Dev dx

BWA/0.7.17/BWASW.nf

@@ -6,13 +6,13 @@ process BWASW {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    tuple sample_id, rg_id, file("${fastq[0].simpleName}.sam")
+        tuple(sample_id, rg_id, path("${fastq[0].simpleName}.sam"), emit: sam_file)
 
     script:
-    """
-    bwa bwasw -t ${task.cpus} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
-    """
+        """
+        bwa bwasw -t ${task.cpus} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
+        """
 }

BWA/0.7.17/MEM.nf

@@ -6,16 +6,16 @@ process MEM {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    tuple sample_id, rg_id, file("${fastq[0].simpleName}.sam")
+        tuple(sample_id, rg_id, path("${fastq[0].simpleName}.sam"), emit: sam_file)
 
     script:
-    def barcode = rg_id.split('_')[1]
-    def readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
+        def barcode = rg_id.split('_')[1]
+        def readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
 
-    """
-    bwa mem -t ${task.cpus} -R ${readgroup} ${params.optional} ${params.genome} ${fastq}  > ${fastq[0].simpleName}.sam
-    """
+        """
+        bwa mem -t ${task.cpus} -R ${readgroup} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
+        """
 }

ControlFREEC/11.5/AssessSignificance.nf

@@ -0,0 +1,18 @@
+process AssessSignificance {
+    tag {"Control Freec AssessSignificance ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_AssessSignificance'
+    container = 'quay.io/biocontainers/control-freec:11.5--he1b5a44_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(ratio_file), path(cnv_file))
+
+    output:
+        tuple(sample_id, path("${cnv_file.name}.p.value.txt"), emit: cnv_pvalue)
+
+    script:
+        """
+        cat /usr/local/bin/assess_significance.R | R --slave --args ${cnv_file} ${ratio_file}
+        """
+}

ControlFREEC/11.5/Freec.nf

@@ -0,0 +1,34 @@
+process Freec {
+    tag {"Control Freec ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_Freec'
+    container = 'quay.io/biocontainers/control-freec:11.5--he1b5a44_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file))
+
+    output:
+        tuple(sample_id, path("${bam_file.name}_ratio.txt"), path("${bam_file.name}_CNVs"), emit: cnv)
+        tuple(sample_id, path("${bam_file.name}_sample.cpn"), path("${bam_file.name}_ratio.BedGraph"), path("${bam_file.name}_info.txt"), emit: other)
+
+    script:
+        def config = "${sample_id}.config"
+        """
+        touch ${config}
+        echo "[general]" >> ${config}
+        echo "chrLenFile = ${params.chr_len_file}" >> ${config}
+        echo "chrFiles = ${params.chr_files}" >> ${config}
+        echo "gemMappabilityFile = ${params.gem_mappability_file}" >> ${config}
+        echo "ploidy = ${params.ploidy}" >> ${config}
+        echo "window = ${params.window}" >> ${config}
+        echo "BedGraphOutput=TRUE" >> ${config}
+        echo "maxThreads=${task.cpus}" >> ${config}
+
+        echo "[sample]" >> ${config}
+        echo "inputFormat = BAM" >> ${config}
+        echo "mateFile = ${bam_file}" >> ${config}
+
+        freec -conf ${config}
+        """
+}

ControlFREEC/11.5/MakeGraph.nf

@@ -0,0 +1,18 @@
+process MakeGraph {
+    tag {"Control Freec MakeGraph ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_MakeGraph'
+    container = 'quay.io/biocontainers/control-freec:11.5--he1b5a44_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(ratio_file), path(cnv_file))
+
+    output:
+        tuple(sample_id, path("${ratio_file.name}.png"), path("${ratio_file.name}.log2.png"), emit: ratio_png)
+
+    script:
+        """
+        cat /usr/local/bin/makeGraph.R | R --slave --args ${params.ploidy} ${ratio_file}
+        """
+}

FastQC/0.11.8/FastQC.nf

@@ -5,13 +5,13 @@ process FastQC {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    file "*_fastqc.{zip,html}"
+        path("*_fastqc.{zip,html}", emit: report)
 
     script:
-    """
-    fastqc ${params.optional} -t ${task.cpus} ${fastq}
-    """
+        """
+        fastqc ${params.optional} -t ${task.cpus} ${fastq}
+        """
 }

GATK/3.8-1-0-gf15c1c3ef/BaseRecalibrator.nf

@@ -0,0 +1,32 @@
+process BaseRecalibrator {
+    tag {"GATK BaseRecalibrator ${sample_id} - ${chr}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_BaseRecalibrator'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file), chr)
+
+    output:
+        tuple(sample_id, path("${bam_file.baseName}.bqsr.${chr}.bam"), path("${bam_file.baseName}.bqsr.${chr}.bai"), emit: bam_file)
+
+    script:
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar $params.gatk_path -T BaseRecalibrator \
+        --num_cpu_threads_per_data_thread ${task.cpus} \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --intervals ${chr} \
+        --out ${bam_file.baseName}.bqsr.${chr}.table \
+        ${params.optional}
+
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T PrintReads \
+        --num_cpu_threads_per_data_thread ${task.cpus} \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --BQSR ${bam_file.baseName}.bqsr.${chr}.table \
+        --intervals ${chr} \
+        --out ${bam_file.baseName}.bqsr.${chr}.bam
+        """
+}

GATK/3.8-1-0-gf15c1c3ef/CatVariants.nf

@@ -0,0 +1,19 @@
+process CatVariantsGVCF {
+    tag {"GATK CatVariantsGVCF ${sample_id}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_CatVariantsGVCF'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(gvcf_files), path(gvcf_idx_files))
+
+    output:
+        tuple(sample_id, path("${sample_id}.g.vcf.gz"), path("${sample_id}.g.vcf.gz.tbi"), emit:vcf_file)
+
+    script:
+        def input_files = gvcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -cp ${params.gatk_path} org.broadinstitute.gatk.tools.CatVariants --reference ${params.genome} -V ${input_files} --outputFile ${sample_id}.g.vcf.gz ${params.optional}
+        """
+}

GATK/3.8-1-0-gf15c1c3ef/CombineVariants.nf

@@ -6,14 +6,34 @@ process CombineVariants {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(analysis_id), file(vcf_files), file(vcf_idx_files)
+        tuple(analysis_id, path(vcf_files), path(vcf_idx_files))
 
     output:
-    tuple val(analysis_id), file("${analysis_id}.vcf"), file("${analysis_id}.vcf.idx")
+        tuple(analysis_id, path("${analysis_id}.vcf"), path("${analysis_id}.vcf.idx"), emit:vcf_file)
 
     script:
-    def input_files = vcf_files.collect{"$it"}.join(" -V ")
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${analysis_id}.vcf ${params.optional}
-    """
+        def input_files = vcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${analysis_id}.vcf ${params.optional}
+        """
+}
+
+process CombineVariantsGVCF {
+    tag {"GATK CombineVariantsGVCF ${sample_id}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_CombineVariantsGVCF'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(vcf_files), path(vcf_idx_files))
+
+    output:
+        tuple(sample_id, path("${sample_id}.g.vcf"), path("${sample_id}.g.vcf.idx"), emit:vcf_file)
+
+    script:
+        def input_files = vcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${sample_id}.g.vcf ${params.optional}
+        """
 }

GATK/3.8-1-0-gf15c1c3ef/GenotypeGVCFs.nf

@@ -0,0 +1,24 @@
+process GenotypeGVCFs {
+    tag {"GATK GenotypeGVCFs ${analysis_id}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_GenotypeGVCFs'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(analysis_id, path(gvcf_files), path(gvcf_idx_files), path(interval_file))
+
+    output:
+        tuple(analysis_id, path("${analysis_id}_${interval_file.baseName}.vcf"), path("${analysis_id}_${interval_file.baseName}.vcf.idx"), emit:vcf_file)
+
+    script:
+        def input_files = gvcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T GenotypeGVCFs \
+        --reference_sequence ${params.genome} \
+        -V ${input_files} \
+        --out ${analysis_id}_${interval_file.baseName}.vcf \
+        --intervals ${interval_file} \
+        ${params.optional} \
+        """
+}

GATK/3.8-1-0-gf15c1c3ef/HaplotypeCaller.nf

@@ -6,19 +6,44 @@ process HaplotypeCaller {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(analysis_id), file(bam_files), file(bai_files), file(interval_file)
+        tuple(analysis_id, path(bam_files), path(bai_files), path(interval_file))
 
     output:
-    tuple val(analysis_id), file("${analysis_id}.${interval_file.baseName}.vcf"), file("${analysis_id}.${interval_file.baseName}.vcf.idx")
+        tuple(val(analysis_id), path("${analysis_id}.${interval_file.baseName}.vcf"), path("${analysis_id}.${interval_file.baseName}.vcf.idx"), emit: vcf_file)
 
     script:
-    def input_files = bam_files.collect{"$it"}.join(" --input_file ")
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T HaplotypeCaller \
-    --reference_sequence ${params.genome} \
-    --input_file ${input_files} \
-    --intervals ${interval_file} \
-    --out ${analysis_id}.${interval_file.baseName}.vcf \
-    ${params.optional}
-    """
+        def input_files = bam_files.collect{"$it"}.join(" --input_file ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T HaplotypeCaller \
+        --reference_sequence ${params.genome} \
+        --input_file ${input_files} \
+        --intervals ${interval_file} \
+        --out ${analysis_id}.${interval_file.baseName}.vcf \
+        ${params.optional}
+        """
+}
+
+process HaplotypeCallerGVCF {
+    tag {"GATK HaplotypeCallerGVCF ${sample_id} - ${interval_file.baseName}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_HaplotypeCallerGVCF'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file), path(interval_file))
+
+    output:
+        tuple(val(sample_id), path("${sample_id}_${interval_file.baseName}.g.vcf"), path("${sample_id}_${interval_file.baseName}.g.vcf.idx"), path(interval_file), emit: vcf_file)
+
+    script:
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T HaplotypeCaller \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --intervals ${interval_file} \
+        --out ${sample_id}_${interval_file.baseName}.g.vcf \
+        --emitRefConfidence GVCF \
+        ${params.optional}
+        """
 }

GATK/3.8-1-0-gf15c1c3ef/IndelRealigner.nf

@@ -6,20 +6,19 @@ process IndelRealigner {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(sample_id), file(bam_file), file(bai_file), val(chr), file(target_intervals)
+        tuple(sample_id, path(bam_file), path(bai_file), chr, path(target_intervals))
 
     output:
-    tuple val(sample_id), file("${bam_file.baseName}.realigned.${chr}.bam"), file("${bam_file.baseName}.realigned.${chr}.bai")
+        tuple(sample_id, path("${bam_file.baseName}.realigned.${chr}.bam"), path("${bam_file.baseName}.realigned.${chr}.bai"), emit: bam_file)
 
     script:
-
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T IndelRealigner \
-    --reference_sequence ${params.genome} \
-    --input_file ${bam_file} \
-    --intervals ${chr} \
-    --targetIntervals ${bam_file.baseName}.target_intervals.${chr}.list \
-    --out ${bam_file.baseName}.realigned.${chr}.bam \
-    ${params.optional}
-    """
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T IndelRealigner \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --intervals ${chr} \
+        --targetIntervals ${bam_file.baseName}.target_intervals.${chr}.list \
+        --out ${bam_file.baseName}.realigned.${chr}.bam \
+        ${params.optional}
+        """
 }

GATK/3.8-1-0-gf15c1c3ef/RealignerTargetCreator.nf

@@ -6,19 +6,18 @@ process RealignerTargetCreator {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(sample_id), file(bam_file), file(bai_file), val(chr)
+        tuple(sample_id, path(bam_file), path(bai_file), chr)
 
     output:
-    tuple val(sample_id), val(chr), file("${bam_file.baseName}.target_intervals.${chr}.list")
+        tuple(sample_id, chr, path("${bam_file.baseName}.target_intervals.${chr}.list"), emit: interval_list)
 
     script:
-
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar $params.gatk_path -T RealignerTargetCreator \
-    --reference_sequence ${params.genome} \
-    --input_file ${bam_file} \
-    --intervals ${chr} \
-    --out ${bam_file.baseName}.target_intervals.${chr}.list \
-    ${params.optional}
-    """
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar $params.gatk_path -T RealignerTargetCreator \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --intervals ${chr} \
+        --out ${bam_file.baseName}.target_intervals.${chr}.list \
+        ${params.optional}
+        """
 }

GATK/3.8-1-0-gf15c1c3ef/SelectVariants.nf

@@ -6,13 +6,13 @@ process SelectVariantsSample {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(analysis_id), file(vcf_file), file(vcf_idx_file), val(sample_id)
+        tuple(analysis_id, path(vcf_file), path(vcf_idx_file), sample_id)
 
     output:
-    tuple val(sample_id), file("${sample_id}_${vcf_file.baseName}.vcf"), file("${sample_id}_${vcf_file.baseName}.vcf.idx")
+        tuple(sample_id, path("${sample_id}_${vcf_file.baseName}.vcf"), path("${sample_id}_${vcf_file.baseName}.vcf.idx"), emit: vcf_file)
 
     script:
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T SelectVariants --reference_sequence ${params.genome} -V ${vcf_file} --out ${sample_id}_${vcf_file.baseName}.vcf -sn ${sample_id}
-    """
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T SelectVariants --reference_sequence ${params.genome} -V ${vcf_file} --out ${sample_id}_${vcf_file.baseName}.vcf -sn ${sample_id}
+        """
 }