive: + $ref: + - "_terms.yaml#/hiv_positive/common" + enum: + - "Yes" + - "No" + - Unknown + + hpv_positive_type: + $ref: + - "_terms.yaml#/hpv_positive_type/common" + enum: + - HPV 16 + - HPV 18 + - Other HPV type(s) + - Unknown + + hpv_status: + $ref: + - "_terms.yaml#/hpv_status/common" + enum: + - Negative + - Positive + - Unknown + + last_known_disease_status: + $ref: + - "_terms.yaml#/last_known_disease_status/common" + enum: + - Distant met recurrence/progression + - Loco-regional recurrence/progression + - Biochemical evidence of disease without structural correlate + - Tumor free + - Unknown tumor status + - With tumor + - not reported + - Not Allowed To Collect + + laterality: + $ref: + - "_terms.yaml#/laterality/common" + enum: + - Bilateral + - Left + - Right + - Unknown + + ldh_level_at_diagnosis: + $ref: + - "_terms.yaml#/ldh_level_at_diagnosis/common" + oneOf: + - type: number + - type: "null" + + ldh_normal_range_upper: + $ref: + - "_terms.yaml#/ldh_normal_range_upper/common" + oneOf: + - type: number + - type: "null" + + lymph_nodes_positive: + $ref: + - "_terms.yaml#/lymph_nodes_positive/common" + type: integer + + lymphatic_invasion_present: + $ref: + - "_terms.yaml#/lymphatic_invasion_present/common" + enum: + - "Yes" + - "No" + - Unknown + + method_of_diagnosis: + $ref: + - "_terms.yaml#/method_of_diagnosis/common" + enum: + - Autopsy + - Biopsy + - Blood Draw + - Bone Marrow Aspirate + - Core Biopsy + - Cytology + - Debulking + - Diagnostic Imaging + - Excisional Biopsy + - Fine Needle Aspiration + - Incisional Biopsy + - Laparoscopy + - Laparotomy + - Other + - Surgical Resection + - Ultrasound Guided Biopsy + - Unknown + - Not Reported + - Not Allowed To Collect + + morphology: + $ref: + - "_terms.yaml#/morphology/common" + type: string + + new_event_anatomic_site: + $ref: + - "_terms.yaml#/new_event_anatomic_site/common" + enum: + - Abdomen + - Adrenal + - Anus + - Appendix + - Ascites/Peritoneum + - Axillary lymph nodes + - Bladder + - Bone + - Bone Marrow + - Brain + - Breast + - Cervical lymph nodes + - Cervix + - Colon + - Conjunctiva + - Contralateral Pleura + - Distant Metastasis + - Epididymis + - Epidural + - Epitrochlear lymph nodes + - Esophagus + - Extremities + - Femoral lymph nodes + - Gallbladder + - Gastrointestinal/Abdominal + - Head & Neck + - Heart + - Hilar lymph nodes + - Hypopharynx + - Iliac Lymph Node + - Iliac-common lymph nodes + - Iliac-external lymph nodes + - Inguinal lymph nodes + - Intraocular + - Ipsilateral Chest Cavity + - Ipsilateral Chest Wall + - Ipsilateral Lymph Nodes + - Ipsilateral Pleura + - Kidney + - Large Intestine + - Larynx + - Leptomeninges + - Liver + - Lung + - Lymph Node Only + - Lymph Node(s) + - Mandible + - Maxilla + - Mediastinal Soft Tissue + - Mediastinal lymph nodes + - Mediastinal/Intra-thoracic + - Mesenteric lymph nodes + - Nasal Soft Tissue + - Nasopharynx + - No Known Extranodal Involvement + - Non-regional / Distant Lymph Nodes + - Not Applicable + - Occipital lymph nodes + - Oral Cavity + - Oropharynx + - Other + - Other Extranodal Site + - Other, specify + - Ovary + - Pancreas + - Paraaortic lymph nodes + - Parotid Gland + - Parotid lymph nodes + - Pelvis + - Peri-orbital Soft Tissue + - Pericardium + - Perihilar Lymph Node + - Peripheral Blood + - Peritoneal Surfaces + - Pleura/Pleural Effusion + - Popliteal lymph nodes + - Prostate + - Pulmonary + - Rectum + - Renal Pelvis + - Retroperitoneal lymph nodes + - Retroperitoneum + - Salivary Gland + - Sinus + - Skin + - Small Intestine + - Soft Tissue + - Splenic lymph nodes + - Stomach + - Submandibular lymph nodes + - Supraclavicular lymph nodes + - Testes + - Thyroid + - Trunk + - Tumor Bed + - Ureter + - Urethra + - Uterus + - Vulva + - Unknown + - Not Reported + - Not Allowed To Collect + + new_event_type: + $ref: + - "_terms.yaml#/new_event_type/common" + enum: + - Biochemical Evidence of Disease + - Both Locoregional and Distant Metastasis + - Distant Metastasis + - Extrahepatic Recurrence + - Intrahepatic Recurrence + - Intrapleural Progression + - Locoregional (Urothelial tumor event) + - Locoregional Disease + - Locoregional Recurrence + - Metachronous Testicular Tumor + - Metastatic + - New Primary Tumor + - New primary Melanoma + - No New Tumor Event + - Not Applicable + - Progression of Disease + - Recurrence + - Regional Lymph Node + - Unknown + - Not Reported + - Not Allowed To Collect + + perineural_invasion_present: + $ref: + - "_terms.yaml#/perineural_invasion_present/common" + enum: + - "Yes" + - "No" + - Unknown + + primary_diagnosis: + $ref: + - "_terms.yaml#/primary_diagnosis/common" + type: string + + prior_malignancy: + $ref: + - "_terms.yaml#/prior_malignancy/common" + enum: + - "yes" + - "no" + - unknown + - not reported + - Not Allowed To Collect + + prior_treatment: + $ref: + - "_terms.yaml#/prior_treatment/common" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + - Not Allowed To Collect + + progression_or_recurrence: + $ref: + - "_terms.yaml#/progression_or_recurrence/common" + enum: + - "yes" + - "no" + - unknown + - not reported + - Not Allowed To Collect + + residual_disease: + $ref: + - "_terms.yaml#/residual_disease/common" + enum: + - R0 + - R1 + - R2 + - RX + + site_of_resection_or_biopsy: + $ref: + - "_terms.yaml#/site_of_resection_or_biopsy/common" + type: string + + tissue_or_organ_of_origin: + $ref: + - "_terms.yaml#/tissue_or_organ_of_origin/common" + type: string + + tumor_grade: + $ref: + - "_terms.yaml#/tumor_grade/common" + type: string + + tumor_stage: + $ref: + - "_terms.yaml#/tumor_stage/common" + type: string + + vascular_invasion_present: + $ref: + - "_terms.yaml#/vascular_invasion_present/common" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + - Not Allowed To Collect + + vital_status: + $ref: + - "_terms.yaml#/vital_status/common" + enum: + - alive + - dead + - lost to follow-up + - unknown + - not reported + - Not Allowed To Collect + - pending + + year_of_diagnosis: + $ref: + - "_terms.yaml#/year_of_diagnosis/common" + oneOf: + - type: number + - type: "null" + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/experiment.yaml b/gdcdictionary/schemas/experiment.yaml new file mode 100644 index 000000000..fa3038004 --- /dev/null +++ b/gdcdictionary/schemas/experiment.yaml @@ -0,0 +1,142 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "experiment" +title: Experiment +type: object +namespace: http://bloodprofilingatlas.org/bpa/ +category: administrative +program: '*' +project: '*' +description: >- + A coordinated set of actions and observations designed to generate data, with the + ultimate goal of discovery or hypothesis testing. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - name: projects + backref: experiments + label: performed_for + target_type: project + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + - projects + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - experiment + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + number_experimental_group: + description: >- + The number denoting this experiment's place within the group within the whole. + type: integer + + number_samples_per_experimental_group: + description: >- + The number of samples contained within this experimental group. + type: integer + + experimental_description: + description: >- + A brief description of the experiment being performed. + type: string + + experimental_intent: + description: >- + Summary of the goals the experiment is designed to discover. + type: string + + associated_experiment: + description: >- + The submitter_id for any experiment with which this experiment is associated, + paired, or matched. + type: string + + type_of_sample: + description: >- + String indicator identifying the types of samples as contrived or clinical. + type: string + + type_of_specimen: + description: >- + Broad description of the specimens used in the experiment. + type: string + + marker_panel_description: + description: >- + Brief description of the marker panel used in this experiment. + type: string + + somatic_mutations_identified: + description: >- + Are somatic mutations identified for this experiment? + type: boolean + + indels_identified: + description: >- + Are indels identified in this experiment? + type: boolean + + copy_numbers_identified: + description: >- + Are copy number variations identified in this experiment? + type: boolean + + type_of_data: + description: >- + Is the data raw or processed? + enum: + - Raw + - Processed + + data_description: + description: >- + Brief description of the data being provided for this experiment. + type: string + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + projects: + $ref: "_definitions.yaml#/to_one_project" diff --git a/gdcdictionary/schemas/experimental_metadata.yaml b/gdcdictionary/schemas/experimental_metadata.yaml new file mode 100644 index 000000000..c38577663 --- /dev/null +++ b/gdcdictionary/schemas/experimental_metadata.yaml @@ -0,0 +1,85 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "experimental_metadata" +title: Experimental Metadata +type: object +namespace: http://gdc.nci.nih.gov +category: metadata_file +program: '*' +project: '*' +description: >- + Data file containing the metadata for the experiment performed. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: core_metadata_collections + backref: experiment_metadata_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - name: experiments + backref: experiment_metadata_files + label: derived_from + target_type: experiment + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - md5sum + - data_category + - data_type + - data_format + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - experimental_metadata + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + type: string + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Experimental Metadata + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + type: string + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" + + experiments: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/exposure.yaml b/gdcdictionary/schemas/exposure.yaml new file mode 100644 index 000000000..0b170024a --- /dev/null +++ b/gdcdictionary/schemas/exposure.yaml @@ -0,0 +1,137 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "exposure" +title: Exposure +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Clinically relevant patient information not immediately resulting from genetic predispositions. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: cases + backref: exposures + label: describes + target_type: case + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - exposure + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + alcohol_history: + $ref: + - "_terms.yaml#/alcohol_history/common" + type: string + + alcohol_intensity: + $ref: + - "_terms.yaml#/alcohol_intensity/common" + type: string + + bmi: + $ref: + - "_terms.yaml#/bmi/common" + type: number + + cigarettes_per_day: + $ref: + - "_terms.yaml#/cigarettes_per_day/common" + type: number + + height: + $ref: + - "_terms.yaml#/height/common" + type: number + + pack_years_smoked: + $ref: + - "_terms.yaml#/pack_years_smoked/common" + type: number + + tobacco_smoking_onset_year: + $ref: + - "_terms.yaml#/tobacco_smoking_onset_year/common" + type: integer + + tobacco_smoking_quit_year: + $ref: + - "_terms.yaml#/tobacco_smoking_quit_year/common" + type: integer + + tobacco_smoking_status: + $ref: + - "_terms.yaml#/tobacco_smoking_status/common" + enum: + - "1" + - "2" + - "3" + - "4" + - "5" + - "6" + - "7" + - Unknown + - Not Reported + - Not Allowed To Collect + + weight: + $ref: + - "_terms.yaml#/weight/common" + type: number + + years_smoked: + $ref: + - "_terms.yaml#/years_smoked/common" + type: number + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/family_history.yaml b/gdcdictionary/schemas/family_history.yaml new file mode 100644 index 000000000..67523f4af --- /dev/null +++ b/gdcdictionary/schemas/family_history.yaml @@ -0,0 +1,106 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "family_history" +title: Family History +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Record of a patient's background regarding cancer events of blood relatives. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: cases + backref: family_histories + label: describes + target_type: case + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - family_history + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + relative_with_cancer_history: + $ref: + - "_terms.yaml#/relative_with_cancer_history/common" + enum: + - "yes" + - "no" + - unknown + - not reported + + relationship_type: + $ref: + - "_terms.yaml#/relationship_type/common" + type: string + + relationship_gender: + $ref: + - "_terms.yaml#/gender/common" + enum: + - female + - male + - unknown + - unspecified + - not reported + + relationship_age_at_diagnosis: + $ref: + - "_terms.yaml#/relationship_age_at_diagnosis/common" + type: number + + relationship_primary_diagnosis: + $ref: + - "_terms.yaml#/primary_diagnosis/common" + type: string + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/keyword.yaml b/gdcdictionary/schemas/keyword.yaml new file mode 100644 index 000000000..866a35670 --- /dev/null +++ b/gdcdictionary/schemas/keyword.yaml @@ -0,0 +1,77 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "keyword" +title: Keyword +type: object +namespace: http://gdc.nci.nih.gov +category: administrative +program: '*' +project: '*' +description: >- + A keyword for a project. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: projects + backref: keywords + label: describe + target_type: project + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - projects + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - keyword + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + keyword_name: + description: >- + The name of the keyword. + type: string + + project_id: + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + projects: + $ref: "_definitions.yaml#/to_many_project" diff --git a/gdcdictionary/schemas/program.yaml b/gdcdictionary/schemas/program.yaml new file mode 100644 index 000000000..5fc9adf7c --- /dev/null +++ b/gdcdictionary/schemas/program.yaml @@ -0,0 +1,47 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "program" +title: Program +type: object +namespace: null +category: administrative +program: '*' +project: '*' +description: >- + A broad framework of goals to be achieved. (NCIt C52647) +additionalProperties: false +submittable: false +validators: null + +systemProperties: + - id + +links: [] + +required: + - name + - dbgap_accession_number + +uniqueKeys: + - [id] + - [name] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + name: + description: >- + Full name/title of the program. + type: string + + dbgap_accession_number: + description: >- + The dbgap accession number provided for the program. + type: string diff --git a/gdcdictionary/schemas/project.yaml b/gdcdictionary/schemas/project.yaml new file mode 100644 index 000000000..d3ed0be4b --- /dev/null +++ b/gdcdictionary/schemas/project.yaml @@ -0,0 +1,139 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "project" +title: Project +type: object +namespace: null +category: administrative +program: '*' +project: '*' +description: >- + Any specifically defined piece of work that is undertaken or attempted to meet a + single requirement. (NCIt C47885) +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - state + - released + - releasable + - intended_release_date + +links: + - name: programs + backref: projects + label: member_of + target_type: program + multiplicity: many_to_one + required: true + +required: + - code + - name + - dbgap_accession_number + - programs + +uniqueKeys: + - [id] + - [code] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + description: >- + UUID for the project. + systemAlias: node_id + + name: + description: >- + Display name/brief description for the project. + type: string + + code: + description: >- + Unique identifier for the project. + type: string + + investigator_name: + description: >- + Name of the principal investigator for the project. + type: string + + investigator_affiliation: + description: >- + The investigator's affiliation with respect to a research institution. + type: string + + date_collected: + description: >- + The date or date range in which the project data was collected. + type: string + + availability_type: + description: >- + Is the project open or restricted? + enum: + - Open + - Restricted + + availability_mechanism: + description: >- + Mechanism by which the project will be made avilable. + type: string + + support_source: + description: >- + The name of source providing support/grant resources. + type: string + + support_id: + description: >- + The ID of the source providing support/grant resources. + type: string + + state: + description: >- + The possible states a project can be in. All but `open` are equivalent to some + type of locked state. + default: open + enum: + - open + - review + - submitted + - processing + - closed + - legacy + + released: + description: >- + To release a project is to tell the GDC to include all submitted entities in + the next GDC index. + type: boolean + default: false + + releasable: + description: >- + A project can only be released by the user when `releasable` is true. + type: boolean + default: false + + intended_release_date: + description: >- + Tracks a Project's intended release date. + type: string + format: date-time + + dbgap_accession_number: + description: >- + The dbgap accession number provided for the project. + type: string + + programs: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/projects/project1.yaml b/gdcdictionary/schemas/projects/project1.yaml new file mode 100644 index 000000000..c5d141abe --- /dev/null +++ b/gdcdictionary/schemas/projects/project1.yaml @@ -0,0 +1,21 @@ +##################################################################### +# Project 1 specific overrides +##################################################################### + +$schema: "http://json-schema.org/draft-04/schema#" + +##################################################################### +# Aliquot +##################################################################### + +id: "aliquot" +program: 'program1' +project: 'project1' +required: + - submitter_aliquot_id + - parents + - project_1_specific_thing + +properties: + project_1_specific_thing: +type: string diff --git a/gdcdictionary/schemas/publication.yaml b/gdcdictionary/schemas/publication.yaml new file mode 100644 index 000000000..1b14878a8 --- /dev/null +++ b/gdcdictionary/schemas/publication.yaml @@ -0,0 +1,78 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "publication" +title: Publication +type: object +namespace: http://gdc.nci.nih.gov +category: administrative +program: '*' +project: '*' +description: >- + Publication for a project. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: projects + backref: publications + label: refers_to + target_type: project + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - projects + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - publication + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + pmid: + type: string + + doi: + type: string + + project_id: + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + projects: + $ref: "_definitions.yaml#/to_many_project" diff --git a/gdcdictionary/schemas/read_group.yaml b/gdcdictionary/schemas/read_group.yaml new file mode 100644 index 000000000..cf43c20f1 --- /dev/null +++ b/gdcdictionary/schemas/read_group.yaml @@ -0,0 +1,276 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "read_group" +title: Read Group +type: object +namespace: http://gdc.nci.nih.gov +category: biospecimen +program: '*' +project: '*' +description: >- + Sequencing reads from one lane of an NGS experiment. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - name: aliquots + backref: read_groups + label: derived_from + target_type: aliquot + multiplicity: many_to_one + required: true + +required: + - type + - submitter_id + - aliquots + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + id: + $ref: + - "_definitions.yaml#/uuid" + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + submitter_id: + type: string + + state: + $ref: + - "_definitions.yaml#/state" + + type: + enum: + - read_group + + experiment_name: + $ref: + - "_terms.yaml#/experiment_name/common" + type: string + + sequencing_center: + $ref: + - "_terms.yaml#/sequencing_center/common" + type: string + + sequencing_date: + $ref: + - "_definitions.yaml#/datetime" + + platform: + $ref: + - "_terms.yaml#/platform/common" + enum: + - Illumina + - SOLiD + - LS454 + - Ion Torrent + - Complete Genomics + - PacBio + - Other + + instrument_model: + $ref: + - "_terms.yaml#/instrument_model/common" + enum: + - 454 GS FLX Titanium + - AB SOLiD 4 + - AB SOLiD 2 + - AB SOLiD 3 + - Complete Genomics + - Illumina HiSeq X Ten + - Illumina HiSeq X Five + - Illumina Genome Analyzer II + - Illumina Genome Analyzer IIx + - Illumina HiSeq 2000 + - Illumina HiSeq 2500 + - Illumina HiSeq 4000 + - Illumina MiSeq + - Illumina NextSeq + - Ion Torrent PGM + - Ion Torrent Proton + - PacBio RS + - Ion S5 XL System, Ion 530 Chip + - Other + + library_strategy: + $ref: + - "_terms.yaml#/library_strategy/common" + enum: + - WGS + - WXS + - RNA-Seq + - ChIP-Seq + - miRNA-Seq + - Bisulfite-Seq + - Validation + - Amplicon + - Other + + rin: + $ref: + - "_terms.yaml#/rin/common" + type: number + + flow_cell_barcode: + $ref: + - "_terms.yaml#/flow_cell_barcode/common" + type: string + + includes_spike_ins: + $ref: + - "_terms.yaml#/includes_spike_ins/common" + type: boolean + + spike_ins_fasta: + $ref: + - "_terms.yaml#/spike_ins_fasta/common" + type: string + + spike_ins_concentration: + $ref: + - "_terms.yaml#/spike_ins_concentration/common" + type: string + + library_selection: + $ref: + - "_terms.yaml#/library_selection/common" + enum: + - Hybrid_Selection + - PCR + - Affinity_Enrichment + - Poly-T_Enrichment + - RNA_Depletion + - Other + + library_preparation_kit_name: + $ref: + - "_terms.yaml#/library_preparation_kit_name/common" + type: string + + library_preparation_kit_vendor: + $ref: + - "_terms.yaml#/library_preparation_kit_vendor/common" + type: string + + library_preparation_kit_catalog_number: + $ref: + - "_terms.yaml#/library_preparation_kit_catalog_number/common" + type: string + + library_preparation_kit_version: + $ref: + - "_terms.yaml#/library_preparation_kit_version/common" + type: string + + library_name: + $ref: + - "_terms.yaml#/library_name/common" + type: string + + target_capture_kit_name: + $ref: + - "_terms.yaml#/target_capture_kit_name/common" + type: string + + target_capture_kit_vendor: + $ref: + - "_terms.yaml#/target_capture_kit_vendor/common" + type: string + + target_capture_kit_catalog_number: + $ref: + - "_terms.yaml#/target_capture_kit_catalog_number/common" + type: string + + target_capture_kit_version: + $ref: + - "_terms.yaml#/target_capture_kit_version/common" + type: string + + target_capture_kit_target_region: + $ref: + - "_terms.yaml#/target_capture_kit_target_region/common" + type: string + + size_selection_range: + $ref: + - "_terms.yaml#/size_selection_range/common" + type: string + + adapter_name: + $ref: + - "_terms.yaml#/adapter_name/common" + type: string + + adapter_sequence: + $ref: + - "_terms.yaml#/adapter_sequence/common" + type: string + + to_trim_adapter_sequence: + $ref: + - "_terms.yaml#/to_trim_adapter_sequence/common" + type: boolean + + library_strand: + $ref: + - "_terms.yaml#/library_strand/common" + enum: + - Unstranded + - First_Stranded + - Second_Stranded + + base_caller_name: + $ref: + - "_terms.yaml#/base_caller_name/common" + type: string + + base_caller_version: + $ref: + - "_terms.yaml#/base_caller_version/common" + type: string + + is_paired_end: + $ref: + - "_terms.yaml#/is_paired_end/common" + type: boolean + + read_length: + type: integer + + read_group_name: + description: >- + Read Group Name + type: string + + barcoding_applied: + description: >- + True/False: was barcoding applied? + type: boolean + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + aliquots: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/read_group_qc.yaml b/gdcdictionary/schemas/read_group_qc.yaml new file mode 100644 index 000000000..f79ea75e2 --- /dev/null +++ b/gdcdictionary/schemas/read_group_qc.yaml @@ -0,0 +1,175 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "read_group_qc" +title: Read Group QC +type: object +namespace: http://gdc.nci.nih.gov +category: notation +program: '*' +project: '*' +description: >- + GDC QC run metadata. +additionalProperties: false +submittable: false +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - exclusive: true + required: true + subgroup: + - name: submitted_aligned_reads_files + backref: read_group_qcs + label: data_from + target_type: submitted_aligned_reads + multiplicity: one_to_one + required: false + - name: submitted_unaligned_reads_files + backref: read_group_qcs + label: data_from + target_type: submitted_unaligned_reads + multiplicity: one_to_many + required: false + - name: read_groups + backref: read_group_qcs + label: generated_from + target_type: read_group + multiplicity: many_to_one + required: true + +required: + - submitter_id + - workflow_link + - type + - percent_gc_content + - encoding + - total_sequences + - basic_statistics + - per_base_sequence_quality + - per_tile_sequence_quality + - per_sequence_quality_score + - per_base_sequence_content + - per_sequence_gc_content + - per_base_n_content + - sequence_length_distribution + - sequence_duplication_levels + - overrepresented_sequences + - adapter_content + - kmer_content + - read_groups + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/workflow_properties" + + type: + enum: + - read_group_qc + + workflow_type: + $ref: + - "_terms.yaml#/workflow_type/common" + enum: + - Read Group Quality Control + + fastq_name: + $ref: + - "_terms.yaml#/file_name/common" + type: string + + percent_aligned: + description: >- + The percent of reads with at least one reported alignment. + type: integer + maximum: 100 + minimum: 0 + + percent_gc_content: + $ref: + - "_terms.yaml#/percent_gc_content/common" + type: integer + maximum: 100 + minimum: 0 + + encoding: + $ref: + - "_terms.yaml#/encoding/common" + type: string + + total_aligned_reads: + description: >- + The total number of reads with at least one reported alignment. + type: integer + + total_sequences: + $ref: + - "_terms.yaml#/total_sequences/common" + type: integer + + basic_statistics: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_base_sequence_quality: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_tile_sequence_quality: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_sequence_quality_score: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_base_sequence_content: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_sequence_gc_content: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + per_base_n_content: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + sequence_length_distribution: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + sequence_duplication_levels: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + overrepresented_sequences: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + adapter_content: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + kmer_content: + $ref: + - "_definitions.yaml#/qc_metrics_state" + + submitted_aligned_reads_files: + $ref: "_definitions.yaml#/to_one" + + submitted_unaligned_reads_files: + $ref: "_definitions.yaml#/to_many" + + read_groups: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/sample.yaml b/gdcdictionary/schemas/sample.yaml new file mode 100644 index 000000000..3a5d4527e --- /dev/null +++ b/gdcdictionary/schemas/sample.yaml @@ -0,0 +1,723 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "sample" +title: Sample +type: object +namespace: http://gdc.nci.nih.gov +category: biospecimen +program: '*' +project: '*' +description: >- + Any material sample taken from a biological entity for testing, diagnostic, propagation, + treatment or research purposes, including a sample obtained from a living organism + or taken from the biological object after halting of all its life functions. Biospecimen + can contain one or more components including but not limited to cellular molecules, + cells, tissues, organs, body fluids, embryos, and body excretory products. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: cases + backref: samples + label: derived_from + target_type: case + multiplicity: many_to_one + required: true + - name: diagnoses + backref: samples + label: related_to + target_type: diagnosis + multiplicity: many_to_one + required: false + +required: + - submitter_id + - type + - cases + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + description: >- + The legacy barcode used before prior to the use UUIDs, varies by project. For + TCGA this is bcrsamplebarcode. + oneOf: + - type: string + - type: "null" + + biospecimen_anatomic_site: + $ref: + - "_terms.yaml#/biospecimen_anatomic_site/common" + enum: + - Abdomen + - Abdominal Wall + - Acetabulum + - Adenoid + - Adipose + - Adrenal + - Alveolar Ridge + - Amniotic Fluid + - Ampulla Of Vater + - Anal Sphincter + - Ankle + - Anorectum + - Antecubital Fossa + - Antrum + - Anus + - Aorta + - Aortic Body + - Appendix + - Aqueous Fluid + - Arm + - Artery + - Ascending Colon + - Ascending Colon Hepatic Flexure + - Auditory Canal + - Autonomic Nervous System + - Axilla + - Back + - Bile Duct + - Bladder + - Blood + - Blood Vessel + - Bone + - Bone Marrow + - Bowel + - Brain + - Brain Stem + - Breast + - Broad Ligament + - Bronchiole + - Bronchus + - Brow + - Buccal Cavity + - Buccal Mucosa + - Buttock + - Calf + - Capillary + - Cardia + - Carina + - Carotid Artery + - Carotid Body + - Cartilage + - Cecum + - Cell-Line + - Central Nervous System + - Cerebellum + - Cerebral Cortex + - Cerebrospinal Fluid + - Cerebrum + - Cervical Spine + - Cervix + - Chest + - Chest Wall + - Chin + - Clavicle + - Clitoris + - Colon + - Colon - Mucosa Only + - Common Duct + - Conjunctiva + - Connective Tissue + - Dermal + - Descending Colon + - Diaphragm + - Duodenum + - Ear + - Ear Canal + - Ear, Pinna (External) + - Effusion + - Elbow + - Endocrine Gland + - Epididymis + - Epidural Space + - Esophagogastric Junction + - Esophagus + - Esophagus - Mucosa Only + - Eye + - Fallopian Tube + - Femoral Artery + - Femoral Vein + - Femur + - Fibroblasts + - Fibula + - Finger + - Floor Of Mouth + - Fluid + - Foot + - Forearm + - Forehead + - Foreskin + - Frontal Cortex + - Frontal Lobe + - Fundus Of Stomach + - Gallbladder + - Ganglia + - Gastroesophageal Junction + - Gastrointestinal Tract + - Groin + - Gum + - Hand + - Hard Palate + - Head & Neck + - Head - Face Or Neck, Nos + - Heart + - Hepatic + - Hepatic Duct + - Hepatic Vein + - Hip + - Hippocampus + - Humerus + - Hypopharynx + - Ileum + - Ilium + - Index Finger + - Ischium + - Islet Cells + - Jaw + - Jejunum + - Joint + - Kidney + - Knee + - Lacrimal Gland + - Large Bowel + - Laryngopharynx + - Larynx + - Leg + - Leptomeninges + - Ligament + - Lip + - Liver + - Lumbar Spine + - Lung + - Lymph Node + - Lymph Node(s) Axilla + - Lymph Node(s) Cervical + - Lymph Node(s) Distant + - Lymph Node(s) Epitrochlear + - Lymph Node(s) Femoral + - Lymph Node(s) Hilar + - Lymph Node(s) Iliac-Common + - Lymph Node(s) Iliac-External + - Lymph Node(s) Inguinal + - Lymph Node(s) Internal Mammary + - Lymph Node(s) Mammary + - Lymph Node(s) Mesenteric + - Lymph Node(s) Occipital + - Lymph Node(s) Paraaortic + - Lymph Node(s) Parotid + - Lymph Node(s) Pelvic + - Lymph Node(s) Popliteal + - Lymph Node(s) Regional + - Lymph Node(s) Retroperitoneal + - Lymph Node(s) Scalene + - Lymph Node(s) Splenic + - Lymph Node(s) Subclavicular + - Lymph Node(s) Submandibular + - Lymph Node(s) Supraclavicular + - Lymph Nodes(s) Mediastinal + - Mandible + - Maxilla + - Mediastinal Soft Tissue + - Mediastinum + - Mesentery + - Mesothelium + - Middle Finger + - Mitochondria + - Muscle + - Nails + - Nasal Cavity + - Nasal Soft Tissue + - Nasopharynx + - Neck + - Nerve + - Nerve(s) Cranial + - Occipital Cortex + - Ocular Orbits + - Omentum + - Oral Cavity + - Oral Cavity - Mucosa Only + - Oropharynx + - Other + - Ovary + - Palate + - Pancreas + - Paraspinal Ganglion + - Parathyroid + - Parotid Gland + - Patella + - Pelvis + - Penis + - Pericardium + - Periorbital Soft Tissue + - Peritoneal Cavity + - Peritoneum + - Pharynx + - Pineal + - Pineal Gland + - Pituitary Gland + - Placenta + - Pleura + - Popliteal Fossa + - Prostate + - Pylorus + - Rectosigmoid Junction + - Rectum + - Retina + - Retro-Orbital Region + - Retroperitoneum + - Rib + - Ring Finger + - Round Ligament + - Sacrum + - Salivary Gland + - Scalp + - Scapula + - Sciatic Nerve + - Scrotum + - Seminal Vesicle + - Shoulder + - Sigmoid Colon + - Sinus + - Sinus(es), Maxillary + - Skeletal Muscle + - Skin + - Skull + - Small Bowel + - Small Bowel - Mucosa Only + - Small Finger + - Soft Tissue + - Spinal Column + - Spinal Cord + - Spleen + - Splenic Flexure + - Sternum + - Stomach + - Stomach - Mucosa Only + - Subcutaneous Tissue + - Synovium + - Temporal Cortex + - Tendon + - Testis + - Thigh + - Thoracic Spine + - Thorax + - Throat + - Thumb + - Thymus + - Thyroid + - Tibia + - Tongue + - Tonsil + - Tonsil (Pharyngeal) + - Trachea / Major Bronchi + - Transverse Colon + - Trunk + - Umbilical Cord + - Ureter + - Urethra + - Urinary Tract + - Uterus + - Uvula + - Vagina + - Vas Deferens + - Vein + - Venous + - Vertebra + - Vulva + - White Blood Cells + - Wrist + - Unknown + - Not Reported + - Not Allowed To Collect + + composition: + $ref: + - "_terms.yaml#/composition/common" + enum: + - Buccal Cells + - Buffy Coat + - Bone Marrow Components + - Bone Marrow Components NOS + - Control Analyte + - Cell + - Circulating Tumor Cell (CTC) + - Derived Cell Line + - EBV Immortalized + - Fibroblasts from Bone Marrow Normal + - Granulocytes + - Human Original Cells + - Lymphocytes + - Mononuclear Cells from Bone Marrow Normal + - Peripheral Blood Components NOS + - Peripheral Blood Nucleated Cells + - Pleural Effusion + - Plasma + - Peripheral Whole Blood + - Serum + - Saliva + - Sputum + - Solid Tissue + - Whole Bone Marrow + - Unknown + - Not Reported + - Not Allowed To Collect + + current_weight: + $ref: + - "_terms.yaml#/current_weight/common" + type: number + + days_to_collection: + $ref: + - "_terms.yaml#/days_to_collection/common" + type: integer + + days_to_sample_procurement: + $ref: + - "_terms.yaml#/days_to_sample_procurement/common" + type: integer + + diagnosis_pathologically_confirmed: + enum: + - "Yes" + - "No" + - Unknown + + freezing_method: + $ref: + - "_terms.yaml#/freezing_method/common" + type: string + + initial_weight: + $ref: + - "_terms.yaml#/initial_weight/common" + type: number + + intermediate_dimension: + $ref: + - "_terms.yaml#/intermediate_dimension/common" + type: string + + is_ffpe: + $ref: + - "_terms.yaml#/is_ffpe/common" + type: boolean + + longest_dimension: + $ref: + - "_terms.yaml#/longest_dimension/common" + type: string + + method_of_sample_procurement: + $ref: + - "_terms.yaml#/method_of_sample_procurement/common" + enum: + - Abdomino-perineal Resection of Rectum + - Anterior Resection of Rectum + - Aspirate + - Biopsy + - Blood Draw + - Bone Marrow Aspirate + - Core Biopsy + - Cystectomy + - Endo Rectal Tumor Resection + - Endoscopic Biopsy + - Endoscopic Mucosal Resection (EMR) + - Enucleation + - Excisional Biopsy + - Fine Needle Aspiration + - Full Hysterectomy + - Gross Total Resection + - Hand Assisted Laparoscopic Radical Nephrectomy + - Hysterectomy NOS + - Incisional Biopsy + - Indeterminant + - Laparoscopic Biopsy + - Laparoscopic Partial Nephrectomy + - Laparoscopic Radical Nephrectomy + - Laparoscopic Radical Prostatectomy with Robotics + - Laparoscopic Radical Prostatectomy without Robotics + - Left Hemicolectomy + - Lobectomy + - Local Resection (Exoresection; wall resection) + - Lumpectomy + - Modified Radical Mastectomy + - Needle Biopsy + - Open Craniotomy + - Open Partial Nephrectomy + - Open Radical Nephrectomy + - Open Radical Prostatectomy + - Orchiectomy + - Other + - Other Surgical Resection + - Pan-Procto Colectomy + - Pneumonectomy + - Right Hemicolectomy + - Sigmoid Colectomy + - Simple Mastectomy + - Subtotal Resection + - Surgical Resection + - Thoracoscopic Biopsy + - Total Colectomy + - Total Mastectomy + - Transplant + - Transurethral resection (TURBT) + - Transverse Colectomy + - Tumor Resection + - Wedge Resection + - Unknown + - Not Reported + - Not Allowed To Collect + + oct_embedded: + $ref: + - "_terms.yaml#/oct_embedded/common" + type: string + + preservation_method: + $ref: + - "_terms.yaml#/preservation_method/common" + enum: + - Cryopreserved + - FFPE + - Fresh + - OCT + - Snap Frozen + - Frozen + - Unknown + - Not Reported + - Not Allowed To Collect + + sample_type: + description: >- + Characterization of the sample as either clinical or contrived. + enum: + - Additional Metastatic + - Additional - New Primary + - Blood Derived Cancer - Bone Marrow, Post-treatment + - Blood Derived Cancer - Peripheral Blood, Post-treatment + - Blood Derived Normal + - Bone Marrow Normal + - Buccal Cell Normal + - Cell Line Derived Xenograft Tissue + - Cell Lines + - cfDNA + - Circulating Tumor Cell (CTC) + - Control Analyte + - Clinical + - Contrived + - ctDNA + - DNA + - EBV Immortalized Normal + - FFPE Recurrent + - FFPE Scrolls + - Fibroblasts from Bone Marrow Normal + - GenomePlex (Rubicon) Amplified DNA + - Granulocytes + - Human Tumor Original Cells + - Metastatic + - Mononuclear Cells from Bone Marrow Normal + - Primary Blood Derived Cancer - Peripheral Blood + - Recurrent Blood Derived Cancer - Peripheral Blood + - Pleural Effusion + - Primary Blood Derived Cancer - Bone Marrow + - Primary Tumor + - Primary Xenograft Tissue + - Post neo-adjuvant therapy + - Recurrent Blood Derived Cancer - Bone Marrow + - Recurrent Tumor + - Repli-G (Qiagen) DNA + - Repli-G X (Qiagen) DNA + - RNA + - Slides + - Solid Tissue Normal + - Total RNA + - Xenograft Tissue + - Unknown + - Not Reported + - Not Allowed To Collect + + sample_type_id: + $ref: + - "_terms.yaml#/sample_type_id/common" + enum: + - "01" + - "02" + - "03" + - "04" + - "05" + - "06" + - "07" + - "08" + - "09" + - "10" + - "11" + - "12" + - "13" + - "14" + - "15" + - "16" + - "20" + - "40" + - "41" + - "42" + - "50" + - "60" + - "61" + - "99" + + sample_volume: + description: >- + The volume of the sample in mL. + type: number + + shortest_dimension: + $ref: + - "_terms.yaml#/shortest_dimension/common" + type: string + + time_between_clamping_and_freezing: + $ref: + - "_terms.yaml#/time_between_clamping_and_freezing/common" + type: string + + time_between_excision_and_freezing: + $ref: + - "_terms.yaml#/time_between_excision_and_freezing/common" + type: string + + tissue_type: + $ref: + - "_terms.yaml#/tissue_type/common" + enum: + - Tumor + - Normal + - Abnormal + - Peritumoral + - Contrived + - Unknown + - Not Reported + - Not Allowed To Collect + + tumor_code: + $ref: + - "_terms.yaml#/tumor_code/common" + enum: + - Non cancerous tissue + - Diffuse Large B-Cell Lymphoma (DLBCL) + - Lung Cancer (all types) + - Lung Adenocarcinoma + - Non-small Cell Lung Carcinoma (NSCLC) + - Colon Cancer (all types) + - Breast Cancer (all types) + - Cervical Cancer (all types) + - Anal Cancer (all types) + - Acute lymphoblastic leukemia (ALL) + - Acute myeloid leukemia (AML) + - Induction Failure AML (AML-IF) + - Neuroblastoma (NBL) + - Osteosarcoma (OS) + - Ewing sarcoma + - Wilms tumor (WT) + - Clear cell sarcoma of the kidney (CCSK) + - Rhabdoid tumor (kidney) (RT) + - CNS, ependymoma + - CNS, glioblastoma (GBM) + - CNS, rhabdoid tumor + - CNS, low grade glioma (LGG) + - CNS, medulloblastoma + - CNS, other + - NHL, anaplastic large cell lymphoma + - NHL, Burkitt lymphoma (BL) + - Rhabdomyosarcoma + - Soft tissue sarcoma, non-rhabdomyosarcoma + - Castration-Resistant Prostate Cancer (CRPC) + - Prostate Cancer + - Hepatocellular Carcinoma (HCC) + + tumor_code_id: + $ref: + - "_terms.yaml#/tumor_code_id/common" + enum: + - "00" + - "01" + - "02" + - "03" + - "04" + - "10" + - "20" + - "21" + - "30" + - "40" + - "41" + - "50" + - "51" + - "52" + - "60" + - "61" + - "62" + - "63" + - "64" + - "65" + - "70" + - "71" + - "80" + - "81" + + tumor_descriptor: + $ref: + - "_terms.yaml#/tumor_descriptor/common" + description: >- + A description of the tumor from which the sample was derived. + enum: + - Metastatic + - Not Applicable + - Primary + - Recurrence + - Xenograft + - NOS + - Unknown + - Not Reported + - Not Allowed To Collect + + project_id: + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + cases: + $ref: "_definitions.yaml#/to_one" + + diagnoses: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/slide.yaml b/gdcdictionary/schemas/slide.yaml new file mode 100644 index 000000000..49428a4ba --- /dev/null +++ b/gdcdictionary/schemas/slide.yaml @@ -0,0 +1,185 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "slide" +title: Slide +type: object +namespace: http://gdc.nci.nih.gov +category: biospecimen +program: '*' +project: '*' +description: >- + A digital image, microscopic or otherwise, of any sample, portion, or sub-part thereof. + (GDC) +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: samples + backref: slides + label: derived_from + target_type: sample + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - samples + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + type: string + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + apoptotic_concentration: + description: >- + The concentration, in cells/mL, of apoptotic cells in the slide blood. + type: number + + ctc_concentration: + description: >- + The concentration, in cells/mL, of traditional CTC cells (intact and enlarged + cell and nucleus, cytokeratin positive, and CD45 negative) in the slide blood. + type: number + + ctc_low_concentration: + description: >- + The concentration, in cells/mL, of CTC-low cells (those with low cytokeratin + levels compared to traditional CTCs) in the slide blood. + type: number + + ctc_small_concentration: + description: >- + The concentration, in cells/mL, of CTC-small cells (those with a small nuclear + and cellular size relative to traditional CTCs) in the slide blood. + type: number + + section_location: + $ref: + - "_terms.yaml#/section_location/common" + type: string + + methanol_added: + description: >- + True/False indicator for if methanol was used in the slide preparation process. + type: boolean + + number_proliferating_cells: + $ref: + - "_terms.yaml#/number_proliferating_cells/common" + type: integer + + number_nucleated_cells: + description: >- + The total number of nucleated cells identified on the slide. + type: integer + + percent_tumor_cells: + $ref: + - "_terms.yaml#/percent_tumor_cells/common" + type: number + + percent_tumor_nuclei: + $ref: + - "_terms.yaml#/percent_tumor_nuclei/common" + type: number + + percent_normal_cells: + $ref: + - "_terms.yaml#/percent_normal_cells/common" + type: number + + percent_necrosis: + $ref: + - "_terms.yaml#/percent_necrosis/common" + type: number + + percent_stromal_cells: + $ref: + - "_terms.yaml#/percent_stromal_cells/common" + type: number + + percent_inflam_infiltration: + $ref: + - "_terms.yaml#/percent_inflam_infiltration/common" + type: number + + percent_lymphocyte_infiltration: + $ref: + - "_terms.yaml#/percent_lymphocyte_infiltration/common" + type: number + + percent_monocyte_infiltration: + $ref: + - "_terms.yaml#/percent_monocyte_infiltration/common" + type: number + + percent_granulocyte_infiltration: + $ref: + - "_terms.yaml#/percent_granulocyte_infiltration/common" + type: number + + percent_neutrophil_infiltration: + $ref: + - "_terms.yaml#/percent_neutrophil_infiltration/common" + type: number + + percent_eosinophil_infiltration: + $ref: + - "_terms.yaml#/percent_eosinophil_infiltration/common" + type: number + + run_datetime: + $ref: + - "_definitions.yaml#/datetime" + + run_name: + description: >- + Name, number, or other identifier given to this slide's run. + type: string + + slide_identifier: + description: >- + Unique identifier given to the this slide. + type: string + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + samples: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/slide_count.yaml b/gdcdictionary/schemas/slide_count.yaml new file mode 100644 index 000000000..e39678323 --- /dev/null +++ b/gdcdictionary/schemas/slide_count.yaml @@ -0,0 +1,144 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "slide_count" +title: Slide Count +type: object +namespace: http://gdc.nci.nih.gov +category: notation +program: '*' +project: '*' +description: >- + Information pertaining to processed results obtained from slides; often in the form + of counts. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + +links: + - name: slides + backref: slide_counts + label: data_from + target_type: slide + multiplicity: many_to_many + required: true + +required: + - submitter_id + - type + - slides + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - slide_count + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + cell_type: + description: >- + The type of cell being counted or measured. + type: string + + cell_identifier: + description: >- + An alternative identifier for a given cell type. + type: string + + cell_count: + description: >- + Raw count of a particular cell type. + type: integer + + ck_signal: + description: >- + Numeric quantification of the CK signal. + type: number + + biomarker_signal: + description: >- + Numeric quantification of the biomarker signal. + type: number + + er_localization: + description: >- + Cellular localization of the endoplasmic reticulum as determined by staining. + enum: + - Nuclear + - Cytoplasmic + - Both + - None + - Not Determined + + frame_identifier: + description: >- + Name, number, or other identifier given to the frame of the slide from which + this image was taken. + type: string + + relative_nuclear_size: + description: >- + The ratio of the single cell's nucleus size to the average of the surrounding + cells. + type: number + + relative_nuclear_intensity: + description: >- + The ratio of the single cell's nuclear staining intensity to the average of + the surrounding cells. + type: number + + relative_cytokeratin_intensity: + description: >- + The ratio of the single cell's cytokeratin staining intensity to the average + of the surrounding cells. + type: number + + relative_er_intensity: + description: >- + The ratio of the single cell's endoplasmic reticulum staining intensity to the + average of the surrounding cells. + type: number + + run_name: + description: >- + The name or identifier given to the run that was used to generate this slide + count. + type: string + + project_id: + type: string + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + slides: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/slide_image.yaml b/gdcdictionary/schemas/slide_image.yaml new file mode 100644 index 000000000..08dacd472 --- /dev/null +++ b/gdcdictionary/schemas/slide_image.yaml @@ -0,0 +1,136 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "slide_image" +title: Slide Image +type: object +namespace: http://gdc.nci.nih.gov +category: data_file +program: '*' +project: '*' +description: >- + Data file containing image of a slide. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: slides + backref: slide_images + label: data_from + target_type: slide + multiplicity: many_to_one + required: false + - name: core_metadata_collections + backref: slide_images + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - md5sum + - data_category + - data_type + - data_format + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - slide_image + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Biospecimen + - Slide Image + - Mass Cytometry + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - image + - Single Cell Image + - Raw IMC Data + - Single Channel IMC Image + - Antibody Panel Added + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + type: string + + experimental_strategy: + description: >- + Classification of the slide type with respect to its experimental use. + enum: + - Diagnostic Slide + - Tissue Slide + + cell_type: + description: >- + The type of cell being imaged or otherwised analysed. + type: string + + cell_identifier: + description: >- + An alternative identifier for a given cell type. + type: string + + cell_count: + description: >- + Count of the cell type being imaged or otherwise analysed. + type: integer + + frame_identifier: + description: >- + Name, number, or other identifier given to the frame of the slide from which + this image was taken. + type: string + + panel_used: + description: >- + Name or other identifier given to the panel used during an IMC run. + type: string + + protocol_used: + description: >- + Name or other identifier given to the protocol used during an IMC run. + type: string + + run_name: + description: >- + Name, number, or other identifier given to the run that generated this slide + image. + type: string + + slides: + $ref: "_definitions.yaml#/to_one" + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_aligned_reads.yaml b/gdcdictionary/schemas/submitted_aligned_reads.yaml new file mode 100644 index 000000000..80494a5b1 --- /dev/null +++ b/gdcdictionary/schemas/submitted_aligned_reads.yaml @@ -0,0 +1,105 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_aligned_reads" +title: Submitted Aligned Reads +type: object +namespace: http://gdc.nci.nih.gov +category: data_file +program: '*' +project: '*' +description: >- + Data file containing aligned reads that are used as input to GDC workflows. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: read_groups + backref: submitted_aligned_reads_files + label: data_from + target_type: read_group + multiplicity: one_to_many + required: false + - name: core_metadata_collections + backref: submitted_aligned_reads_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - data_format + - md5sum + - data_category + - data_type + - experimental_strategy + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - submitted_aligned_reads + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Sequencing Data + - Sequencing Reads + - Raw Sequencing Data + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Aligned Reads + - Alignment Coordinates + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - BAM + - BED + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + enum: + - WGS + - WXS + - Low Pass WGS + - Validation + - RNA-Seq + - miRNA-Seq + - Total RNA-Seq + - DNA Panel + + read_groups: + $ref: "_definitions.yaml#/to_many" + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_copy_number.yaml b/gdcdictionary/schemas/submitted_copy_number.yaml new file mode 100644 index 000000000..982d404f6 --- /dev/null +++ b/gdcdictionary/schemas/submitted_copy_number.yaml @@ -0,0 +1,89 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_copy_number" +title: Submitted Copy Number +type: object +namespace: http://gdc.nci.nih.gov +category: data_file +program: '*' +project: '*' +description: >- + Data file containing normalized copy number information from an aliquot. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: true + required: true + subgroup: + - name: aliquots + backref: submitted_copy_number_files + label: derived_from + target_type: aliquot + multiplicity: one_to_one + required: false + - name: read_groups + backref: submitted_copy_number_files + label: derived_from + target_type: read_group + multiplicity: many_to_many + required: false + +required: + - submitter_id + - file_name + - file_size + - data_format + - md5sum + - data_category + - data_type + - experimental_strategy + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - submitted_copy_number + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + type: string + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + type: string + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + type: string + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + type: string + + aliquots: + $ref: "_definitions.yaml#/to_one" + + read_groups: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_methylation.yaml b/gdcdictionary/schemas/submitted_methylation.yaml new file mode 100644 index 000000000..4f654753f --- /dev/null +++ b/gdcdictionary/schemas/submitted_methylation.yaml @@ -0,0 +1,103 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_methylation" +title: Submitted Methylation +type: object +namespace: https://www.bloodpac.org/ +category: data_file +program: '*' +project: '*' +description: >- + DNA methylation data files contain information on raw and normalized signal intensities, + detection confidence and calculated beta values for methylated and unmethylated + probes. DNA methylation is an epigenetic mark which can be associated with transcriptional + inactivity when located in promoter regions. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: core_metadata_collections + backref: submitted_methylation_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - name: aliquots + backref: submitted_methylation_files + label: data_from + target_type: aliquot + multiplicity: many_to_one + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - md5sum + - data_category + - data_type + - data_format + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - submitted_methylation + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Methylation Data + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Methylation Intensity Values + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - IDAT + + assay_method: + enum: + - Methylation Array + + assay_instrument: + enum: + - Illumina + + assay_instrument_model: + enum: + - Illumina Infinium HumanMethylation450 + - Illumina Infinium HumanMethylation450K + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" + + aliquots: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/submitted_somatic_mutation.yaml b/gdcdictionary/schemas/submitted_somatic_mutation.yaml new file mode 100644 index 000000000..1aa8e6e73 --- /dev/null +++ b/gdcdictionary/schemas/submitted_somatic_mutation.yaml @@ -0,0 +1,96 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_somatic_mutation" +title: Submitted Somatic Mutation +type: object +namespace: http://gdc.nci.nih.gov +category: data_file +program: '*' +project: '*' +description: >- + Data file containing somatic mutation calls from a read group. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: core_metadata_collections + backref: submitted_somatic_mutations + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - name: read_groups + backref: submitted_somatic_mutations + label: derived_from + target_type: read_group + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - data_format + - md5sum + - data_category + - data_type + - experimental_strategy + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - submitted_somatic_mutation + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + type: string + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + type: string + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + type: string + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + type: string + + total_variants: + description: >- + The total number of variants detected carrying a base change difference from + the reference genome. + type: integer + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" + + read_groups: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_unaligned_reads.yaml b/gdcdictionary/schemas/submitted_unaligned_reads.yaml new file mode 100644 index 000000000..7978a54af --- /dev/null +++ b/gdcdictionary/schemas/submitted_unaligned_reads.yaml @@ -0,0 +1,104 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_unaligned_reads" +title: Submitted Unaligned Reads +type: object +namespace: http://gdc.nci.nih.gov +category: data_file +program: '*' +project: '*' +description: >- + Data file containing unaligned reads that have not been GDC Harmonized. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - state + - file_state + - error_type + +links: + - exclusive: false + required: true + subgroup: + - name: read_groups + backref: submitted_unaligned_reads_files + label: data_from + target_type: read_group + multiplicity: many_to_one + required: false + - name: core_metadata_collections + backref: submitted_unaligned_reads_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + +required: + - submitter_id + - type + - file_name + - file_size + - md5sum + - data_category + - data_type + - data_format + - experimental_strategy + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + type: + enum: + - submitted_unaligned_reads + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Sequencing Data + - Sequencing Reads + - Raw Sequencing Data + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Unaligned Reads + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - BAM + - FASTQ + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + enum: + - WGS + - WXS + - Low Pass WGS + - Validation + - RNA-Seq + - miRNA-Seq + - Total RNA-Seq + - DNA Panel + + read_groups: + $ref: "_definitions.yaml#/to_one" + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/treatment.yaml b/gdcdictionary/schemas/treatment.yaml new file mode 100644 index 000000000..2ed0925ae --- /dev/null +++ b/gdcdictionary/schemas/treatment.yaml @@ -0,0 +1,221 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "treatment" +title: Treatment +type: object +namespace: http://gdc.nci.nih.gov +category: clinical +program: '*' +project: '*' +description: >- + Record of the administration and intention of therapeutic agents provided to a patient + to alter the course of a pathologic process. +additionalProperties: false +submittable: true +validators: null + +systemProperties: + - id + - project_id + - state + - created_datetime + - updated_datetime + +links: + - name: diagnoses + backref: treatments + label: describes + target_type: diagnosis + multiplicity: many_to_one + required: true + +required: + - submitter_id + - type + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + type: + enum: + - treatment + + id: + $ref: + - "_definitions.yaml#/uuid" + systemAlias: node_id + + state: + $ref: + - "_definitions.yaml#/state" + + submitter_id: + oneOf: + - type: string + - type: "null" + + days_to_treatment: + $ref: + - "_terms.yaml#/days_to_treatment/common" + type: number + + days_to_treatment_end: + $ref: + - "_terms.yaml#/days_to_treatment_end/common" + type: number + + days_to_treatment_start: + $ref: + - "_terms.yaml#/days_to_treatment_start/common" + type: number + + therapeutic_agents: + $ref: + - "_terms.yaml#/therapeutic_agents/common" + type: string + + treatment_anatomic_site: + $ref: + - "_terms.yaml#/treatment_anatomic_site/common" + enum: + - Abdomen, total + - Arm + - Ascites + - Axillary + - Body, total + - Bone + - Bone, non-spine + - Brain, focal + - Brain, whole + - Brain-C2 + - Breast + - Cervical + - Chest Wall + - Effusion + - Epitrochlear + - Eye + - Femoral + - Gastrointestinal, Colon + - Gastrointestinal, Gallbladder + - Gastrointestinal, Intestine + - Gastrointestinal, Liver + - Gastrointestinal, NOS + - Gastrointestinal, Pancreas + - Gastrointestinal, Rectum + - Gastrointestinal, Stomach + - Genitourinary, Bladder + - Genitourinary, Kidney + - Genitourinary, NOS + - Genitourinary, Prostate + - Genitourinary, Prostate and Seminal Vesicles + - Head + - Head, Face, or Neck + - Hilar + - Iliac-common + - Iliac-external + - Inguinal + - Internal Mammary Nodes + - Leg + - Lung + - Lymph Nodes + - Lymph node, distant (specify site) + - Lymph node, locoregional (specify site) + - Mantle + - Mediastinal + - Mediastinum + - Mesenteric + - Occipital + - Other + - Paraaortic + - Parametrium + - Parotid + - Pelvis + - Popliteal + - Primary tumor site + - Prostate + - Prostate Bed + - Prostate, Seminal Vesicles and Lymph Nodes + - Rectum + - Retroperitoneal + - Sacrum + - Seminal vesicles + - Shoulder + - Skin, lower extremity, local + - Skin, total + - Skin, trunk, local + - Skin, upper extremity, local + - Spine + - Spine, whole + - Splenic + - Submandibular + - Supraclavicular + - Supraclavicular/Axillary Level 3 + - Thorax + - Trunk + - Unknown + - Not Reported + - Not Allowed To Collect + + treatment_intent_type: + $ref: + - "_terms.yaml#/treatment_intent_type/common" + type: string + + treatment_or_therapy: + $ref: + - "_terms.yaml#/treatment_or_therapy/common" + enum: + - "yes" + - "no" + - unknown + - not reported + + treatment_outcome: + $ref: + - "_terms.yaml#/treatment_outcome/common" + enum: + - Complete Response + - Partial Response + - Treatment Ongoing + - Treatment Stopped Due to Toxicity + - Unknown + + treatment_type: + $ref: + - "_terms.yaml#/treatment_type/common" + enum: + - Ablation + - Chemotherapy + - Concurrent Chemoradiation + - Cryoablation + - Embolization + - Hormone Therapy + - Internal Radiation + - Immunotherapy (Including Vaccines) + - Other + - Pharmaceutical Therapy + - Radiation Therapy + - Stem Cell Treatment + - Surgery + - Targeted Molecular Therapy + - Unknown + - Not Reported + - Not Allowed To Collect + + project_id: + $ref: + - "_definitions.yaml#/project_id" + + created_datetime: + $ref: + - "_definitions.yaml#/datetime" + + updated_datetime: + $ref: + - "_definitions.yaml#/datetime" + + diagnoses: + $ref: "_definitions.yaml#/to_one" From 9ff6275e3f916e764ce2c173fc8d1697ff143b26 Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Fri, 22 May 2020 03:04:54 -0500 Subject: [PATCH 5/7] manual changes to submitted_copy_number.yaml --- .../schemas/submitted_copy_number.yaml | 39 ++++++++++++------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/gdcdictionary/schemas/submitted_copy_number.yaml b/gdcdictionary/schemas/submitted_copy_number.yaml index 982d404f6..d3109047d 100644 --- a/gdcdictionary/schemas/submitted_copy_number.yaml +++ b/gdcdictionary/schemas/submitted_copy_number.yaml @@ -23,24 +23,34 @@ systemProperties: - error_type links: - - exclusive: true + - exclusive: false required: true subgroup: - - name: aliquots - backref: submitted_copy_number_files - label: derived_from - target_type: aliquot - multiplicity: one_to_one - required: false - - name: read_groups - backref: submitted_copy_number_files - label: derived_from - target_type: read_group - multiplicity: many_to_many - required: false + - name: core_metadata_collections + backref: submitted_copy_number_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - exclusive: true + required: false + subgroup: + - name: aliquots + backref: submitted_copy_number_files + label: derived_from + target_type: aliquot + multiplicity: one_to_one + required: false + - name: read_groups + backref: submitted_copy_number_files + label: derived_from + target_type: read_group + multiplicity: many_to_many + required: false required: - submitter_id + - type - file_name - file_size - data_format @@ -87,3 +97,6 @@ properties: read_groups: $ref: "_definitions.yaml#/to_many" + + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" From 86a72334b27291c6cd3449a4c41048d5d5a23ac3 Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Fri, 22 May 2020 03:14:18 -0500 Subject: [PATCH 6/7] fix validator in aliquot --- gdcdictionary/schemas/aliquot.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gdcdictionary/schemas/aliquot.yaml b/gdcdictionary/schemas/aliquot.yaml index 7ebecea81..f4dfcd0ee 100644 --- a/gdcdictionary/schemas/aliquot.yaml +++ b/gdcdictionary/schemas/aliquot.yaml @@ -12,7 +12,7 @@ description: >- of the same volume or weight. additionalProperties: false submittable: true -validators: '[]' +validators: null systemProperties: - id From 8d27e9102276e57c37726ffee65913f6acebf497 Mon Sep 17 00:00:00 2001 From: ganjigajanan Date: Fri, 22 May 2020 03:35:08 -0500 Subject: [PATCH 7/7] updated branch tag for dictionaryutils --- setup.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/setup.py b/setup.py index 28f6decc6..ba7ec72fb 100644 --- a/setup.py +++ b/setup.py @@ -28,6 +28,10 @@ def get_version(): 'jsonschema>=2.5.1', 'dictionaryutils', ], + dependency_links=[ + # for testing purpose + "git+https://github.com/uc-cdis/dictionaryutils.git@feat/format_upgrade#egg=dictionaryutils", + ], package_data={ "gdcdictionary": [ "schemas/*.yaml",