Merge branch 'master' into BIOWDL-25

biopet.wdl

+# PLEASE ADD TASKS IN ALPHABETIC ORDER.
+# This makes searching a lot easier.
+task BaseCounter {
+    String? preCommand
+    String tool_jar #Should this be of type File?
+    File bam
+    File refFlat
+    String outputDir
+    String prefix
+
+    Float? memory
+    Float? memoryMultiplier
+
+    Int mem = ceil(select_first([memory, 12.0]))
+    command {
+        set -e -o pipefail
+        ${preCommand}
+        mkdir -p ${outputDir}
+        java -Xmx${mem}G -jar ${tool_jar} \
+        -b ${bam} \
+        -r ${refFlat} \
+        -o ${outputDir} \
+        -p ${prefix}
+    }
+
+    output {
+        File exonAntisense = outputDir + "/" + prefix + ".base.exon.antisense.counts"
+        File exon = outputDir + "/" + prefix + ".base.exon.counts"
+        File exonMergeAntisense = outputDir + "/" + prefix + ".base.exon.merge.antisense.counts"
+        File exonMerge = outputDir + "/" + prefix + ".base.exon.merge.counts"
+        File exonMergeSense = outputDir + "/" + prefix + ".base.exon.merge.sense.counts"
+        File exonSense = outputDir + "/" + prefix + ".base.exon.sense.counts"
+        File geneAntisense = outputDir + "/" + prefix + ".base.gene.antisense.counts"
+        File gene = outputDir + "/" + prefix + ".base.gene.counts"
+        File geneExonicAntisense = outputDir + "/" + prefix + ".base.gene.exonic.antisense.counts"
+        File geneExonic = outputDir + "/" + prefix + ".base.gene.exonic.counts"
+        File geneExonicSense = outputDir + "/" + prefix + ".base.gene.exonic.sense.counts"
+        File geneIntronicAntisense = outputDir + "/" + prefix + ".base.gene.intronic.antisense.counts"
+        File geneIntronic = outputDir + "/" + prefix + ".base.gene.intronic.counts"
+        File geneIntronicSense = outputDir + "/" + prefix + ".base.gene.intronic.sense.counts"
+        File geneSense = outputDir + "/" + prefix + ".base.gene.sense.counts"
+        File intronAntisense = outputDir + "/" + prefix + ".base.intron.antisense.counts"
+        File intron = outputDir + "/" + prefix + ".base.intron.counts"
+        File intronMergeAntisense = outputDir + "/" + prefix + ".base.intron.merge.antisense.counts"
+        File intronMerge = outputDir + "/" + prefix + ".base.intron.merge.counts"
+        File intronMergeSense = outputDir + "/" + prefix + ".base.intron.merge.sense.counts"
+        File intronSense = outputDir + "/" + prefix + ".base.intron.sense.counts"
+        File metaExonsNonStranded = outputDir + "/" + prefix + ".base.metaexons.non_stranded.counts"
+        File metaExonsStrandedAntisense = outputDir + "/" + prefix + ".base.metaexons.stranded.antisense.counts"
+        File metaExonsStranded = outputDir + "/" + prefix + ".base.metaexons.stranded.counts"
+        File metaExonsStrandedSense = outputDir + "/" + prefix + ".base.metaexons.stranded.sense.counts"
+        File transcriptAntisense = outputDir + "/" + prefix + ".base.transcript.antisense.counts"
+        File transcript = outputDir + "/" + prefix + ".base.transcript.counts"
+        File transcriptExonicAntisense = outputDir + "/" + prefix + ".base.transcript.exonic.antisense.counts"
+        File transcriptExonic = outputDir + "/" + prefix + ".base.transcript.exonic.counts"
+        File transcriptExonicSense = outputDir + "/" + prefix + ".base.transcript.exonic.sense.counts"
+        File transcriptIntronicAntisense = outputDir + "/" + prefix + ".base.transcript.intronic.antisense.counts"
+        File transcriptIntronic = outputDir + "/" + prefix + ".base.transcript.intronic.counts"
+        File transcriptIntronicSense = outputDir + "/" + prefix + ".base.transcript.intronic.sense.counts"
+        File transcriptSense = outputDir + "/" + prefix + ".base.transcript.sense.counts"
+    }
+
+    runtime {
+        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+    }
+}
+
 task FastqSplitter {
     String? preCommand
     File inputFastq
@@ -23,36 +90,30 @@ task FastqSplitter {
     }
 }
 
-task ScatterRegions {
+task FastqSync {
     String? preCommand
-    File ref_fasta
-    File ref_dict
-    String outputDirPath
-    String tool_jar
-    Int? scatterSize
-    File? regions
-
-    Float? memory
-    Float? memoryMultiplier
-
-    Int mem = ceil(select_first([memory, 4.0]))
+    File ref1
+    File ref2
+    File in1
+    File in2
+    String out1path
+    String out2path
+    File tool_jar
     command {
         set -e -o pipefail
         ${preCommand}
-        mkdir -p ${outputDirPath}
-        java -Xmx${mem}G -jar ${tool_jar} \
-          -R ${ref_fasta} \
-          -o ${outputDirPath} \
-          ${"-s " + scatterSize} \
-          ${"-L " + regions}
+        mkdir -p $(dirname ${out1path}) $(dirname ${out2path})
+        java -jar ${tool_jar} \
+        --in1 ${in1} \
+        --in2 ${in2} \
+        --ref1 ${ref1} \
+        --ref2 ${ref2} \
+        --out1 ${out1path} \
+        --out2 ${out2path}
     }
-
     output {
-        Array[File] scatters = glob(outputDirPath + "/scatter-*.bed")
-    }
-
-    runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
+        File out1 = out1path
+        File out2 = out2path
     }
 }
 
@@ -96,67 +157,36 @@ task SampleConfig {
     }
 }
 
-task BaseCounter {
+task ScatterRegions {
     String? preCommand
-    String tool_jar #Should this be of type File?
-    File bam
-    File refFlat
-    String outputDir
-    String prefix
+    File ref_fasta
+    File ref_dict
+    String outputDirPath
+    String tool_jar
+    Int? scatterSize
+    File? regions
 
     Float? memory
     Float? memoryMultiplier
 
-    Int mem = ceil(select_first([memory, 12.0]))
+    Int mem = ceil(select_first([memory, 4.0]))
     command {
         set -e -o pipefail
         ${preCommand}
-        mkdir -p ${outputDir}
+        mkdir -p ${outputDirPath}
         java -Xmx${mem}G -jar ${tool_jar} \
-        -b ${bam} \
-        -r ${refFlat} \
-        -o ${outputDir} \
-        -p ${prefix}
+          -R ${ref_fasta} \
+          -o ${outputDirPath} \
+          ${"-s " + scatterSize} \
+          ${"-L " + regions}
     }
 
     output {
-        File exonAntisense = outputDir + "/" + prefix + ".base.exon.antisense.counts"
-        File exon = outputDir + "/" + prefix + ".base.exon.counts"
-        File exonMergeAntisense = outputDir + "/" + prefix + ".base.exon.merge.antisense.counts"
-        File exonMerge = outputDir + "/" + prefix + ".base.exon.merge.counts"
-        File exonMergeSense = outputDir + "/" + prefix + ".base.exon.merge.sense.counts"
-        File exonSense = outputDir + "/" + prefix + ".base.exon.sense.counts"
-        File geneAntisense = outputDir + "/" + prefix + ".base.gene.antisense.counts"
-        File gene = outputDir + "/" + prefix + ".base.gene.counts"
-        File geneExonicAntisense = outputDir + "/" + prefix + ".base.gene.exonic.antisense.counts"
-        File geneExonic = outputDir + "/" + prefix + ".base.gene.exonic.counts"
-        File geneExonicSense = outputDir + "/" + prefix + ".base.gene.exonic.sense.counts"
-        File geneIntronicAntisense = outputDir + "/" + prefix + ".base.gene.intronic.antisense.counts"
-        File geneIntronic = outputDir + "/" + prefix + ".base.gene.intronic.counts"
-        File geneIntronicSense = outputDir + "/" + prefix + ".base.gene.intronic.sense.counts"
-        File geneSense = outputDir + "/" + prefix + ".base.gene.sense.counts"
-        File intronAntisense = outputDir + "/" + prefix + ".base.intron.antisense.counts"
-        File intron = outputDir + "/" + prefix + ".base.intron.counts"
-        File intronMergeAntisense = outputDir + "/" + prefix + ".base.intron.merge.antisense.counts"
-        File intronMerge = outputDir + "/" + prefix + ".base.intron.merge.counts"
-        File intronMergeSense = outputDir + "/" + prefix + ".base.intron.merge.sense.counts"
-        File intronSense = outputDir + "/" + prefix + ".base.intron.sense.counts"
-        File metaExonsNonStranded = outputDir + "/" + prefix + ".base.metaexons.non_stranded.counts"
-        File metaExonsStrandedAntisense = outputDir + "/" + prefix + ".base.metaexons.stranded.antisense.counts"
-        File metaExonsStranded = outputDir + "/" + prefix + ".base.metaexons.stranded.counts"
-        File metaExonsStrandedSense = outputDir + "/" + prefix + ".base.metaexons.stranded.sense.counts"
-        File transcriptAntisense = outputDir + "/" + prefix + ".base.transcript.antisense.counts"
-        File transcript = outputDir + "/" + prefix + ".base.transcript.counts"
-        File transcriptExonicAntisense = outputDir + "/" + prefix + ".base.transcript.exonic.antisense.counts"
-        File transcriptExonic = outputDir + "/" + prefix + ".base.transcript.exonic.counts"
-        File transcriptExonicSense = outputDir + "/" + prefix + ".base.transcript.exonic.sense.counts"
-        File transcriptIntronicAntisense = outputDir + "/" + prefix + ".base.transcript.intronic.antisense.counts"
-        File transcriptIntronic = outputDir + "/" + prefix + ".base.transcript.intronic.counts"
-        File transcriptIntronicSense = outputDir + "/" + prefix + ".base.transcript.intronic.sense.counts"
-        File transcriptSense = outputDir + "/" + prefix + ".base.transcript.sense.counts"
+        Array[File] scatters = glob(outputDirPath + "/scatter-*.bed")
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
     }
 }
+

bwa.wdl

-task BwaMem {
+task mem {
     String? preCommand
     File inputR1
     File? inputR2
-    String referenceFasta
+    File referenceFasta
     Array[File] indexFiles # These indexFiles need to be added, otherwise cromwell will not find them.
     String outputPath
     String? readgroup
@@ -10,6 +10,7 @@ task BwaMem {
     Int? threads
     Int? memory
 
+
     command {
         set -e -o pipefail
         mkdir -p $(dirname ${outputPath})
@@ -23,8 +24,8 @@ task BwaMem {
         File bamFile = outputPath
     }
     runtime{
-        cpu: if defined(threads) then threads else 1
-        memory: if defined(memory) then memory else 8
+        cpu: select_first([threads,1])
+        memory: select_first([memory,8])
     }
 }
 
@@ -35,6 +36,7 @@ task index {
     Int? blockSize
     String? outputDir
     String fastaFilename = basename(fasta)
+    String outputFile = if (defined(outputDir)) then outputDir + "/" + fastaFilename else fasta
 
     command {
         set -e -o pipefail
@@ -47,13 +49,12 @@ task index {
         bwa index \
         ${"-a " + constructionAlgorithm} \
         ${"-b" + blockSize} \
-        ${outputDir + "/"}${fastaFilename}
+        ${outputFile}
     }
 
     output {
-        File indexBase = if (defined(outputDir)) then select_first([outputDir]) + "/" + fastaFilename else fastaFilename
-        File indexedFasta = indexBase
-        Array[File] indexFiles = [indexBase + ".bwt",indexBase + ".pac",indexBase + ".sa",indexBase + ".amb",indexBase + ".ann"]
+        File indexedFasta = outputFile
+        Array[File] indexFiles = [outputFile + ".bwt",outputFile + ".pac",outputFile + ".sa",outputFile + ".amb",outputFile + ".ann"]
     }
     parameter_meta {
         fasta: "Fasta file to be indexed"

picard.wdl

@@ -147,6 +147,41 @@ task MergeVCFs {
         File output_vcf_index = output_vcf_path + ".tbi"
     }
 
+    runtime {
+        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+    }
+}
+
+task SamToFastq {
+    String? preCommand
+    File inputBam
+    String outputRead1
+    String? outputRead2
+    String? outputUnpaired
+    String picard_jar
+    Float? memory
+    Float? memoryMultiplier
+    Int mem = ceil(select_first([memory, 16.0])) # High memory default to avoid crashes.
+
+    command {
+        set -e -o pipefail
+        ${preCommand}
+        java \
+        -Xmx${mem}G \
+        -jar ${picard_jar} \
+        SamToFastq \
+        I=${inputBam} \
+        ${"FASTQ=" + outputRead1} \
+        ${"SECOND_END_FASTQ=" + outputRead2} \
+        ${"UNPAIRED_FASTQ=" + outputUnpaired}
+    }
+
+    output {
+        File read1 = outputRead1
+        File? read2 = outputRead2
+        File? unpairedRead = outputUnpaired
+    }
+
     runtime {
         memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
     }

samtools.wdl

@@ -118,3 +118,40 @@ task fastq {
 
     }
 }
+
+task view {
+    String? preCommand
+    File inFile
+    File? referenceFasta
+    String outputFileName
+    Boolean? outputBam
+    Boolean? uncompressedBamOutput
+    Int? includeFilter
+    Int? excludeFilter
+    Int? excludeSpecificFilter
+    Int? threads
+    Int? memory
+
+    command {
+    set -e -o pipefail
+    ${preCommand}
+    samtools view \
+    ${"-T " + referenceFasta} \
+    ${"-o " + outputFileName} \
+    ${true="-b " false="" outputBam} \
+    ${true="-u " false="" uncompressedBamOutput} \
+    ${"-f " + includeFilter} \
+    ${"-F " + excludeFilter} \
+    ${"-G " + excludeSpecificFilter} \
+    ${"--threads " + threads - 1} \
+    ${inFile}
+    }
+
+    output {
+        File outputFile = outputFileName
+    }
+    runtime {
+        cpu: select_first([threads, 1])
+        memory: select_first([memory, 1])
+    }
+}

spades.wdl

@@ -22,14 +22,15 @@ task spades {
     Boolean? disableRepeatResolution
     File? dataset
     Int? threads
-    Int? memoryGb
+    Float? memoryGb
     File? tmpDir
     String? k
     Float? covCutoff
     Int? phredOffset
     Int finalThreads = select_first([threads,1])
-    Int totalMemory = select_first([memoryGb, finalThreads * 16])
-    Int clusterMemory = totalMemory / finalThreads
+    Float totalMemory = select_first([memoryGb, finalThreads * 16.0])
+    Int finalMemory = ceil(totalMemory)
+    Int clusterMemory = ceil(totalMemory / finalThreads)
 
     command {
         set -e -o pipefail
@@ -57,7 +58,7 @@ task spades {
         ${true="--disable-rr" false="" disableRepeatResolution } \
         ${"--dataset " + dataset } \
         ${"--threads " + finalThreads} \
-        ${"--memory " + totalMemory } \
+        ${"--memory " + finalMemory } \
         ${"-k " + k } \
         ${"--cov-cutoff " + covCutoff } \
         ${"--phred-offset " + phredOffset }