diff --git a/.travis.yml b/.travis.yml
index cb8b70de06b9c35f8d7759b565eb621c435549ca..4065d1cb15dd8c5d625c7ed43043955d1b7bd8a8 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,6 +1,9 @@
language: java
script:
- - set -e
- - export CROMWELL_VERSION=34
- - wget https://github.com/broadinstitute/cromwell/releases/download/$CROMWELL_VERSION/womtool-$CROMWELL_VERSION.jar
- - for F in $(git ls-files *.wdl); do echo $F; java -jar womtool-$CROMWELL_VERSION.jar validate $F; done
+- set -e
+- export CROMWELL_VERSION=34
+# - wget https://github.com/broadinstitute/cromwell/releases/download/$CROMWELL_VERSION/womtool-$CROMWELL_VERSION.jar
+- wget https://barmsijs.lumc.nl/womtool-35-a7ae2d8-SNAP.jar
+- for F in `find -name "*.wdl"`; do echo $F; java -jar womtool-*.jar validate $F; done
+- 'if [ "$TRAVIS_PULL_REQUEST" != "false" ]; then git submodule foreach --recursive git checkout $TRAVIS_BRANCH && git submodule foreach --recursive git pull; fi'
+- "git diff --exit-code || (echo ERROR: Git changes detected. Please update submodules && exit 1)"
diff --git a/biopet/bamstats.wdl b/biopet/bamstats.wdl
index 8459ca4f26e344764f7ea04b0d32f846829b7262..df919ef82352df4c73b4ec6efe290c2d5b34784b 100644
--- a/biopet/bamstats.wdl
+++ b/biopet/bamstats.wdl
@@ -2,19 +2,19 @@ version 1.0
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 2018
+import "../common.wdl" as common
+
task Generate {
input {
String? preCommand
File? toolJar
- File bam
- File bamIndex
+ IndexedBamFile bam
File? bedFile
Boolean scatterMode = false
Boolean onlyUnmapped = false
Boolean tsvOutputs = false
String outputDir
- File? reference
- File? referenceDict
+ Reference? reference
Int memory = 4
Float memoryMultiplier = 2.0
}
@@ -23,14 +23,16 @@ task Generate {
then "java -Xmx" + memory + "G -jar " + toolJar
else "biopet-bamstats -Xmx" + memory + "G"
+ String refArg = if (defined(reference)) then "--reference " + select_first([reference]).fasta else ""
+
command {
set -e -o pipefail
~{preCommand}
mkdir -p ~{outputDir}
~{toolCommand} Generate \
- --bam ~{bam} \
+ --bam ~{bam.file} \
~{"--bedFile " + bedFile} \
- ~{"--reference " + reference} \
+ ~{refArg} \
~{true="--onlyUnmapped" false="" onlyUnmapped} \
~{true="--scatterMode" false="" scatterMode} \
~{true="--tsvOutputs" false="" tsvOutputs} \
diff --git a/biopet.wdl b/biopet/biopet.wdl
similarity index 81%
rename from biopet.wdl
rename to biopet/biopet.wdl
index feb963fc2745f7d523025a3258a4a9f27a0280f7..daa5371764393b99253c16945549eb1ab9c1fcf6 100644
--- a/biopet.wdl
+++ b/biopet/biopet.wdl
@@ -1,11 +1,12 @@
version 1.0
+import "../common.wdl"
+
task BaseCounter {
input {
String? preCommand
File? toolJar
- File bam
- File bamIndex
+ IndexedBamFile bam
File refFlat
String outputDir
String prefix
@@ -23,7 +24,7 @@ task BaseCounter {
mkdir -p ~{outputDir}
~{preCommand}
~{toolCommand} \
- -b ~{bam} \
+ -b ~{bam.file} \
-r ~{refFlat} \
-o ~{outputDir} \
-p ~{prefix}
@@ -160,10 +161,8 @@ task FastqSplitter {
task FastqSync {
input {
String? preCommand
- File ref1
- File ref2
- File in1
- File in2
+ FastqPair refFastq
+ FastqPair inputFastq
String out1path
String out2path
File? toolJar
@@ -181,17 +180,19 @@ task FastqSync {
~{preCommand}
mkdir -p $(dirname ~{out1path}) $(dirname ~{out2path})
~{toolCommand} \
- --in1 ~{in1} \
- --in2 ~{in2} \
- --ref1 ~{ref1} \
- --ref2 ~{ref2} \
+ --in1 ~{inputFastq.R1} \
+ --in2 ~{inputFastq.R2} \
+ --ref1 ~{refFastq.R1} \
+ --ref2 ~{refFastq.R2} \
--out1 ~{out1path} \
--out2 ~{out2path}
}
output {
- File out1 = out1path
- File out2 = out2path
+ FastqPair out1 = object {
+ R1: out1path,
+ R1: out2path
+ }
}
runtime {
@@ -199,89 +200,10 @@ task FastqSync {
}
}
-task SampleConfig {
- input {
- File? toolJar
- String? preCommand
- Array[File]+ inputFiles
- String keyFilePath
- String? sample
- String? library
- String? readgroup
- String? jsonOutputPath
- String? tsvOutputPath
-
- Int memory = 4
- Float memoryMultiplier = 2.0
- }
-
- String toolCommand = if defined(toolJar)
- then "java -Xmx" + memory + "G -jar " +toolJar
- else "biopet-sampleconfig -Xmx" + memory + "G"
-
- command {
- set -e -o pipefail
- ~{preCommand}
- mkdir -p . ~{"$(dirname " + jsonOutputPath + ")"} ~{"$(dirname " + tsvOutputPath + ")"}
- ~{toolCommand} \
- -i ~{sep="-i " inputFiles} \
- ~{"--sample " + sample} \
- ~{"--library " + library} \
- ~{"--readgroup " + readgroup} \
- ~{"--jsonOutput " + jsonOutputPath} \
- ~{"--tsvOutput " + tsvOutputPath} \
- > ~{keyFilePath}
- }
-
- output {
- File keysFile = keyFilePath
- File? jsonOutput = jsonOutputPath
- File? tsvOutput = tsvOutputPath
- }
-
- runtime {
- memory: ceil(memory * memoryMultiplier)
- }
-}
-
-task SampleConfigCromwellArrays {
- input {
- File? toolJar
- String? preCommand
- Array[File]+ inputFiles
- String outputPath
-
- Int memory = 4
- Float memoryMultiplier = 2.0
- }
-
- String toolCommand = if defined(toolJar)
- then "java -Xmx" + memory + "G -jar " + toolJar
- else "biopet-sampleconfig -Xmx" + memory + "G"
-
- command {
- set -e -o pipefail
- ~{preCommand}
- mkdir -p $(dirname ~{outputPath})
- ~{toolCommand} CromwellArrays \
- -i ~{sep="-i " inputFiles} \
- ~{"-o " + outputPath}
- }
-
- output {
- File outputFile = outputPath
- }
-
- runtime {
- memory: ceil(memory * memoryMultiplier)
- }
-}
-
task ScatterRegions {
input {
String? preCommand
- File refFasta
- File refDict
+ Reference reference
String outputDirPath
File? toolJar
Int? scatterSize
@@ -300,7 +222,7 @@ task ScatterRegions {
~{preCommand}
mkdir -p ~{outputDirPath}
~{toolCommand} \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-o ~{outputDirPath} \
~{"-s " + scatterSize} \
~{"-L " + regions}
@@ -315,48 +237,13 @@ task ScatterRegions {
}
}
-task Seqstat {
- input {
- String? preCommand
- File? toolJar
- File fastq
- String outputFile
-
- Int memory = 4
- Float memoryMultiplier = 2.0
- }
-
- String toolCommand = if defined(toolJar)
- then "java -Xmx" + memory + "G -jar " + toolJar
- else "biopet-seqstat -Xmx" + memory + "G"
-
- command {
- set -e -o pipefail
- ~{preCommand}
- mkdir -p $(dirname ~{outputFile})
- ~{toolCommand} \
- --fastq ~{fastq} \
- --output ~{outputFile}
- }
-
- output {
- File json = outputFile
- }
-
- runtime {
- memory: ceil(memory * memoryMultiplier)
- }
-}
-
task ValidateAnnotation {
input {
String? preCommand
File? toolJar
File? refRefflat
File? gtfFile
- File refFasta
- File refFastaIndex
- File refDict
+ Reference reference
Int memory = 4
Float memoryMultiplier = 2.0
@@ -372,7 +259,7 @@ task ValidateAnnotation {
~{toolCommand} \
~{"-r " + refRefflat} \
~{"-g " + gtfFile} \
- -R ~{refFasta}
+ -R ~{reference.fasta}
}
output {
@@ -388,8 +275,7 @@ task ValidateFastq {
input {
String? preCommand
File? toolJar
- File fastq1
- File? fastq2
+ FastqPair inputFastq
Int memory = 4
Float memoryMultiplier = 2.0
@@ -403,14 +289,13 @@ task ValidateFastq {
set -e -o pipefail
~{preCommand}
~{toolCommand} \
- --fastq1 ~{fastq1} \
- ~{"--fastq2 " + fastq2}
+ --fastq1 ~{inputFastq.R1} \
+ ~{"--fastq2 " + inputFastq.R2}
}
output {
File stderr = stderr()
- File validatedFastq1 = fastq1
- File? validatedFastq2 = fastq2
+ FastqPair validatedFastq = inputFastq
}
runtime {
@@ -422,11 +307,8 @@ task ValidateVcf {
input {
String? preCommand
File? toolJar
- File vcfFile
- File vcfIndex
- File refFasta
- File refFastaIndex
- File refDict
+ IndexedVcfFile vcf
+ Reference reference
Int memory = 4
Float memoryMultiplier = 2.0
@@ -440,8 +322,8 @@ task ValidateVcf {
set -e -o pipefail
~{preCommand}
~{toolCommand} \
- -i ~{vcfFile} \
- -R ~{refFasta}
+ -i ~{vcf.file} \
+ -R ~{reference.fasta}
}
output {
@@ -455,11 +337,8 @@ task ValidateVcf {
task VcfStats {
input {
- File vcfFile
- File vcfIndex
- File refFasta
- File refFastaIndex
- File refDict
+ IndexedVcfFile vcf
+ Reference reference
String outputDir
File? intervals
Array[String]+? infoTags
@@ -493,8 +372,8 @@ task VcfStats {
mkdir -p ~{outputDir}
~{preCommand}
~{toolCommand} \
- -I ~{vcfFile} \
- -R ~{refFasta} \
+ -I ~{vcf.file} \
+ -R ~{reference.fasta} \
-o ~{outputDir} \
-t ~{localThreads} \
~{"--intervals " + intervals} \
diff --git a/biopet/sampleconfig.wdl b/biopet/sampleconfig.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..61defae84ff0583b3515f16a8e6948bbc564c84a
--- /dev/null
+++ b/biopet/sampleconfig.wdl
@@ -0,0 +1,79 @@
+version 1.0
+
+task SampleConfig {
+ input {
+ File? toolJar
+ String? preCommand
+ Array[File]+ inputFiles
+ String keyFilePath
+ String? sample
+ String? library
+ String? readgroup
+ String? jsonOutputPath
+ String? tsvOutputPath
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
+
+ String toolCommand = if defined(toolJar)
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-sampleconfig -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ mkdir -p . ~{"$(dirname " + jsonOutputPath + ")"} ~{"$(dirname " + tsvOutputPath + ")"}
+ ~{toolCommand} \
+ -i ~{sep="-i " inputFiles} \
+ ~{"--sample " + sample} \
+ ~{"--library " + library} \
+ ~{"--readgroup " + readgroup} \
+ ~{"--jsonOutput " + jsonOutputPath} \
+ ~{"--tsvOutput " + tsvOutputPath} \
+ > ~{keyFilePath}
+ }
+
+ output {
+ File keysFile = keyFilePath
+ File? jsonOutput = jsonOutputPath
+ File? tsvOutput = tsvOutputPath
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
+
+task SampleConfigCromwellArrays {
+ input {
+ File? toolJar
+ String? preCommand
+ Array[File]+ inputFiles
+ String outputPath
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
+
+ String toolCommand = if defined(toolJar)
+ then "java -Xmx" + memory + "G -jar " + toolJar
+ else "biopet-sampleconfig -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ mkdir -p $(dirname ~{outputPath})
+ ~{toolCommand} CromwellArrays \
+ -i ~{sep="-i " inputFiles} \
+ ~{"-o " + outputPath}
+ }
+
+ output {
+ File outputFile = outputPath
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
diff --git a/biopet/seqstat.wdl b/biopet/seqstat.wdl
index c1e83a2f86919ad181dfaa4498c0d94b96752e15..a9c24dc688f03a1fdf00eebfab7c1be779b5c326 100644
--- a/biopet/seqstat.wdl
+++ b/biopet/seqstat.wdl
@@ -2,12 +2,13 @@ version 1.0
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 2018
+import "../common.wdl" as common
+
task Generate {
input {
String? preCommand
File? toolJar
- File fastqR1
- File? fastqR2
+ FastqPair fastq
String outputFile
String sample
String library
@@ -26,8 +27,8 @@ task Generate {
~{preCommand}
mkdir -p $(dirname ~{outputFile})
~{toolCommand} Generate \
- --fastqR1 ~{fastqR1} \
- ~{"--fastqR2 " + fastqR2} \
+ --fastqR1 ~{fastq.R1} \
+ ~{"--fastqR2 " + fastq.R2} \
--output ~{outputFile} \
~{"--sample " + sample} \
~{"--library " + library } \
diff --git a/bwa.wdl b/bwa.wdl
index d8ce3e3239a202f93de5ce25fbacd3e75bde6371..9c717ccd789bdde15d9a5f033f7efa82d49386be 100644
--- a/bwa.wdl
+++ b/bwa.wdl
@@ -5,15 +5,14 @@ import "common.wdl" as common
task Mem {
input {
String? preCommand
- File inputR1
- File? inputR2
+ FastqPair inputFastq
BwaIndex bwaIndex
String outputPath
String? readgroup
String? picardJar
- Int threads = 1
+ Int threads = 2
Int memory = 8
Int picardMemory = 4
}
@@ -48,8 +47,8 @@ task Mem {
bwa mem ~{"-t " + threads} \
~{readgroupArg} \
~{bwaIndex.fastaFile} \
- ~{inputR1} \
- ~{inputR2} \
+ ~{inputFastq.R1} \
+ ~{inputFastq.R2} \
~{altCommand} \
| ~{picardCommand}
}
diff --git a/common.wdl b/common.wdl
index 7bd1da697e678744c521a0432337a4e86714af7e..af3b66bf470be5da4cf72ca1bcb8d5cc77cacb88 100644
--- a/common.wdl
+++ b/common.wdl
@@ -24,13 +24,14 @@ task AppendToStringArray {
task CheckFileMD5 {
input {
File file
- String MD5sum
+ File md5
}
command {
set -e -o pipefail
MD5SUM=$(md5sum ~{file} | cut -d ' ' -f 1)
- [ $MD5SUM = ~{MD5sum} ]
+ MD5SUM_CORRECT=$(cat ~{md5} | grep ~{basename(file)} | cut -d ' ' -f 1)
+ [ $MD5SUM = $MD5SUM_CORRECT ]
}
}
@@ -147,16 +148,18 @@ struct Reference {
struct IndexedVcfFile {
File file
File index
+ File? md5sum
}
struct IndexedBamFile {
File file
File index
+ File? md5sum
}
struct FastqPair {
File R1
- String? R1_md5
+ File? R1_md5
File? R2
- String? R2_md5
+ File? R2_md5
}
diff --git a/cutadapt.wdl b/cutadapt.wdl
index 0df1ced44f253b904586c7a89b7dc61436181551..a8160aa2df7039c55f0f10375698a14164553cc9 100644
--- a/cutadapt.wdl
+++ b/cutadapt.wdl
@@ -1,9 +1,10 @@
version 1.0
+import "common.wdl"
+
task Cutadapt {
input {
- File read1
- File? read2
+ FastqPair inputFastq
String read1output
String? read2output
String? format
@@ -119,15 +120,17 @@ task Cutadapt {
~{true="--bwa" false="" bwa} \
~{true="--zero-cap" false="" zeroCap} \
~{true="--no-zero-cap" false="" noZeroCap} \
- ~{read1} \
- ~{read2} \
+ ~{inputFastq.R1} \
+ ~{inputFastq.R2} \
~{"> " + reportPath}
}
output{
+ FastqPair cutOutput = object {
+ R1: read1output,
+ R2: read2output
+ }
File report = if defined(reportPath) then select_first([reportPath]) else stdout()
- File cutRead1 = read1output
- File? cutRead2 = read2output
File? tooLongOutput=tooLongOutputPath
File? tooShortOutput=tooShortOutputPath
File? untrimmedOutput=untrimmedOutputPath
diff --git a/flash.wdl b/flash.wdl
index 3d3eecdf3820be7c841ca44f0f4de580df5e61d1..728a237cc6c3d6eba8b19008d1404df97746913b 100644
--- a/flash.wdl
+++ b/flash.wdl
@@ -1,10 +1,11 @@
version 1.0
+import "common.wdl" as common
+
task Flash {
input {
String? preCommand
- File inputR1
- File inputR2
+ FastqPair inputFastq
String outdirPath
String outPrefix = "flash"
Int? minOverlap
@@ -25,13 +26,17 @@ task Flash {
~{true="--compress " false="" compress} \
~{"--min-overlap=" + minOverlap} \
~{"--max-overlap=" + maxOverlap} \
- ~{inputR1} ~{inputR2}
+ ~{inputFastq.R1} ~{inputFastq.R2}
}
output {
File extendedFrags = outdirPath + "/" + outPrefix + ".extendedFrags.fastq.gz"
File notCombined1 = outdirPath + "/" + outPrefix + ".notCombined_1.fastq.gz"
File notCombined2 = outdirPath + "/" + outPrefix + ".notCombined_2.fastq.gz"
+ FastqPair notCombined = object {
+ R1: notCombined1,
+ R2: notCombined2
+ }
File hist = outdirPath + "/" + outPrefix + ".hist"
File histogram = outdirPath + "/" + outPrefix + ".histogram"
}
diff --git a/gatk.wdl b/gatk.wdl
index f252c7eca36c4676dfbe383d549936494c6183cb..99a5b2c472b2b812cdcdae9a0b6cfa5ff454599d 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -1,18 +1,17 @@
version 1.0
+import "common.wdl"
+
# Apply Base Quality Score Recalibration (BQSR) model
task ApplyBQSR {
input {
String? preCommand
File? gatkJar
- File inputBam
- File inputBamIndex
+ IndexedBamFile inputBam
String outputBamPath
File recalibrationReport
Array[File]+ sequenceGroupInterval
- File refDict
- File refFasta
- File refFastaIndex
+ Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
@@ -29,8 +28,8 @@ task ApplyBQSR {
ApplyBQSR \
--create-output-bam-md5 \
--add-output-sam-program-record \
- -R ~{refFasta} \
- -I ~{inputBam} \
+ -R ~{reference.fasta} \
+ -I ~{inputBam.file} \
--use-original-qualities \
-O ~{outputBamPath} \
-bqsr ~{recalibrationReport} \
@@ -41,8 +40,11 @@ task ApplyBQSR {
}
output {
- File recalibrated_bam = outputBamPath
- File recalibrated_bam_checksum = outputBamPath + ".md5"
+ IndexedBamFile recalibratedBam = {
+ "file": outputBamPath,
+ "index": sub(outputBamPath, "\.bam$", ".bai"),
+ "md5": outputBamPath + ".md5"
+ }
}
runtime {
@@ -55,28 +57,20 @@ task BaseRecalibrator {
input {
String? preCommand
File? gatkJar
- File inputBam
- File inputBamIndex
+ IndexedBamFile inputBam
String recalibrationReportPath
Array[File]+ sequenceGroupInterval
Array[File]? knownIndelsSitesVCFs
- Array[File]? knownIndelsSitesIndices
- File? dbsnpVCF
- File? dbsnpVCFindex
- File refDict
- File refFasta
- File refFastaIndex
+ Array[File]? knownIndelsSitesVCFIndexes
+ IndexedVcfFile? dbsnpVCF
+ Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
}
Array[File]+ knownIndelsSitesVCFsArg = flatten([
select_first([knownIndelsSitesVCFs, []]),
- select_all([dbsnpVCF])
- ])
- Array[File]+ knownIndelsSitesIndicesArg = flatten([
- select_first([knownIndelsSitesIndices, []]),
- select_all([dbsnpVCFindex])
+ [select_first([dbsnpVCF]).file]
])
String toolCommand = if defined(gatkJar)
@@ -88,8 +82,8 @@ task BaseRecalibrator {
~{preCommand}
~{toolCommand} \
BaseRecalibrator \
- -R ~{refFasta} \
- -I ~{inputBam} \
+ -R ~{reference.fasta} \
+ -I ~{inputBam.file} \
--use-original-qualities \
-O ~{recalibrationReportPath} \
--known-sites ~{sep=" --known-sites " knownIndelsSitesVCFsArg} \
@@ -109,16 +103,14 @@ task CombineGVCFs {
input {
String? preCommand
Array[File]+ gvcfFiles
- Array[File]+ gvcfFileIndexes
+ Array[File]+ gvcfFilesIndex
Array[File]+ intervals
String outputPath
String? gatkJar
- File refFasta
- File refFastaIndex
- File refDict
+ Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
@@ -135,19 +127,21 @@ task CombineGVCFs {
if [ ~{length(gvcfFiles)} -gt 1 ]; then
~{toolCommand} \
CombineGVCFs \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{outputPath} \
-V ~{sep=' -V ' gvcfFiles} \
-L ~{sep=' -L ' intervals}
else # TODO this should be handeled in wdl
ln -sf ~{gvcfFiles[0]} ~{outputPath}
- ln -sf ~{gvcfFileIndexes[0]} ~{outputPath}.tbi
+ ln -sf ~{gvcfFiles[0]} ~{outputPath}.tbi
fi
}
output {
- File outputGVCF = outputPath
- File outputGVCFindex = outputPath + ".tbi"
+ IndexedVcfFile outputVCF = {
+ "file": outputPath,
+ "index": outputPath + ".tbi"
+ }
}
runtime {
@@ -192,25 +186,24 @@ task GatherBqsrReports {
task GenotypeGVCFs {
input {
String? preCommand
- File gvcfFiles
- File gvcfFileIndexes
+ Array[File]+ gvcfFiles
+ Array[File]+ gvcfFilesIndex
Array[File]+ intervals
String outputPath
String? gatkJar
- File refFasta
- File refFastaIndex
- File refDict
+ Reference reference
- File? dbsnpVCF
- File? dbsnpVCFindex
+ IndexedVcfFile? dbsnpVCF
- Int memory = 4
- Float memoryMultiplier =3.0
+ Int memory = 6
+ Float memoryMultiplier = 2.0
}
+ String dbsnpArg = if defined(dbsnpVCF) then "-D " + select_first([dbsnpVCF]).file else ""
+
String toolCommand = if defined(gatkJar)
then "java -Xmx" + memory + "G -jar " + gatkJar
else "gatk --java-options -Xmx" + memory + "G"
@@ -220,19 +213,21 @@ task GenotypeGVCFs {
~{preCommand}
~{toolCommand} \
GenotypeGVCFs \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{outputPath} \
- ~{"-D " + dbsnpVCF} \
+ ~{dbsnpArg} \
-G StandardAnnotation \
--only-output-calls-starting-in-intervals \
-new-qual \
- -V ~{gvcfFiles} \
+ -V ~{sep=' -V ' gvcfFiles} \
-L ~{sep=' -L ' intervals}
}
output {
- File outputVCF = outputPath
- File outputVCFindex = outputPath + ".tbi"
+ IndexedVcfFile outputVCF = {
+ "file": outputPath,
+ "index": outputPath + ".tbi"
+ }
}
runtime{
@@ -248,19 +243,18 @@ task HaplotypeCallerGvcf {
Array[File]+ inputBamsIndex
Array[File]+ intervalList
String gvcfPath
- File refDict
- File refFasta
- File refFastaIndex
+ Reference reference
Float contamination = 0.0
String? gatkJar
- File? dbsnpVCF
- File? dbsnpVCFindex
+ IndexedVcfFile? dbsnpVCF
Int memory = 4
Float memoryMultiplier = 3
}
+ String dbsnpArg = if (defined(dbsnpVCF)) then "-D " + select_first([dbsnpVCF]).file else ""
+
String toolCommand = if defined(gatkJar)
then "java -Xmx" + memory + "G -jar " + gatkJar
else "gatk --java-options -Xmx" + memory + "G"
@@ -270,18 +264,20 @@ task HaplotypeCallerGvcf {
~{preCommand}
~{toolCommand} \
HaplotypeCaller \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{gvcfPath} \
-I ~{sep=" -I " inputBams} \
-L ~{sep=' -L ' intervalList} \
- ~{"-D " + dbsnpVCF} \
+ ~{dbsnpArg} \
-contamination ~{contamination} \
-ERC GVCF
}
output {
- File outputGVCF = gvcfPath
- File outputGVCFindex = gvcfPath + ".tbi"
+ IndexedVcfFile outputGVCF = {
+ "file": gvcfPath,
+ "index": gvcfPath + ".tbi"
+ }
}
runtime {
@@ -294,10 +290,8 @@ task MuTect2 {
String? preCommand
Array[File]+ inputBams
- Array[File]+ inputBamIndex
- File refFasta
- File refFastaIndex
- File refDict
+ Array[File]+ inputBamsIndex
+ Reference reference
String outputVcf
String tumorSample
String? normalSample
@@ -317,7 +311,7 @@ task MuTect2 {
~{preCommand}
~{toolCommand} \
Mutect2 \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-I ~{sep=" -I " inputBams} \
-tumor ~{tumorSample} \
~{"-normal " + normalSample} \
@@ -326,8 +320,10 @@ task MuTect2 {
}
output {
- File vcfFile = outputVcf
- File vcfIndex = outputVcf + ".tbi"
+ IndexedVcfFile vcfFile = {
+ "file": outputVcf,
+ "index": outputVcf + ".tbi"
+ }
}
runtime {
@@ -339,11 +335,8 @@ task SplitNCigarReads {
input {
String? preCommand
- File inputBam
- File inputBamIndex
- File refFasta
- File refFastaIndex
- File refDict
+ IndexedBamFile inputBam
+ Reference reference
String outputBam
String? gatkJar
Array[File]+ intervals
@@ -361,15 +354,17 @@ task SplitNCigarReads {
~{preCommand}
~{toolCommand} \
SplitNCigarReads \
- -I ~{inputBam} \
- -R ~{refFasta} \
+ -I ~{inputBam.file} \
+ -R ~{reference.fasta} \
-O ~{outputBam} \
-L ~{sep=' -L ' intervals}
}
output {
- File bam = outputBam
- File bamIndex = sub(outputBam, "\.bam$", ".bai")
+ IndexedBamFile bam = {
+ "file": outputBam,
+ "index": sub(outputBam, "\.bam$", ".bai")
+ }
}
runtime {
diff --git a/htseq.wdl b/htseq.wdl
index db399cc2fb35061e69d280eb2efbcf44e1ccfb6d..cdfc98421feb745340bb5dabe6908c670ef3c9d0 100644
--- a/htseq.wdl
+++ b/htseq.wdl
@@ -1,9 +1,12 @@
version 1.0
+import "common.wdl"
+
task HTSeqCount {
input {
String? preCommand
- Array[File] alignmentFiles
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
File gtfFile
String outputTable
String format = "bam"
@@ -21,7 +24,7 @@ task HTSeqCount {
-f ~{format} \
-r ~{order} \
-s ~{stranded} \
- ~{sep=" " alignmentFiles} \
+ ~{sep=" " inputBams} \
~{gtfFile} \
> ~{outputTable}
}
diff --git a/macs2.wdl b/macs2.wdl
index 9364d9dc4f318bc657d42163925c758b592b2cfd..982802f6d33fde3c6eb5024a1262fced21f74382 100644
--- a/macs2.wdl
+++ b/macs2.wdl
@@ -1,9 +1,12 @@
version 1.0
+import "common.wdl"
+
task PeakCalling {
input {
String? preCommand
- Array[File] bamFiles
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
String outDir
String sampleName
Int threads = 1
@@ -15,7 +18,7 @@ task PeakCalling {
set -e -o pipefail
~{preCommand}
macs2 callpeak \
- --treatment ~{sep = ' ' bamFiles} \
+ --treatment ~{sep = ' ' inputBams} \
--outdir ~{outDir} \
--name ~{sampleName} \
~{true='--nomodel' false='' nomodel}
diff --git a/manta.wdl b/manta.wdl
index a5b024c55f8f864ea97774a82081c4e35e089df6..dea9937c1a2466e03be8dee2b333787f6f8ac63a 100644
--- a/manta.wdl
+++ b/manta.wdl
@@ -1,13 +1,12 @@
version 1.0
+import "common.wdl"
+
task ConfigureSomatic {
input {
- File tumorBam
- File tumorIndex
- File? normalBam
- File? normalIndex
- File refFasta
- File refFastaIndex
+ IndexedBamFile tumorBam
+ IndexedBamFile? normalBam
+ Reference reference
String runDir
File? callRegions
File? callRegionsIndex
@@ -20,13 +19,15 @@ task ConfigureSomatic {
then installDir + "bin/configMata.py"
else "configManta.py"
+ String normalArg = if (defined(normalBam)) then "--normalBam " + select_first([normalBam]).file else ""
+
command {
set -e -o pipefail
~{preCommand}
~{toolCommand} \
- ~{"--normalBam " + normalBam} \
- ~{"--tumorBam " + tumorBam} \
- --referenceFasta ~{refFasta} \
+ ~{normalArg} \
+ ~{"--tumorBam " + tumorBam.file} \
+ --referenceFasta ~{reference.fasta} \
~{"--callRegions " + callRegions} \
--runDir ~{runDir} \
~{true="--exome" false="" exome}
@@ -53,19 +54,27 @@ task RunSomatic {
}
output {
- File condidateSmallIndels = runDir + "/results/variants/candidateSmallIndels.vcf.gz"
- File condidateSmallIndelsIndex = runDir +
- "/results/variants/candidateSmallIndels.vcf.gz.tbi"
- File candidateSV = runDir + "/results/variants/candidateSV.vcf.gz"
- File candidateSVindex = runDir + "/results/variants/candidateSV.vcf.gz.tbi"
- File tumorSV = if paired
- then runDir + "/results/variants/somaticSV.vcf.gz"
- else runDir + "/results/variants/tumorSV.vcf.gz"
- File tumorSVindex = if paired
- then runDir + "/results/variants/somaticSV.vcf.gz.tbi"
- else runDir + "/results/variants/tumorSV.vcf.gz.tbi"
- File? diploidSV = "/results/variants/diploidSV.vcf.gz"
- File? diploidSVindex = "/results/variants/diploidSV.vcf.gz.tbi"
+ IndexedVcfFile condidateSmallIndels = object {
+ file: runDir + "/results/variants/candidateSmallIndels.vcf.gz",
+ index: runDir + "/results/variants/candidateSmallIndels.vcf.gz.tbi"
+ }
+ IndexedVcfFile candidateSV = object {
+ file: runDir + "/results/variants/candidateSV.vcf.gz",
+ index: runDir + "/results/variants/candidateSV.vcf.gz.tbi"
+ }
+ IndexedVcfFile tumorSV = if (paired)
+ then object {
+ file: runDir + "/results/variants/somaticSV.vcf.gz",
+ index: runDir + "/results/variants/somaticSV.vcf.gz.tbi"
+ }
+ else object {
+ file: runDir + "/results/variants/tumorSV.vcf.gz",
+ index: runDir + "/results/variants/tumorSV.vcf.gz.tbi"
+ }
+
+ #FIXME: workaround for https://github.com/broadinstitute/cromwell/issues/4111
+ File? diploidSV = runDir + "/results/variants/diploidSV.vcf.gz"
+ File? diploidSVindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
}
runtime {
diff --git a/picard.wdl b/picard.wdl
index f0175ac9839dae4d22b957e2e29312d131ffaccd..6a52ee4c53a62a5b3b48a5cd1ed41838c2dd4e28 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -1,5 +1,7 @@
version 1.0
+import "common.wdl"
+
task BedToIntervalList {
input {
String? preCommand
@@ -40,11 +42,8 @@ task BedToIntervalList {
task CollectMultipleMetrics {
input {
String? preCommand
- File bamFile
- File bamIndex
- File refFasta
- File refDict
- File refFastaIndex
+ IndexedBamFile bamFile
+ Reference reference
String basename
Boolean collectAlignmentSummaryMetrics = true
@@ -53,7 +52,7 @@ task CollectMultipleMetrics {
Boolean meanQualityByCycle = true
Boolean collectBaseDistributionByCycle = true
Boolean collectGcBiasMetrics = true
- #Boolean rnaSeqMetrics = false # There is a bug in picard https://github.com/broadinstitute/picard/issues/999
+ #FIXME: Boolean rnaSeqMetrics = false # There is a bug in picard https://github.com/broadinstitute/picard/issues/999
Boolean collectSequencingArtifactMetrics = true
Boolean collectQualityYieldMetrics = true
@@ -73,8 +72,8 @@ task CollectMultipleMetrics {
~{preCommand}
~{toolCommand} \
CollectMultipleMetrics \
- I=~{bamFile} \
- R=~{refFasta} \
+ I=~{bamFile.file} \
+ R=~{reference.fasta} \
O=~{basename} \
PROGRAM=null \
~{true="PROGRAM=CollectAlignmentSummaryMetrics" false="" collectAlignmentSummaryMetrics} \
@@ -117,8 +116,7 @@ task CollectMultipleMetrics {
task CollectRnaSeqMetrics {
input {
String? preCommand
- File bamFile
- File bamIndex
+ IndexedBamFile bamFile
File refRefflat
String basename
String strandSpecificity = "NONE"
@@ -139,7 +137,7 @@ task CollectRnaSeqMetrics {
~{preCommand}
~{toolCommand} \
CollectRnaSeqMetrics \
- I=~{bamFile} \
+ I=~{bamFile.file} \
O=~{basename}.RNA_Metrics \
CHART_OUTPUT=~{basename}.RNA_Metrics.pdf \
STRAND_SPECIFICITY=~{strandSpecificity} \
@@ -159,11 +157,8 @@ task CollectRnaSeqMetrics {
task CollectTargetedPcrMetrics {
input {
String? preCommand
- File bamFile
- File bamIndex
- File refFasta
- File refDict
- File refFastaIndex
+ IndexedBamFile bamFile
+ Reference reference
File ampliconIntervals
Array[File]+ targetIntervals
String basename
@@ -184,8 +179,8 @@ task CollectTargetedPcrMetrics {
~{preCommand}
~{toolCommand} \
CollectTargetedPcrMetrics \
- I=~{bamFile} \
- R=~{refFasta} \
+ I=~{bamFile.file} \
+ R=~{reference.fasta} \
AMPLICON_INTERVALS=~{ampliconIntervals} \
TARGET_INTERVALS=~{sep=" TARGET_INTERVALS=" targetIntervals} \
O=~{basename}.targetPcrMetrics \
@@ -208,9 +203,9 @@ task CollectTargetedPcrMetrics {
task GatherBamFiles {
input {
String? preCommand
- Array[File]+ input_bams
- String output_bam_path
- Int? compression_level
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
+ String outputBamPath
String? picardJar
Int memory = 4
@@ -226,16 +221,18 @@ task GatherBamFiles {
~{preCommand}
~{toolCommand} \
GatherBamFiles \
- INPUT=~{sep=' INPUT=' input_bams} \
- OUTPUT=~{output_bam_path} \
+ INPUT=~{sep=' INPUT=' inputBams} \
+ OUTPUT=~{outputBamPath} \
CREATE_INDEX=true \
CREATE_MD5_FILE=true
}
output {
- File output_bam = "~{output_bam_path}"
- File output_bam_index = sub(output_bam_path, ".bam$", ".bai")
- File output_bam_md5 = "~{output_bam_path}.md5"
+ IndexedBamFile outputBam = object {
+ file: outputBamPath,
+ index: sub(outputBamPath, ".bam$", ".bai"),
+ md5: outputBamPath + ".md5"
+ }
}
runtime {
@@ -247,10 +244,10 @@ task GatherBamFiles {
task MarkDuplicates {
input {
String? preCommand
- Array[File] input_bams
- String output_bam_path
- String metrics_path
- Int? compression_level
+ Array[File]+ inputBams
+ Array[File] inputBamIndexes
+ String outputBamPath
+ String metricsPath
String? picardJar
Int memory = 4
@@ -273,24 +270,28 @@ task MarkDuplicates {
command {
set -e -o pipefail
~{preCommand}
- mkdir -p $(dirname ~{output_bam_path})
+ mkdir -p $(dirname ~{outputBamPath})
~{toolCommand} \
MarkDuplicates \
- INPUT=~{sep=' INPUT=' input_bams} \
- OUTPUT=~{output_bam_path} \
- METRICS_FILE=~{metrics_path} \
+ INPUT=~{sep=' INPUT=' inputBams} \
+ OUTPUT=~{outputBamPath} \
+ METRICS_FILE=~{metricsPath} \
VALIDATION_STRINGENCY=SILENT \
~{"READ_NAME_REGEX=" + read_name_regex} \
OPTICAL_DUPLICATE_PIXEL_DISTANCE=2500 \
CLEAR_DT="false" \
CREATE_INDEX=true \
- ADD_PG_TAG_TO_READS=false
+ ADD_PG_TAG_TO_READS=false \
+ CREATE_MD5_FILE=true
}
output {
- File output_bam = output_bam_path
- File output_bam_index = sub(output_bam_path, ".bam$", ".bai")
- File duplicate_metrics = metrics_path
+ IndexedBamFile outputBam = object {
+ file: outputBamPath,
+ index: sub(outputBamPath, ".bam$", ".bai"),
+ md5: outputBamPath + ".md5"
+ }
+ File metricsFile = metricsPath
}
runtime {
@@ -304,7 +305,7 @@ task MergeVCFs {
String? preCommand
Array[File] inputVCFs
Array[File] inputVCFsIndexes
- String outputVCFpath
+ String outputVcfPath
Int? compressionLevel
String? picardJar
@@ -325,12 +326,14 @@ task MergeVCFs {
~{toolCommand} \
MergeVcfs \
INPUT=~{sep=' INPUT=' inputVCFs} \
- OUTPUT=~{outputVCFpath}
+ OUTPUT=~{outputVcfPath}
}
output {
- File outputVCF = outputVCFpath
- File outputVCFindex = outputVCFpath + ".tbi"
+ IndexedVcfFile outputVcf = object {
+ file: outputVcfPath,
+ index: outputVcfPath + ".tbi"
+ }
}
runtime {
@@ -341,7 +344,7 @@ task MergeVCFs {
task SamToFastq {
input {
String? preCommand
- File inputBam
+ IndexedBamFile inputBam
String outputRead1
String? outputRead2
String? outputUnpaired
@@ -360,7 +363,7 @@ task SamToFastq {
~{preCommand}
~{toolCommand} \
SamToFastq \
- I=~{inputBam} \
+ I=~{inputBam.file} \
~{"FASTQ=" + outputRead1} \
~{"SECOND_END_FASTQ=" + outputRead2} \
~{"UNPAIRED_FASTQ=" + outputUnpaired}
@@ -422,8 +425,8 @@ task SortVcf {
String? picardJar
Array[File]+ vcfFiles
- String outputVcf
- File? sequenceDict
+ String outputVcfPath
+ File? dict
Int memory = 4
Float memoryMultiplier = 3.0
@@ -439,13 +442,15 @@ task SortVcf {
~{toolCommand} \
SortVcf \
I=~{sep=" I=" vcfFiles} \
- ~{"SEQUENCE_DICTIONARY=" + sequenceDict} \
- O=~{outputVcf}
+ ~{"SEQUENCE_DICTIONARY=" + dict} \
+ O=~{outputVcfPath}
}
output {
- File vcfFile = outputVcf
- File vcfIndex = outputVcf + ".tbi"
+ IndexedVcfFile outputVcf = object {
+ file: outputVcfPath,
+ index: outputVcfPath + ".tbi"
+ }
}
runtime {
diff --git a/samtools.wdl b/samtools.wdl
index 58bdcfd85b61264990af124e847a76faceefffef..8bdf771209c658f69892d71c294194f1b27064ee 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -1,5 +1,7 @@
version 1.0
+import "common.wdl"
+
task BgzipAndIndex {
input {
File inputFile
@@ -23,20 +25,21 @@ task BgzipAndIndex {
task Index {
input {
String? preCommand
- File bamFilePath
- String? bamIndexPath
+ File bamFile
+ String bamIndexPath
}
command {
set -e -o pipefail
~{preCommand}
- samtools index ~{bamFilePath} ~{bamIndexPath}
+ samtools index ~{bamFile} ~{bamIndexPath}
}
output {
- File indexFile = if defined(bamIndexPath)
- then select_first([bamIndexPath])
- else bamFilePath + ".bai"
+ IndexedBamFile outputBam = object {
+ file: bamFile,
+ index: bamIndexPath
+ }
}
}
diff --git a/strelka.wdl b/strelka.wdl
index 959fabf8f5a4783986c9e9b56a4b20dd7963e4e4..c47345ed6c4b75991121f49155ce3369d99b23e8 100644
--- a/strelka.wdl
+++ b/strelka.wdl
@@ -1,5 +1,7 @@
version 1.0
+import "common.wdl" as common
+
task ConfigureGermline {
input {
String? preCommand
@@ -7,8 +9,7 @@ task ConfigureGermline {
String runDir
Array[File]+ bams
Array[File]+ indexes
- File refFasta
- File refFastaIndex
+ Reference reference
File? callRegions
File? callRegionsIndex
Boolean exome = false
@@ -24,7 +25,7 @@ task ConfigureGermline {
~{preCommand}
~{toolCommand} \
--bam ~{sep=" --bam " bams} \
- --ref ~{refFasta} \
+ --ref ~{reference.fasta} \
--runDir ~{runDir} \
~{"--callRegions " + callRegions} \
~{true="--exome" false="" exome} \
@@ -41,16 +42,12 @@ task ConfigureSomatic {
String? preCommand
String? installDir
String runDir
- File normalBam
- File normalIndex
- File tumorBam
- File tumorIndex
- File refFasta
- File refFastaIndex
+ IndexedBamFile normalBam
+ IndexedBamFile tumorBam
+ Reference reference
File? callRegions
File? callRegionsIndex
- File? indelCandidates
- File? indelCandidatesIndex
+ IndexedVcfFile? indelCandidates
Boolean exome = false
}
@@ -58,16 +55,18 @@ task ConfigureSomatic {
then installDir + "bin/configureStrelkaSomaticWorkflow.py"
else "configureStrelkaSomaticWorkflow.py"
+ String indelCandidatesArg = if (defined(indelCandidates)) then "--indelCandidates " + select_first([indelCandidates]).file else ""
+
command {
set -e -o pipefail
~{preCommand}
~{toolCommand} \
- --normalBam ~{normalBam} \
- --tumorBam ~{tumorBam} \
- --ref ~{refFasta} \
+ --normalBam ~{normalBam.file} \
+ --tumorBam ~{tumorBam.file} \
+ --ref ~{reference.fasta} \
--runDir ~{runDir} \
~{"--callRegions " + callRegions} \
- ~{"--indelCandidates " + indelCandidates} \
+ ~{indelCandidatesArg} \
~{true="--exome" false="" exome} \
}
@@ -82,6 +81,7 @@ task Run {
Int cores = 1
Int memory = 4
Boolean somatic = true
+ #FIXME: This task does not have input files
}
command {
diff --git a/stringtie.wdl b/stringtie.wdl
index 97455da498f722ddf05008fc7102c9eef360335e..b26109d1b18980b902d552baefc06aadc3345b86 100644
--- a/stringtie.wdl
+++ b/stringtie.wdl
@@ -1,9 +1,11 @@
version 1.0
+import "common.wdl"
+
task Stringtie {
input {
String? preCommand
- File alignedReads
+ IndexedBamFile bamFile
File? referenceGtf
Int threads = 1
String assembledTranscriptsFile
@@ -23,7 +25,7 @@ task Stringtie {
~{true="fr" false="" secondStranded} \
-o ~{assembledTranscriptsFile} \
~{"-A " + geneAbundanceFile} \
- ~{alignedReads}
+ ~{bamFile.file}
}
output {
diff --git a/vardict.wdl b/vardict.wdl
index c79a768ffc1fc0a72c9c8506e20338a952a91d4d..989fc25417e2a77601dbeb18a06d6480d6b486b2 100644
--- a/vardict.wdl
+++ b/vardict.wdl
@@ -1,18 +1,17 @@
version 1.0
+import "common.wdl"
+
task VarDict {
input {
String? installDir
Boolean useJavaVersion = true
String tumorSampleName
- File tumorBam
- File tumorIndex
+ IndexedBamFile tumorBam
String? normalSampleName
- File? normalBam
- File? normalIndex
- File refFasta
- File refFastaIndex
+ IndexedBamFile? normalBam
+ Reference reference
File bedFile
String outputVcf
@@ -26,6 +25,8 @@ task VarDict {
Float memoryMultiplier = 2.0
}
+ String normalArg = if (defined(normalBam)) then "|" + select_first([normalBam]).file else ""
+
String toolCommand = if defined(installDir)
then installDir + "/VarDict"
else if useJavaVersion
@@ -37,9 +38,9 @@ task VarDict {
export JAVA_OPTS="-Xmx~{memory}G"
~{preCommand}
~{toolCommand} \
- -G ~{refFasta} \
+ -G ~{reference.fasta} \
-N ~{tumorSampleName} \
- -b "~{tumorBam}~{"|" + normalBam}" \
+ -b "~{tumorBam.file}~{normalArg}" \
~{true="" false="-z" defined(normalBam)} \
-c ~{chromosomeColumn} \
-S ~{startColumn} \
@@ -52,10 +53,14 @@ task VarDict {
-N "~{tumorSampleName}~{"|" + normalSampleName}" \
~{true="" false="-E" defined(normalBam)} | \
bgzip -c > ~{outputVcf}
+ tabix -p vcf ~{outputVcf}
}
output {
- File vcfFile = outputVcf
+ IndexedVcfFile vcfFile = object {
+ file: outputVcf,
+ index: outputVcf + ".tbi"
+ }
}
runtime {