OpenBioML · kjappelbaum · Mar 16, 2023 · Mar 16, 2023 · Mar 16, 2023 · Mar 16, 2023
diff --git a/data/ClinTox/meta.yaml b/data/ClinTox/meta.yaml
@@ -15,7 +15,10 @@ targets:
           - http://purl.bioontology.org/ontology/MESH/Q000633
           - https://ncit.nci.nih.gov/ncitbrowser/ConceptReport.jsp?dictionary=NCI_Thesaurus&ns=ncit&code=C27990
           - https://ncit.nci.nih.gov/ncitbrowser/ConceptReport.jsp?dictionary=NCI_Thesaurus&ns=ncit&code=C27955
-split_col: split
+benchmarks:
+    - name: TDC
+      link: https://tdcommons.ai/
+      split_column: split
 identifiers:
     - id: SMILES
       type: SMILES

diff --git a/data/ClinTox/transform.py b/data/ClinTox/transform.py
@@ -57,7 +57,9 @@ def get_and_transform_data():
                 ],
             },
         ],
-        "split_col": "split",  # name of the column that contains the split information
+        "benchmarks": [
+            {"name": "TDC", "link": "https://tdcommons.ai/", "split_column": "split"}
+        ],
         "identifiers": [
             {
                 "id": "SMILES",  # column name

diff --git a/data/caco2_wang/meta.yaml b/data/caco2_wang/meta.yaml
@@ -17,7 +17,10 @@ targets:
       uris:
           - http://www.bioassayontology.org/bao#BAO_0010008
           - http://purl.obolibrary.org/obo/MI_2162
-split_col: split
+benchmarks:
+    - name: TDC
+      link: https://tdcommons.ai/
+      split_column: split
 identifiers:
     - id: SMILES
       type: SMILES

diff --git a/data/caco2_wang/transform.py b/data/caco2_wang/transform.py
@@ -70,7 +70,9 @@ def get_and_transform_data():
                 ],
             },
         ],
-        "split_col": "split",  # name of the column that contains the split information
+        "benchmarks": [
+            {"name": "TDC", "link": "https://tdcommons.ai/", "split_column": "split"}
+        ],
         "identifiers": [
             {
                 "id": "SMILES",  # column name

diff --git a/data/cav3_t-type_calcium_channels_butkiewicz/meta.yaml b/data/cav3_t-type_calcium_channels_butkiewicz/meta.yaml
@@ -1,9 +1,9 @@
 ---
 name: cav3_t-type_calcium_channels_butkiewicz
-description: This dataset was initially curated from HTS data at the PubChem database. The curation process is documented in Butkiewicz et al. Primary screening
-    with AID 449739 identified inhibitors of Cav3 T-type calcium channels. Four follow-up screens were performed to confirm inhibitory effects on smaller
-    sets of compounds involving AID 493021, AID 493022, AID 493023, and AID 493041. AID 489005 was performed as counter screen validating active compounds
-    of the primary screen.
+description: "\n        This dataset was initially curated from HTS data at the PubChem database.         The curation process is documented in Butkiewicz\
+    \ et al.         Primary screening with AID 449739 identified inhibitors of Cav3 T-type calcium channels.         Four follow-up screens were performed\
+    \ to confirm inhibitory effects on smaller sets of compounds         involving AID 493021, AID 493022, AID 493023, and AID 493041.\n        AID 489005\
+    \ was performed as counter screen validating active compounds of the primary screen.         "
 targets:
     - id: activity_cav3_t_type_calcium_channels
       description: whether it active against cav3 t-type calcium channels receptor (1) or not (0)
@@ -34,7 +34,10 @@ links:
       description: corresponding publication
     - url: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5962024/
       description: corresponding publication
-split_col: split
+benchmarks:
+    - name: TDC
+      link: https://tdcommons.ai/
+      split_column: split
 num_points: 100875
 url: https://tdcommons.ai/single_pred_tasks/hts/#butkiewicz-et-al
 bibtex:
@@ -48,7 +51,7 @@ bibtex:
                     volume = {18},
                     number = {1},
                     pages = {735--756},
-                    author = {Mariusz Butkiewicz and Edward Lowe and Ralf Mueller and Jeffrey Mendenhall and Pedro Teixeira and C. Weaver and Jens Meiler},
+                    author = {Mariusz Butkiewicz and Edward Lowe and Ralf Mueller and Jeffrey Mendenhall                 and Pedro Teixeira and C. Weaver and Jens Meiler},
                     title = {Benchmarking Ligand-Based Virtual High-Throughput Screening with the {PubChem} Database},
                     journal = {Molecules}}
     - |-
@@ -61,7 +64,7 @@ bibtex:
                     volume = {47},
                     number = {D1},
                     pages = {D1102--D1109},
-                    author = {Sunghwan Kim and Jie Chen and Tiejun Cheng and Asta Gindulyte and Jia He and Siqian He and Qingliang Li and Benjamin A Shoemaker and Paul A Thiessen and Bo Yu and Leonid Zaslavsky and Jian Zhang and Evan E Bolton},
+                    author = {Sunghwan Kim and Jie Chen and Tiejun Cheng and Asta Gindulyte and Jia He and Siqian He             and Qingliang Li and Benjamin A Shoemaker and Paul A Thiessen and Bo Yu and Leonid Zaslavsky             and Jian Zhang and Evan E Bolton},
                     title = {{PubChem} 2019 update: improved access to chemical data},
                     journal = {Nucleic Acids Research}}
     - |-
@@ -72,6 +75,6 @@ bibtex:
                     publisher = {Chem Inform},
                     volume = {3},
                     number = {1},
-                    author = {Butkiewicz, M. and Wang, Y. and Bryant, S. H. and Lowe, E. W. and Weaver, D. C. and Meiler, J.},
+                    author = {Butkiewicz, M.  and Wang, Y.  and Bryant, S. H.  and Lowe, E. W.  and Weaver, D. C.              and Meiler, J.},
                     title = {{H}igh-{T}hroughput {S}creening {A}ssay {D}atasets from the {P}ub{C}hem {D}atabase}},
                     journal = {Chemical Science}}
diff --git a/data/cav3_t-type_calcium_channels_butkiewicz/transform.py b/data/cav3_t-type_calcium_channels_butkiewicz/transform.py
@@ -83,7 +83,9 @@ def get_and_transform_data():
                 "description": "corresponding publication",
             },
         ],
-        "split_col": "split",  # name of the column that contains the split information
+        "benchmarks": [
+            {"name": "TDC", "link": "https://tdcommons.ai/", "split_column": "split"}
+        ],
         "num_points": len(df),  # number of datapoints in this dataset
         "url": "https://tdcommons.ai/single_pred_tasks/hts/#butkiewicz-et-al",
         "bibtex": [

diff --git a/data/choline_transporter_butkiewicz/meta.yaml b/data/choline_transporter_butkiewicz/meta.yaml
@@ -1,11 +1,18 @@
 ---
 name: choline_transporter_butkiewicz
-description: This dataset was originally curated from HTS data at the PubChem database. The primary screen AID 488975 identified inhibitors of CHT. The
-    counter screen AID 493221 was used as a validation screen to confirm the active compounds that inhibit CHT. AID504840 and AID588401 experiments were
-    used as additional validation experiments. The screen AID 493222 evaluated remaining active compounds for non-specific activity in parental HEK293 cells.
-    AID602208 tested a selected set of compounds for 3H choline uptake. The final set of 254 active compounds was determined by the overlap of active compounds
-    in screens AID 493221, AID504840, and AID588401 subtracting any non-specific hits from AID 49322 and all inactive compounds in the re-confirmation screen
-    AID602208.
+description: |-
+    This dataset was originally curated from HTS data at
+            the PubChem database. The primary screen AID 488975 identified
+            inhibitors of CHT. The counter screen AID 493221 was used as a
+            validation screen to confirm the active compounds that inhibit CHT.
+            AID504840 and AID588401 experiments were used as additional validation
+            experiments. The screen AID 493222 evaluated remaining active compounds
+            for non-specific activity in parental HEK293 cells. AID602208 tested a
+            selected set of compounds for 3H choline uptake. The final set of 254
+            active compounds was determined by the overlap of active compounds in
+            screens AID 493221, AID504840, and AID588401 subtracting any
+            non-specific hits from AID 49322 and all inactive compounds in the
+            re-confirmation screen AID602208.
 targets:
     - id: activity_choline_transporter
       description: inhibition of choline transporter receptor (1) or not (0).
@@ -21,7 +28,10 @@ targets:
           - 588401
           - 493222
           - 602208
-split_col: split
+benchmarks:
+    - name: TDC
+      link: https://tdcommons.ai/
+      split_column: split
 identifiers:
     - id: SMILES
       type: SMILES
@@ -47,8 +57,11 @@ bibtex:
                     volume = {18},
                     number = {1},
                     pages = {735--756},
-                    author = {Mariusz Butkiewicz and Edward Lowe and Ralf Mueller and Jeffrey Mendenhall and Pedro Teixeira and C. Weaver and Jens Meiler},
-                    title = {Benchmarking Ligand-Based Virtual High-Throughput Screening with the {PubChem} Database},
+                    author = {Mariusz Butkiewicz and Edward Lowe and Ralf Mueller and
+                    Jeffrey Mendenhall and Pedro Teixeira and C. Weaver and Jens
+                    Meiler},
+                    title = {Benchmarking Ligand-Based Virtual High-Throughput
+                    Screening with the {PubChem} Database},
                     journal = {Molecules}}
     - |-
       @article{Kim2018,
@@ -60,7 +73,10 @@ bibtex:
                     volume = {47},
                     number = {D1},
                     pages = {D1102--D1109},
-                    author = {Sunghwan Kim and Jie Chen and Tiejun Cheng and Asta Gindulyte and Jia He and Siqian He and Qingliang Li and Benjamin A Shoemaker and Paul A Thiessen and Bo Yu and Leonid Zaslavsky and Jian Zhang and Evan E Bolton},
+                    author = {Sunghwan Kim and Jie Chen and Tiejun Cheng and
+                    Asta Gindulyte and Jia He and Siqian He and Qingliang Li and
+                    Benjamin A Shoemaker and Paul A Thiessen and Bo Yu and Leonid
+                    Zaslavsky and Jian Zhang and Evan E Bolton},
                     title = {{PubChem} 2019 update: improved access to chemical data},
                     journal = {Nucleic Acids Research}}
     - |-
@@ -71,6 +87,8 @@ bibtex:
                     publisher = {Chem Inform},
                     volume = {3},
                     number = {1},
-                    author = {Butkiewicz, M. and Wang, Y. and Bryant, S. H. and Lowe, E. W. and Weaver, D. C. and Meiler, J.},
-                    title = {{H}igh-{T}hroughput {S}creening {A}ssay {D}atasets from the {P}ub{C}hem {D}atabase}},
+                    author = {Butkiewicz, M. and Wang, Y. and Bryant, S. H. and Lowe,
+                    E. W. and Weaver, D. C. and Meiler, J.},
+                    title = {{H}igh-{T}hroughput {S}creening {A}ssay {D}atasets from
+                    the {P}ub{C}hem {D}atabase}},
                     journal = {Chemical Science}}
diff --git a/data/choline_transporter_butkiewicz/transform.py b/data/choline_transporter_butkiewicz/transform.py
@@ -67,7 +67,9 @@ def get_and_transform_data():
                 "pubchem_aids": [488975, 493221, 504840, 588401, 493222, 602208],
             },
         ],
-        "split_col": "split",
+        "benchmarks": [
+            {"name": "TDC", "link": "https://tdcommons.ai/", "split_column": "split"}
+        ],
         "identifiers": [
             {
                 "id": "SMILES",  # column name