Merge branch 'add_sv_tasks' of https://github.com/biowdl/tasks into add_sv_tasks

bcftools.wdl

@@ -4,19 +4,20 @@ task Bcf2Vcf {
     input {
         File bcf
         String outputPath
+
         String dockerImage = "quay.io/biocontainers/bcftools:1.9--ha228f0b_3"
     }
-    
+
     command {
         set -e
         mkdir -p "$(dirname ~{outputPath})"
         bcftools view ~{bcf} -O v -o ~{outputPath}
     }
-    
+
     output {
         File outputVcf = outputPath
     }
-    
+
     runtime {
         docker: dockerImage
     }

clever.wdl

@@ -2,13 +2,17 @@ version 1.0
 
 import "bwa.wdl"
 
-task Prediction {
+task Mateclever {
     input {
-        File bamFile
-        File bamIndex
+        File fiteredBam
+        File indexedFiteredBam
         BwaIndex bwaIndex
+        File predictions
         String outputPath
-   
+        Int cleverMaxDelLength = 100000
+        Int maxLengthDiff= 30
+        Int maxOffset = 150
+
         Int threads = 10
         String memory = "15G"
         String dockerImage = "quay.io/biocontainers/clever-toolkit:2.4--py36hcfe0e84_6"
@@ -17,18 +21,21 @@ task Prediction {
     command {
         set -e
         mkdir -p "$(dirname ~{outputPath})"
-        clever \
+        echo ~{outputPath} ~{fiteredBam} ~{predictions} none > predictions.list
+        mateclever \
         -T ~{threads} \
-        --use_mapq \
-        --sorted \
+        -k \
         -f \
-        ~{bamFile} \
+        -M ~{cleverMaxDelLength} \
+        -z ~{maxLengthDiff} \
+        -o ~{maxOffset} \
         ~{bwaIndex.fastaFile} \
+        predictions.list \
         ~{outputPath}
     }
 
     output {
-        File predictions = outputPath + "/predictions.vcf"
+        File matecleverVcf = outputPath + "/deletions.vcf"
     }
 
     runtime {
@@ -39,26 +46,26 @@ task Prediction {
 
     parameter_meta {
         # inputs
-        bamFile: {description: "The bam file to process.", category: "required"}
-        bamIndex: {description: "The index bam file.", category: "required"}
+        fiteredBam: {description: "The bam file where sequences less than 30bp were removed.", category: "required"}
+        indexedFiteredBam: {description: "The index of the filtered bam file.", category: "required"}
         bwaIndex: {description: "The BWA index files.", category: "required"}
+        predictions: {description: "The predicted deletions (VCF) from clever.", category: "required"}
         outputPath: {description: "The location the output VCF file should be written.", category: "common"}
         threads: {description: "The the number of threads required to run a program", category: "advanced"}
         memory: {description: "The memory required to run the programs", category: "advanced"}
+        cleverMaxDelLength: {description: "Maximum deletion length to look for from clever predictions.", category: "advanced"}
+        maxLengthDiff: {description: "Maximum length difference between split-read and read-pair deletion to be considered identical ", category: "advanced"}
+        maxOffset: {description: "Maximum center distance between split-read and read-pair deletion to be considered identical", category: "advanced"}
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
     }
 }
 
-task Mateclever {
+task Prediction {
     input {
-        File fiteredBam
-        File indexedFiteredBam
+        File bamFile
+        File bamIndex
         BwaIndex bwaIndex
-        File predictions
         String outputPath
-        Int cleverMaxDelLength = 100000
-        Int maxLengthDiff= 30
-        Int maxOffset = 150
 
         Int threads = 10
         String memory = "15G"
@@ -68,21 +75,18 @@ task Mateclever {
     command {
         set -e
         mkdir -p "$(dirname ~{outputPath})"
-        echo ~{outputPath} ~{fiteredBam} ~{predictions} none > predictions.list
-        mateclever \
+        clever \
         -T ~{threads} \
-        -k \
+        --use_mapq \
+        --sorted \
         -f \
-        -M ~{cleverMaxDelLength} \
-        -z ~{maxLengthDiff} \
-        -o ~{maxOffset} \
+        ~{bamFile} \
         ~{bwaIndex.fastaFile} \
-        predictions.list \
         ~{outputPath}
     }
 
     output {
-        File matecleverVcf = outputPath + "/deletions.vcf"
+        File predictions = outputPath + "/predictions.vcf"
     }
 
     runtime {
@@ -92,6 +96,7 @@ task Mateclever {
     }
 
     parameter_meta {
+<<<<<<< HEAD
         fiteredBam: {description: "The bam file where sequences less than 30bp were removed.", category: "advanced"}
         indexedFiteredBam: {description: "The index of the filtered bam file.", category: "advanced"}
         bwaIndex: {description: "The BWA index files.", category: "required"}
@@ -102,6 +107,15 @@ task Mateclever {
         maxLengthDiff: {description: "Maximum length difference between split-read and read-pair deletion to be considered identical ", category: "advanced"}
         cleverMaxDelLength: {description: "Maximum deletion length to look for from clever predictions.", category: "advanced"}
         memory: {description: "The memory required to run the programs", category: "advanced"}
+=======
+        # inputs
+        bamFile: {description: "The bam file to process.", category: "required"}
+        bamIndex: {description: "The index bam file.", category: "required"}
+        bwaIndex: {description: "The BWA index files.", category: "required"}
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        threads: {description: "The the number of threads required to run a program", category: "common"}
+        memory: {description: "The memory required to run the programs", category: "common"}
+>>>>>>> 338f85339b62da7921f2d5d68d0870e81a80d542
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
     }
 }

delly.wdl

@@ -33,6 +33,7 @@ task CallSV {
     }
 
     parameter_meta {
+        # inputs
         bamFile: {description: "The bam file to process.", category: "required"}
         bamIndex: {description: "The index bam file.", category: "required"}
         referenceFasta: {description: "The reference fasta file also used for mapping.", category: "required"}

manta.wdl

@@ -2,15 +2,13 @@ version 1.0
 
 import "common.wdl"
 
-task Somatic {
+task Germline {
     input {
-        File tumorBam
-        File tumorBamIndex
-        File? normalBam
-        File? normalBamIndex
+        File bamFile
+        File bamIndex
         File referenceFasta
         File referenceFastaFai
-        String runDir = "./manta_run"
+        String runDir
         File? callRegions
         File? callRegionsIndex
         Boolean exome = false
@@ -21,9 +19,9 @@ task Somatic {
     }
 
     command {
+        set -e
         configManta.py \
-        ~{"--normalBam " + normalBam} \
-        ~{"--tumorBam " + tumorBam} \
+        ~{"--normalBam " + bamFile} \
         --referenceFasta ~{referenceFasta} \
         ~{"--callRegions " + callRegions} \
         --runDir ~{runDir} \
@@ -36,18 +34,8 @@ task Somatic {
     }
 
     output {
-        File candidateSmallIndelsVcf = runDir + "/results/variants/candidateSmallIndels.vcf.gz"
-        File candidateSmallIndelsVcfIndex = runDir + "/results/variants/candidateSmallIndels.vcf.gz.tbi"
-        File candidateSVVcf = runDir + "/results/variants/candidateSV.vcf.gz"
-        File candidatSVVcfIndex = runDir + "/results/variants/candidateSV.vcf.gz.tbi"
-        File tumorSVVcf = if defined(normalBam)
-                          then runDir + "/results/variants/somaticSV.vcf.gz"
-                          else runDir + "/results/variants/tumorSV.vcf.gz"
-        File tumorSVVcfIndex = if defined(normalBam)
-                               then runDir + "/results/variants/somaticSV.vcf.gz.tbi"
-                               else runDir + "/results/variants/tumorSV.vcf.gz.tbi"
-        File? diploidSV = runDir + "/results/variants/diploidSV.vcf.gz"
-        File? diploidSVindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
+        File mantaVCF = runDir + "/results/variants/diploidSV.vcf.gz"
+        File mantaVCFindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
     }
 
     runtime {
@@ -58,29 +46,29 @@ task Somatic {
 
     parameter_meta {
         # inputs
-        tumorBam: {description: "The tumor/case sample's BAM file.", category: "required"}
-        tumorBamIndex: {description: "The index for the tumor/case sample's BAM file.", category: "required"}
-        normalBam: {description: "The normal/control sample's BAM file.", category: "common"}
-        normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "common"}
-        referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
-        referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+        bamFile: {description: "The bam file to process.", category: "required"}
+        bamIndex: {description: "The index bam file.", category: "required"}
+        referenceFasta: {description: "The reference fasta file also used for mapping.", category: "advanced"}
+        referenceFastaFai: {description: "Fasta index (.fai) file of the reference", category: "required" }
         runDir: {description: "The directory to use as run/output directory.", category: "common"}
         callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
         callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
         exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
-        cores: {description: "The number of cores to use.", category: "advanced"}
-        memoryGb: {description: "The amount of memory this job will use in Gigabytes.", category: "advanced"}
+        cores: {description: "The the number of cores required to run a program", category: "common"}
+        memoryGb: {description: "The memory required to run the manta", category: "common"}
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
     }
 }
 
-task Germline {
+task Somatic {
     input {
-        File bamFile
-        File bamIndex
+        File tumorBam
+        File tumorBamIndex
+        File? normalBam
+        File? normalBamIndex
         File referenceFasta
         File referenceFastaFai
-        String runDir
+        String runDir = "./manta_run"
         File? callRegions
         File? callRegionsIndex
         Boolean exome = false
@@ -91,9 +79,9 @@ task Germline {
     }
 
     command {
-        set -e
         configManta.py \
-        ~{"--normalBam " + bamFile} \
+        ~{"--normalBam " + normalBam} \
+        ~{"--tumorBam " + tumorBam} \
         --referenceFasta ~{referenceFasta} \
         ~{"--callRegions " + callRegions} \
         --runDir ~{runDir} \
@@ -106,8 +94,18 @@ task Germline {
     }
 
     output {
-        File mantaVCF = runDir + "/results/variants/diploidSV.vcf.gz"
-        File mantaVCFindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
+        File candidateSmallIndelsVcf = runDir + "/results/variants/candidateSmallIndels.vcf.gz"
+        File candidateSmallIndelsVcfIndex = runDir + "/results/variants/candidateSmallIndels.vcf.gz.tbi"
+        File candidateSVVcf = runDir + "/results/variants/candidateSV.vcf.gz"
+        File candidatSVVcfIndex = runDir + "/results/variants/candidateSV.vcf.gz.tbi"
+        File tumorSVVcf = if defined(normalBam)
+                          then runDir + "/results/variants/somaticSV.vcf.gz"
+                          else runDir + "/results/variants/tumorSV.vcf.gz"
+        File tumorSVVcfIndex = if defined(normalBam)
+                               then runDir + "/results/variants/somaticSV.vcf.gz.tbi"
+                               else runDir + "/results/variants/tumorSV.vcf.gz.tbi"
+        File? diploidSV = runDir + "/results/variants/diploidSV.vcf.gz"
+        File? diploidSVindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
     }
 
     runtime {
@@ -130,4 +128,3 @@ task Germline {
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
     }
 }
-