diff --git a/.gitignore b/.gitignore
index 9f11b755a17d8192c60f61cb17b8902dffbd9f23..d392f0e82c4ac6dd2e7bb17eb9253e1b30d07105 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1 @@
-.idea/
+*.jar
diff --git a/.travis.yml b/.travis.yml
index b730aaa8e7c65116da7c03734e802a2d8b455aa9..cb8b70de06b9c35f8d7759b565eb621c435549ca 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,5 +1,6 @@
language: java
script:
- set -e
- - wget https://github.com/broadinstitute/cromwell/releases/download/31/womtool-31.jar
- - for F in `find -name "*.wdl"`; do echo $F; java -jar womtool-31.jar validate $F; done
+ - export CROMWELL_VERSION=34
+ - wget https://github.com/broadinstitute/cromwell/releases/download/$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
diff --git a/bioconda.wdl b/bioconda.wdl
index 0600ff72d79dc27065fbdb7b6e4db1950e37e710..0a513ddc5df99f1354cfd8a4db8aad75d8ef7428 100644
--- a/bioconda.wdl
+++ b/bioconda.wdl
@@ -1,13 +1,17 @@
+version 1.0
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 2017
# Bioconda installs
task installPrefix {
- Array[String] requirements
- String prefix
- String? condaPath
- command {
- ${default="conda" condaPath} create \
+ input {
+ Array[String] requirements
+ String prefix
+ String condaPath = "conda"
+ }
+
+ command <<<
+ ~{condaPath} create \
--json -q \
--yes \
--override-channels \
@@ -16,8 +20,9 @@ task installPrefix {
--channel defaults \
--channel r \
--prefix ${prefix} \
- ${sep=' ' requirements}
- }
+ ~{sep=' ' requirements}
+ >>>
+
output {
File condaEnvPath=prefix
File condaJson=stdout()
diff --git a/biopet.wdl b/biopet.wdl
index d076fc2a1c8c271fa1847ab7f3721b03f2a5ee7f..36d6f2a9cd7b4b4bf633a063ff2220c2cee70995 100644
--- a/biopet.wdl
+++ b/biopet.wdl
@@ -1,32 +1,32 @@
-# PLEASE ADD TASKS IN ALPHABETIC ORDER.
-# This makes searching a lot easier.
+version 1.0
task BaseCounter {
- String? preCommand
- File? toolJar
- File bam
- File bamIndex
- File refFlat
- String outputDir
- String prefix
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File? toolJar
+ File bam
+ File bamIndex
+ File refFlat
+ String outputDir
+ String prefix
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " +toolJar
- else "biopet-basecounter -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-basecounter -Xmx" + memory + "G"
command {
set -e -o pipefail
- mkdir -p ${outputDir}
- ${preCommand}
- ${toolCommand} \
- -b ${bam} \
- -r ${refFlat} \
- -o ${outputDir} \
- -p ${prefix}
+ mkdir -p ~{outputDir}
+ ~{preCommand}
+ ~{toolCommand} \
+ -b ~{bam} \
+ -r ~{refFlat} \
+ -o ~{outputDir} \
+ -p ~{prefix}
}
output {
@@ -67,83 +67,84 @@ task BaseCounter {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task ExtractAdaptersFastqc {
- File? toolJar
- String? preCommand
- File inputFile
- String outputDir
- String? adapterOutputFilePath = outputDir + "/adapter.list"
- String? contamsOutputFilePath = outputDir + "/contaminations.list"
- Boolean? skipContams
- File? knownContamFile
- File? knownAdapterFile
- Float? adapterCutoff
- Boolean? outputAsFasta
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ File? toolJar
+ String? preCommand
+ File inputFile
+ String outputDir
+ String adapterOutputFilePath = outputDir + "/adapter.list"
+ String contamsOutputFilePath = outputDir + "/contaminations.list"
+ Boolean? skipContams
+ File? knownContamFile
+ File? knownAdapterFile
+ Float? adapterCutoff
+ Boolean? outputAsFasta
+
+ Int memory = 4
+ Float memoryMultiplier = 2.5
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " +toolJar
- else "biopet-extractadaptersfastqc -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-extractadaptersfastqc -Xmx" + memory + "G"
command {
- set -e
- ${preCommand}
- mkdir -p ${outputDir}
- ${toolCommand} \
- --inputFile ${inputFile} \
- ${"--adapterOutputFile " + adapterOutputFilePath } \
- ${"--contamsOutputFile " + contamsOutputFilePath } \
- ${"--knownContamFile " + knownContamFile} \
- ${"--knownAdapterFile " + knownAdapterFile} \
- ${"--adapterCutoff " + adapterCutoff} \
- ${true="--skipContams" false="" skipContams} \
- ${true="--outputAsFasta" false="" outputAsFasta}
+ set -e
+ ~{preCommand}
+ mkdir -p ~{outputDir}
+ ~{toolCommand} \
+ --inputFile ~{inputFile} \
+ ~{"--adapterOutputFile " + adapterOutputFilePath } \
+ ~{"--contamsOutputFile " + contamsOutputFilePath } \
+ ~{"--knownContamFile " + knownContamFile} \
+ ~{"--knownAdapterFile " + knownAdapterFile} \
+ ~{"--adapterCutoff " + adapterCutoff} \
+ ~{true="--skipContams" false="" skipContams} \
+ ~{true="--outputAsFasta" false="" outputAsFasta}
}
output {
- File adapterOutputFile = select_first([adapterOutputFilePath])
- File contamsOutputFile = select_first([contamsOutputFilePath])
- Array[String] adapterList = read_lines(select_first([adapterOutputFilePath]))
- Array[String] contamsList = read_lines(select_first([contamsOutputFilePath]))
+ File adapterOutputFile = adapterOutputFilePath
+ File contamsOutputFile = contamsOutputFilePath
+ Array[String] adapterList = read_lines(adapterOutputFilePath)
+ Array[String] contamsList = read_lines(contamsOutputFilePath)
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.5]))
+ memory: ceil(memory * memoryMultiplier)
}
}
-
task FastqSplitter {
- String? preCommand
- File inputFastq
- Array[String] outputPaths
- File? toolJar
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File inputFastq
+ Array[String]+ outputPaths
+ File? toolJar
+
+ Int memory = 4
+ Float memoryMultiplier = 2.5
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " +toolJar
- else "biopet-fastqsplitter -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-fastqsplitter -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- mkdir -p $(dirname ${sep=') $(dirname ' outputPaths})
- if [ ${length(outputPaths)} -gt 1 ]; then
- ${toolCommand} \
- -I ${inputFastq} \
- -o ${sep=' -o ' outputPaths}
+ ~{preCommand}
+ mkdir -p $(dirname ~{sep=') $(dirname ' outputPaths})
+ if [ ~{length(outputPaths)} -gt 1 ]; then
+ ~{toolCommand} \
+ -I ~{inputFastq} \
+ -o ~{sep=' -o ' outputPaths}
else
- ln -sf ${inputFastq} ${outputPaths[0]}
+ ln -sf ~{inputFastq} ~{outputPaths[0]}
fi
}
@@ -152,39 +153,40 @@ task FastqSplitter {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.5]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task FastqSync {
- String? preCommand
- File ref1
- File ref2
- File in1
- File in2
- String out1path
- String out2path
- File? toolJar
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File ref1
+ File ref2
+ File in1
+ File in2
+ String out1path
+ String out2path
+ File? toolJar
+
+ Int memory = 4
+ Float memoryMultiplier = 2.5
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " +toolJar
- else "biopet-fastqsync -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-fastqsync -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- mkdir -p $(dirname ${out1path}) $(dirname ${out2path})
- ${toolCommand} \
- --in1 ${in1} \
- --in2 ${in2} \
- --ref1 ${ref1} \
- --ref2 ${ref2} \
- --out1 ${out1path} \
- --out2 ${out2path}
+ ~{preCommand}
+ mkdir -p $(dirname ~{out1path}) $(dirname ~{out2path})
+ ~{toolCommand} \
+ --in1 ~{in1} \
+ --in2 ~{in2} \
+ --ref1 ~{ref1} \
+ --ref2 ~{ref2} \
+ --out1 ~{out1path} \
+ --out2 ~{out2path}
}
output {
@@ -193,41 +195,42 @@ task FastqSync {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.5]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task SampleConfig {
- File? toolJar
- String? preCommand
- Array[File]+ inputFiles
- String keyFilePath
- String? sample
- String? library
- String? readgroup
- String? jsonOutputPath
- String? tsvOutputPath
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ 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" + mem + "G -jar " +toolJar
- else "biopet-sampleconfig -Xmx" + mem + "G"
+ 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} \
- > ${keyFilePath}
+ ~{preCommand}
+ mkdir -p . ~{"$(dirname " + jsonOutputPath + ")"} ~{"$(dirname " + tsvOutputPath + ")"}
+ ~{toolCommand} \
+ -i ~{sep="-i " inputFiles} \
+ ~{"--sample " + sample} \
+ ~{"--library " + library} \
+ ~{"--readgroup " + readgroup} \
+ ~{"--jsonOutput " + jsonOutputPath} \
+ ~{"--tsvOutput " + tsvOutputPath} \
+ > ~{keyFilePath}
}
output {
@@ -237,36 +240,37 @@ task SampleConfig {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task ScatterRegions {
- String? preCommand
- File refFasta
- File refDict
- String outputDirPath
- File? toolJar
- Int? scatterSize
- File? regions
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File refFasta
+ File refDict
+ String outputDirPath
+ File? toolJar
+ Int? scatterSize
+ File? regions
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " +toolJar
- else "biopet-scatterregions -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " +toolJar
+ else "biopet-scatterregions -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- mkdir -p ${outputDirPath}
- ${toolCommand} \
- -R ${refFasta} \
- -o ${outputDirPath} \
- ${"-s " + scatterSize} \
- ${"-L " + regions}
+ ~{preCommand}
+ mkdir -p ~{outputDirPath}
+ ~{toolCommand} \
+ -R ~{refFasta} \
+ -o ~{outputDirPath} \
+ ~{"-s " + scatterSize} \
+ ~{"-L " + regions}
}
output {
@@ -274,65 +278,142 @@ task ScatterRegions {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task Seqstat {
- String? preCommand
- File? toolJar
- File fastq
- String outputFile
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File? toolJar
+ File fastq
+ String outputFile
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " + toolJar
- else "biopet-seqstat -Xmx" + mem + "G"
+ 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}
+ ~{preCommand}
+ mkdir -p $(dirname ~{outputFile})
+ ~{toolCommand} \
+ --fastq ~{fastq} \
+ --output ~{outputFile}
}
+
output {
File json = outputFile
}
+
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
-task ValidateFastq {
- String? preCommand
- File? toolJar
- File fastq1
- File? fastq2
+task ValidateAnnotation {
+ input {
+ String? preCommand
+ File? toolJar
+ File? refRefflat
+ File? gtfFile
+ File refFasta
+ File refFastaIndex
+ File refDict
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
+
+ String toolCommand = if defined(toolJar)
+ then "java -Xmx" + memory + "G -jar " + toolJar
+ else "biopet-validateannotation -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ ~{toolCommand} \
+ ~{"-r " + refRefflat} \
+ ~{"-g " + gtfFile} \
+ -R ~{refFasta}
+ }
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ output {
+ File stderr = stderr()
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
+
+task ValidateFastq {
+ input {
+ String? preCommand
+ File? toolJar
+ File fastq1
+ File? fastq2
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
String toolCommand = if defined(toolJar)
- then "java -Xmx" + mem + "G -jar " + toolJar
- else "biopet-validatefastq -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + toolJar
+ else "biopet-validatefastq -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- biopet-validatefastq \
- --fastq1 ${fastq1} \
- ${"--fastq2 " + fastq2}
+ ~{preCommand}
+ ~{toolCommand} \
+ --fastq1 ~{fastq1} \
+ ~{"--fastq2 " + fastq2}
}
+
output {
File stderr = stderr()
}
+
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
+task ValidateVcf {
+ input {
+ String? preCommand
+ File? toolJar
+ File vcfFile
+ File vcfIndex
+ File refFasta
+ File refFastaIndex
+ File refDict
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
+
+ String toolCommand = if defined(toolJar)
+ then "java -Xmx" + memory + "G -jar " + toolJar
+ else "biopet-validatevcf -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ ~{toolCommand} \
+ -i ~{vcfFile} \
+ -R ~{refFasta}
+ }
+
+ output {
+ File stderr = stderr()
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
diff --git a/bwa.wdl b/bwa.wdl
index 440b6559b2fcceaa0efaebfdeddd35b46da07d5a..01d1b7d08b798083d0bb7dbf6fd74ce4ebe64a14 100644
--- a/bwa.wdl
+++ b/bwa.wdl
@@ -1,61 +1,72 @@
-task mem {
- String? preCommand
- File inputR1
- File? inputR2
- File referenceFasta
- Array[File] indexFiles # These indexFiles need to be added, otherwise cromwell will not find them.
- String outputPath
- String? readgroup
+version 1.0
- Int? threads
- Int? memory
+task Mem {
+ input {
+ String? preCommand
+ File inputR1
+ File? inputR2
+ File referenceFasta
+ Array[File] indexFiles # These indexFiles need to be added, otherwise cromwell will not find them.
+ String outputPath
+ String? readgroup
+ Int threads = 1
+ Int memory = 8
+ }
command {
set -e -o pipefail
- mkdir -p $(dirname ${outputPath})
- ${preCommand}
- bwa mem ${"-t " + threads} \
- ${"-R '" + readgroup + "'"} \
- ${referenceFasta} ${inputR1} ${inputR2} | samtools sort --output-fmt BAM - > ${outputPath}
+ mkdir -p $(dirname ~{outputPath})
+ ~{preCommand}
+ bwa mem ~{"-t " + threads} \
+ ~{"-R '" + readgroup + "'"} \
+ ~{referenceFasta} \
+ ~{inputR1} \
+ ~{inputR2} \
+ | samtools sort --output-fmt BAM - > ~{outputPath}
}
output {
File bamFile = outputPath
}
+
runtime{
- cpu: select_first([threads,1])
- memory: select_first([memory,8])
+ cpu: threads
+ memory: memory
}
}
-task index {
- File fasta
- String? preCommand
- String? constructionAlgorithm
- Int? blockSize
- String? outputDir
+task Index {
+ input {
+ File fasta
+ String? preCommand
+ String? constructionAlgorithm
+ Int? blockSize
+ String? outputDir
+ }
+
String fastaFilename = basename(fasta)
String outputFile = if (defined(outputDir)) then outputDir + "/" + fastaFilename else fasta
command {
set -e -o pipefail
- ${"mkdir -p " + outputDir}
- ${preCommand}
- if [[ ! '${outputDir}' = '' ]]
+ ~{"mkdir -p " + outputDir}
+ ~{preCommand}
+ if [[ ! '~{outputDir}' = '' ]]
then
- ln -sf ${fasta} ${outputDir + "/"}${fastaFilename}
+ ln -sf ~{fasta} ~{outputDir + "/"}~{fastaFilename}
fi
bwa index \
- ${"-a " + constructionAlgorithm} \
- ${"-b" + blockSize} \
- ${outputFile}
+ ~{"-a " + constructionAlgorithm} \
+ ~{"-b" + blockSize} \
+ ~{outputFile}
}
output {
File indexedFasta = outputFile
Array[File] indexFiles = [outputFile + ".bwt",outputFile + ".pac",outputFile + ".sa",outputFile + ".amb",outputFile + ".ann"]
}
+
parameter_meta {
fasta: "Fasta file to be indexed"
constructionAlgorithm: "-a STR BWT construction algorithm: bwtsw, is or rb2 [auto]"
diff --git a/centrifuge.wdl b/centrifuge.wdl
index f466fe3b53c380077fb61cccc12354c2b0cc06a5..4b128c33627eb4eec4facb184c4e49a321d4b4a7 100644
--- a/centrifuge.wdl
+++ b/centrifuge.wdl
@@ -1,105 +1,114 @@
+version 1.0
+
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 2018
#
# Tasks from centrifuge
task Build {
- File conversionTable
- File taxonomyTree
- File inputFasta
- String centrifugeIndexBase
- String? preCommand
- String? centrifugeBuildExecutable = "centrifuge-build"
- #Boolean? c = false
- Boolean? largeIndex = false
- Boolean? noAuto = false
- Int? bMax
- Int? bMaxDivn
- Boolean? noDiffCover = false
- Boolean? noRef = false
- Boolean? justRef = false
- Int? offRate
- Int? fTabChars
- File? nameTable
- File? sizeTable
- Int? seed
- Int? kmerCount
-
- Int? threads
- Int? memory
+ input {
+ File conversionTable
+ File taxonomyTree
+ File inputFasta
+ String centrifugeIndexBase
+ String? preCommand
+ String centrifugeBuildExecutable = "centrifuge-build"
+ #Boolean? c = false
+ Boolean largeIndex = false
+ Boolean noAuto = false
+ Int? bMax
+ Int? bMaxDivn
+ Boolean noDiffCover = false
+ Boolean noRef = false
+ Boolean justRef = false
+ Int? offRate
+ Int? fTabChars
+ File? nameTable
+ File? sizeTable
+ Int? seed
+ Int? kmerCount
+
+ Int threads = 8
+ Int memory = 20
+ }
command {
set -e -o pipefail
- ${preCommand}
- ${"mkdir -p $(dirname " + centrifugeIndexBase + ")"}
- ${centrifugeBuildExecutable} \
- ${true='--large-index' false='' largeIndex} \
- ${true='--noauto' false='' noAuto} \
- ${'--bmax ' + bMax} \
- ${'--bmaxdivn ' + bMaxDivn} \
- ${true='--nodc' false='' noDiffCover} \
- ${true='--noref' false='' noRef} \
- ${true='--justref' false='' justRef} \
- ${'--offrate ' + offRate} \
- ${'--ftabchars ' + fTabChars} \
- ${'--name-table ' + nameTable } \
- ${'--size-table ' + sizeTable} \
- ${'--seed ' + seed} \
- ${'--kmer-count' + kmerCount} \
- ${'--threads ' + threads} \
- --conversion-table ${conversionTable} \
- --taxonomy-tree ${taxonomyTree} \
- ${inputFasta} \
- ${centrifugeIndexBase}
+ ~{preCommand}
+ ~{"mkdir -p $(dirname " + centrifugeIndexBase + ")"}
+ ~{centrifugeBuildExecutable} \
+ ~{true='--large-index' false='' largeIndex} \
+ ~{true='--noauto' false='' noAuto} \
+ ~{'--bmax ' + bMax} \
+ ~{'--bmaxdivn ' + bMaxDivn} \
+ ~{true='--nodc' false='' noDiffCover} \
+ ~{true='--noref' false='' noRef} \
+ ~{true='--justref' false='' justRef} \
+ ~{'--offrate ' + offRate} \
+ ~{'--ftabchars ' + fTabChars} \
+ ~{'--name-table ' + nameTable } \
+ ~{'--size-table ' + sizeTable} \
+ ~{'--seed ' + seed} \
+ ~{'--kmer-count' + kmerCount} \
+ ~{'--threads ' + threads} \
+ --conversion-table ~{conversionTable} \
+ --taxonomy-tree ~{taxonomyTree} \
+ ~{inputFasta} \
+ ~{centrifugeIndexBase}
}
+
runtime {
- cpu: select_first([threads, 8])
- memory: select_first([memory, 20])
+ cpu: threads
+ memory: memory
}
}
task Classify {
- String outputDir
- Boolean? compressOutput = true
- String? preCommand
- String indexPrefix
- Array[File]? unpairedReads
- Array[File]+ read1
- Array[File]? read2
- Boolean? fastaInput
- # Variables for handling output
+ input {
+ String outputDir
+ Boolean compressOutput = true
+ String? preCommand
+ String indexPrefix
+ Array[File]? unpairedReads
+ Array[File]+ read1
+ Array[File]? read2
+ Boolean? fastaInput
+ # Variables for handling output
+
+ String? metFilePath # If this is specified, the report file is empty
+ Int? assignments
+ Int? minHitLen
+ Int? minTotalLen
+ Array[String]? hostTaxIds
+ Array[String]? excludeTaxIds
+
+ Int threads = 4
+ Int memory = 8
+ }
+
String outputFilePath = outputDir + "/centrifuge.out"
String reportFilePath = outputDir + "/centrifuge_report.tsv"
String finalOutputPath = if (compressOutput == true)
then outputFilePath + ".gz"
else outputFilePath
- String? metFilePath # If this is specified, the report file is empty
- Int? assignments
- Int? minHitLen
- Int? minTotalLen
- Array[String]? hostTaxIds
- Array[String]? excludeTaxIds
-
- Int? threads
- Int? memory
command {
set -e -o pipefail
- mkdir -p ${outputDir}
- ${preCommand}
+ mkdir -p ~{outputDir}
+ ~{preCommand}
centrifuge \
- ${"-p " + select_first([threads, 4])} \
- ${"-x " + indexPrefix} \
- ${true="-f" false="" fastaInput} \
- ${true="-k" false="" defined(assignments)} ${assignments} \
- ${true="-1" false="-U" defined(read2)} ${sep=',' read1} \
- ${true="-2" false="" defined(read2)} ${sep=',' read2} \
- ${true="-U" false="" defined(unpairedReads)} ${sep=',' unpairedReads} \
- ${"--report-file " + reportFilePath} \
- ${"--min-hitlen " + minHitLen} \
- ${"--min-totallen " + minTotalLen} \
- ${"--met-file " + metFilePath} \
- ${true="--host-taxids " false="" defined(hostTaxIds)} ${sep=',' hostTaxIds} \
- ${true="--exclude-taxids " false="" defined(excludeTaxIds)} ${sep=',' excludeTaxIds} \
- ${true="| gzip -c >" false="-S" compressOutput} ${finalOutputPath}
+ ~{"-p " + threads} \
+ ~{"-x " + indexPrefix} \
+ ~{true="-f" false="" fastaInput} \
+ ~{true="-k" false="" defined(assignments)} ~{assignments} \
+ ~{true="-1" false="-U" defined(read2)} ~{sep=',' read1} \
+ ~{true="-2" false="" defined(read2)} ~{sep=',' read2} \
+ ~{true="-U" false="" defined(unpairedReads)} ~{sep=',' unpairedReads} \
+ ~{"--report-file " + reportFilePath} \
+ ~{"--min-hitlen " + minHitLen} \
+ ~{"--min-totallen " + minTotalLen} \
+ ~{"--met-file " + metFilePath} \
+ ~{true="--host-taxids " false="" defined(hostTaxIds)} ~{sep=',' hostTaxIds} \
+ ~{true="--exclude-taxids " false="" defined(excludeTaxIds)} ~{sep=',' excludeTaxIds} \
+ ~{true="| gzip -c >" false="-S" compressOutput} ~{finalOutputPath}
}
output {
@@ -108,64 +117,68 @@ task Classify {
}
runtime {
- cpu: select_first([threads, 4])
- memory: select_first([memory, 8])
+ cpu: threads
+ memory: memory
}
}
task Download {
- String libraryPath
- Array[String]? domain
- String? executable = "centrifuge-download"
- String? preCommand
- String? seqTaxMapPath
- String? database = "refseq"
- String? assemblyLevel
- String? refseqCategory
- Array[String]? taxIds
- Boolean? filterUnplaced = false
- Boolean? maskLowComplexRegions = false
- Boolean? downloadRnaSeqs = false
- Boolean? modifyHeader = false
- Boolean? downloadGiMap = false
+ input {
+ String libraryPath
+ Array[String]? domain
+ String executable = "centrifuge-download"
+ String? preCommand
+ String? seqTaxMapPath
+ String database = "refseq"
+ String? assemblyLevel
+ String? refseqCategory
+ Array[String]? taxIds
+ Boolean filterUnplaced = false
+ Boolean maskLowComplexRegions = false
+ Boolean downloadRnaSeqs = false
+ Boolean modifyHeader = false
+ Boolean downloadGiMap = false
+ }
# This will use centrifuge-download to download.
# The bash statement at the beginning is to make sure
# the directory for the SeqTaxMapPath exists.
command {
set -e -o pipefail
- ${preCommand}
- ${"mkdir -p $(dirname " + seqTaxMapPath + ")"}
- ${executable} \
- -o ${libraryPath} \
- ${true='-d ' false='' defined(domain)}${sep=',' domain} \
- ${'-a "' + assemblyLevel + '"'} \
- ${"-c " + refseqCategory} \
- ${true='-t' false='' defined(taxIds)} '${sep=',' taxIds}' \
- ${true='-r' false='' downloadRnaSeqs} \
- ${true='-u' false='' filterUnplaced} \
- ${true='-m' false='' maskLowComplexRegions} \
- ${true='-l' false='' modifyHeader} \
- ${true='-g' false='' downloadGiMap} \
- ${database} ${">> " + seqTaxMapPath}
+ ~{preCommand}
+ ~{"mkdir -p $(dirname " + seqTaxMapPath + ")"}
+ ~{executable} \
+ -o ~{libraryPath} \
+ ~{true='-d ' false='' defined(domain)}~{sep=',' domain} \
+ ~{'-a "' + assemblyLevel + '"'} \
+ ~{"-c " + refseqCategory} \
+ ~{true='-t' false='' defined(taxIds)} '~{sep=',' taxIds}' \
+ ~{true='-r' false='' downloadRnaSeqs} \
+ ~{true='-u' false='' filterUnplaced} \
+ ~{true='-m' false='' maskLowComplexRegions} \
+ ~{true='-l' false='' modifyHeader} \
+ ~{true='-g' false='' downloadGiMap} \
+ ~{database} ~{">> " + seqTaxMapPath}
}
+
output {
- File seqTaxMap = "${seqTaxMapPath}"
+ File seqTaxMap = "~{seqTaxMapPath}"
File library = libraryPath
Array[File] fastaFiles = glob(libraryPath + "/*/*.fna")
}
}
task DownloadTaxonomy {
- String centrifugeTaxonomyDir
- String? executable = "centrifuge-download"
- String? preCommand
-
+ input {
+ String centrifugeTaxonomyDir
+ String executable = "centrifuge-download"
+ String? preCommand
+ }
command {
set -e -o pipefail
- ${preCommand}
- ${executable} \
- -o ${centrifugeTaxonomyDir} \
+ ~{preCommand}
+ ~{executable} \
+ -o ~{centrifugeTaxonomyDir} \
taxonomy
}
@@ -176,36 +189,38 @@ task DownloadTaxonomy {
}
task Kreport {
- String? preCommand
- File centrifugeOut
- Boolean inputIsCompressed
- String outputDir
- String? suffix = "kreport"
- String? prefix = "centrifuge"
- String kreportFilePath = outputDir + "/" + prefix + "." + suffix
- String indexPrefix
- Boolean? onlyUnique
- Boolean? showZeros
- Boolean? isCountTable
- Int? minScore
- Int? minLength
-
- Int? cores
- Int? memory
+ input {
+ String? preCommand
+ File centrifugeOut
+ Boolean inputIsCompressed
+ String outputDir
+ String suffix = "kreport"
+ String prefix = "centrifuge"
+ String indexPrefix
+ Boolean? onlyUnique
+ Boolean? showZeros
+ Boolean? isCountTable
+ Int? minScore
+ Int? minLength
+
+ Int cores = 1
+ Int memory = 4
+ }
+ String kreportFilePath = outputDir + "/" + prefix + "." + suffix
command {
set -e -o pipefail
- ${preCommand}
+ ~{preCommand}
centrifuge-kreport \
- -x ${indexPrefix} \
- ${true="--only-unique" false="" onlyUnique} \
- ${true="--show-zeros" false="" showZeros} \
- ${true="--is-count-table" false="" isCountTable} \
- ${"--min-score " + minScore} \
- ${"--min-length " + minLength} \
- ${true="<(zcat" false="" inputIsCompressed} ${centrifugeOut}\
- ${true=")" false="" inputIsCompressed} \
- > ${kreportFilePath}
+ -x ~{indexPrefix} \
+ ~{true="--only-unique" false="" onlyUnique} \
+ ~{true="--show-zeros" false="" showZeros} \
+ ~{true="--is-count-table" false="" isCountTable} \
+ ~{"--min-score " + minScore} \
+ ~{"--min-length " + minLength} \
+ ~{true="<(zcat" false="" inputIsCompressed} ~{centrifugeOut}\
+ ~{true=")" false="" inputIsCompressed} \
+ > ~{kreportFilePath}
}
output {
@@ -213,7 +228,7 @@ task Kreport {
}
runtime {
- cpu: select_first([cores, 1])
- memory: select_first([memory, 4])
+ cpu: cores
+ memory: memory
}
}
diff --git a/common.wdl b/common.wdl
index d80d47e6d5a964b4ba2637741eeb62b51cecc2f2..15e99f5804089fdd328f263b21804dc18712e752 100644
--- a/common.wdl
+++ b/common.wdl
@@ -1,12 +1,18 @@
-task objectMd5 {
- Object the_object
+version 1.0
+
+task AppendToStringArray {
+ input {
+ Array[String] array
+ String string
+ }
command {
- cat ${write_object(the_object)} | md5sum - | sed -e 's/ -//'
+ echo "~{sep='\n' array}
+ ~{string}"
}
output {
- String md5sum = read_string(stdout())
+ Array[String] outArray = read_lines(stdout())
}
runtime {
@@ -14,32 +20,37 @@ task objectMd5 {
}
}
-task mapMd5 {
- Map[String,String] map
-
- command {
- cat ${write_map(map)} | md5sum - | sed -e 's/ -//'
- }
-
- output {
- String md5sum = read_string(stdout())
+# This task will fail if the MD5sum doesn't match the file.
+task CheckFileMD5 {
+ input {
+ File file
+ String MD5sum
}
- runtime {
- memory: 1
+ command {
+ set -e -o pipefail
+ MD5SUM=$(md5sum ~{file} | cut -d ' ' -f 1)
+ [ $MD5SUM = ~{MD5sum} ]
}
}
-task stringArrayMd5 {
- Array[String] stringArray
+task ConcatenateTextFiles {
+ input {
+ Array[File] fileList
+ String combinedFilePath
+ Boolean unzip = false
+ Boolean zip = false
+ }
command {
- set -eu -o pipefail
- echo ${sep=',' stringArray} | md5sum - | sed -e 's/ -//'
+ set -e -o pipefail
+ ~{"mkdir -p $(dirname " + combinedFilePath + ")"}
+ ~{true='zcat' false= 'cat' unzip} ~{sep=' ' fileList} \
+ ~{true="| gzip -c" false="" zip} > ~{combinedFilePath}
}
output {
- String md5sum = read_string(stdout())
+ File combinedFile = combinedFilePath
}
runtime {
@@ -47,39 +58,38 @@ task stringArrayMd5 {
}
}
-task concatenateTextFiles {
- Array[File] fileList
- String combinedFilePath
- Boolean? unzip=false
- Boolean? zip=false
+task CreateLink {
+ # Making this of type File will create a link to the copy of the file in the execution
+ # folder, instead of the actual file.
+ input {
+ String inputFile
+ String outputPath
+ }
command {
- set -e -o pipefail
- ${"mkdir -p $(dirname " + combinedFilePath + ")"}
- ${true='zcat' false= 'cat' unzip} ${sep=' ' fileList} \
- ${true="| gzip -c" false="" zip} > ${combinedFilePath}
+ ln -sf ~{inputFile} ~{outputPath}
}
output {
- File combinedFile = combinedFilePath
- }
-
- runtime {
- memory: 1
+ File link = outputPath
}
}
-# inspired by https://gatkforums.broadinstitute.org/wdl/discussion/9616/is-there-a-way-to-flatten-arrays
-task flattenStringArray {
- Array[Array[String]] arrayList
+# DEPRECATED. USE BUILT-IN FLATTEN FUNCTION
+# task FlattenStringArray {}
+# Commented out to let pipelines that depend on this fail.
+
+task MapMd5 {
+ input {
+ Map[String,String] map
+ }
command {
- for line in $(echo ${sep=', ' arrayList}) ; \
- do echo $line | tr -d '"[],' ; done
+ cat ~{write_map(map)} | md5sum - | sed -e 's/ -//'
}
output {
- Array[String] flattenedArray = read_lines(stdout())
+ String md5sum = read_string(stdout())
}
runtime {
@@ -87,17 +97,18 @@ task flattenStringArray {
}
}
-task appendToStringArray {
- Array[String] array
- String string
+
+task ObjectMd5 {
+ input {
+ Object the_object
+ }
command {
- echo "${sep='\n' array}
- ${string}"
+ cat ~{write_object(the_object)} | md5sum - | sed -e 's/ -//'
}
output {
- Array[String] out_array = read_lines(stdout())
+ String md5sum = read_string(stdout())
}
runtime {
@@ -105,17 +116,21 @@ task appendToStringArray {
}
}
-task createLink {
- # Making this of type File will create a link to the copy of the file in the execution
- # folder, instead of the actual file.
- String inputFile
- String outputPath
+task StringArrayMd5 {
+ input {
+ Array[String] stringArray
+ }
command {
- ln -sf ${inputFile} ${outputPath}
+ set -eu -o pipefail
+ echo ~{sep=',' stringArray} | md5sum - | sed -e 's/ -//'
}
output {
- File link = outputPath
+ String md5sum = read_string(stdout())
}
-}
\ No newline at end of file
+
+ runtime {
+ memory: 1
+ }
+}
diff --git a/cutadapt.wdl b/cutadapt.wdl
index d4255c695c51e5cd6947b7955f8b871746ad8524..8b073442c02a449871f7dc6a320a8eabdf82d8d4 100644
--- a/cutadapt.wdl
+++ b/cutadapt.wdl
@@ -1,109 +1,127 @@
-task cutadapt {
- File read1
- File? read2
- String read1output
- String? read2output
- String? format
- String? preCommand
- Int? cores = 1
- Int? memory = 4
- Array[String]+? adapter
- Array[String]+? front
- Array[String]+? anywhere
- Array[String]+? adapterRead2
- Array[String]+? frontRead2
- Array[String]+? anywhereRead2
- Boolean? interleaved
- String? pairFilter
- Float? errorRate
- Boolean? noIndels
- Int? times
- Int? overlap
- Boolean? matchReadWildcards
- Boolean? noMatchAdapterWildcards
- Boolean? noTrim
- Boolean? maskAdapter
- Int? cut
- String? nextseqTrim
- String? qualityCutoff
- Int? qualityBase
- Int? length
- Boolean? trimN
- String? lengthTag
- String? stripSuffix
- String? prefix
- String? suffix
- Int? minimumLength = 1 # Necessary to prevent creation of empty reads
- Int? maximumLength
- Int? maxN
- Boolean? discardTrimmed
- Boolean? discardUntrimmed
- String? infoFilePath
- String? restFilePath
- String? wildcardFilePath
- String? tooShortOutputPath
- String? tooLongOutputPath
- String? untrimmedOutputPath
- String? tooShortPairedOutputPath
- String? tooLongPairedOutputPath
- String? untrimmedPairedOutputPath
- Boolean? colorspace
- Boolean? doubleEncode
- Boolean? trimPrimer
- Boolean? stripF3
- Boolean? maq
- Boolean? bwa
- Boolean? zeroCap
- Boolean? noZeroCap
- String? reportPath
+version 1.0
+
+task Cutadapt {
+ input {
+ File read1
+ File? read2
+ String read1output
+ String? read2output
+ String? format
+ String? preCommand
+ Int cores = 1
+ Int memory = 4
+ Array[String]+? adapter
+ Array[String]+? front
+ Array[String]+? anywhere
+ Array[String]+? adapterRead2
+ Array[String]+? frontRead2
+ Array[String]+? anywhereRead2
+ Boolean? interleaved
+ String? pairFilter
+ Float? errorRate
+ Boolean? noIndels
+ Int? times
+ Int? overlap
+ Boolean? matchReadWildcards
+ Boolean? noMatchAdapterWildcards
+ Boolean? noTrim
+ Boolean? maskAdapter
+ Int? cut
+ String? nextseqTrim
+ String? qualityCutoff
+ Int? qualityBase
+ Int? length
+ Boolean? trimN
+ String? lengthTag
+ String? stripSuffix
+ String? prefix
+ String? suffix
+ Int? minimumLength = 1 # Necessary to prevent creation of empty reads
+ Int? maximumLength
+ Int? maxN
+ Boolean? discardTrimmed
+ Boolean? discardUntrimmed
+ String? infoFilePath
+ String? restFilePath
+ String? wildcardFilePath
+ String? tooShortOutputPath
+ String? tooLongOutputPath
+ String? untrimmedOutputPath
+ String? tooShortPairedOutputPath
+ String? tooLongPairedOutputPath
+ String? untrimmedPairedOutputPath
+ Boolean? colorspace
+ Boolean? doubleEncode
+ Boolean? trimPrimer
+ Boolean? stripF3
+ Boolean? maq
+ Boolean? bwa
+ Boolean? zeroCap
+ Boolean? noZeroCap
+ String? reportPath
+ }
command {
set -e -o pipefail
- ${"mkdir -p $(dirname " + read1output + ")"}
- ${"mkdir -p $(dirname " + read2output + ")"}
- ${"mkdir -p $(dirname " + reportPath + ")"}
- ${preCommand}
+ ~{"mkdir -p $(dirname " + read1output + ")"}
+ ~{"mkdir -p $(dirname " + read2output + ")"}
+ ~{"mkdir -p $(dirname " + reportPath + ")"}
+ ~{preCommand}
cutadapt \
- ${"--cores=" + cores} \
- ${true="-a " false="" defined(adapter)} ${sep=" -a " adapter} \
- ${true="-A " false="" defined(adapterRead2)} ${sep=" -A " adapterRead2} \
- ${true="-g " false="" defined(front)} ${sep=" -g " front} \
- ${true="-G " false="" defined(frontRead2)} ${sep=" -G " frontRead2} \
- ${true="-b " false="" defined(anywhere)} ${sep=" -a " anywhere} \
- ${true="-B " false="" defined(anywhereRead2)} ${sep=" -B " anywhereRead2} \
- --output ${read1output} ${"--paired-output " + read2output} \
- ${"--to-short-output " + tooShortOutputPath} ${"--to-short-paired-output " + tooShortPairedOutputPath} \
- ${"--to-long-output " + tooLongOutputPath} ${"--to-long-paired-output " + tooLongPairedOutputPath} \
- ${"--untrimmed-output " + untrimmedOutputPath} ${"--untrimmed-paired-output " + untrimmedPairedOutputPath} \
- ${"--pair-filter " + pairFilter} \
- ${"--error-rate " + errorRate} \
- ${"--times " + times} \
- ${"--overlap " + overlap} \
- ${"--cut " + cut} \
- ${"--nextseq-trim " + nextseqTrim} \
- ${"--quality-cutoff " + qualityCutoff} \
- ${"--quality-base " + qualityBase} \
- ${"--length " + length} \
- ${"--length-tag " + lengthTag} \
- ${"--strip-suffix " + stripSuffix} \
- ${"--prefix " + prefix} \
- ${"--suffix " + suffix} \
- ${"--minimum-length " + minimumLength} \
- ${"--maximum-length " + maximumLength} \
- ${"--max-n " + maxN} \
- ${true="--discard-untrimmed" false="" discardUntrimmed} \
- ${"--info-file " + infoFilePath } \
- ${"--rest-file " + restFilePath } \
- ${"--wildcard-file " + wildcardFilePath} \
- ${true="--match-read-wildcards" false="" matchReadWildcards} ${true="--no-match-adapter-wildcards" false="" noMatchAdapterWildcards} \
- ${true="--no-trim" false="" noTrim} ${true="--mask-adapter" false="" maskAdapter} \
- ${true="--no-indels" false="" noIndels} ${true="--trim-n" false="" trimN} \
- ${true="--interleaved" false="" interleaved} ${true="--discard-trimmed" false="" discardTrimmed } \
- ${true="--colorspace" false="" colorspace} ${true="--double-encode" false="" doubleEncode} \
- ${true="--strip-f3" false="" stripF3} ${true="--maq" false="" maq} ${true="--bwa" false="" bwa} \
- ${true="--zero-cap" false="" zeroCap} ${true="--no-zero-cap" false="" noZeroCap} \
- ${read1} ${read2} ${"> " + reportPath}
+ ~{"--cores=" + cores} \
+ ~{true="-a" false="" defined(adapter)} ~{sep=" -a " adapter} \
+ ~{true="-A" false="" defined(adapterRead2)} ~{sep=" -A " adapterRead2} \
+ ~{true="-g" false="" defined(front)} ~{sep=" -g " front} \
+ ~{true="-G" false="" defined(frontRead2)} ~{sep=" -G " frontRead2} \
+ ~{true="-b" false="" defined(anywhere)} ~{sep=" -b " anywhere} \
+ ~{true="-B" false="" defined(anywhereRead2)} ~{sep=" -B " anywhereRead2} \
+ --output ~{read1output} ~{"--paired-output " + read2output} \
+ ~{"--to-short-output " + tooShortOutputPath} \
+ ~{"--to-short-paired-output " + tooShortPairedOutputPath} \
+ ~{"--to-long-output " + tooLongOutputPath} \
+ ~{"--to-long-paired-output " + tooLongPairedOutputPath} \
+ ~{"--untrimmed-output " + untrimmedOutputPath} \
+ ~{"--untrimmed-paired-output " + untrimmedPairedOutputPath} \
+ ~{"--pair-filter " + pairFilter} \
+ ~{"--error-rate " + errorRate} \
+ ~{"--times " + times} \
+ ~{"--overlap " + overlap} \
+ ~{"--cut " + cut} \
+ ~{"--nextseq-trim " + nextseqTrim} \
+ ~{"--quality-cutoff " + qualityCutoff} \
+ ~{"--quality-base " + qualityBase} \
+ ~{"--length " + length} \
+ ~{"--length-tag " + lengthTag} \
+ ~{"--strip-suffix " + stripSuffix} \
+ ~{"--prefix " + prefix} \
+ ~{"--suffix " + suffix} \
+ ~{"--minimum-length " + minimumLength} \
+ ~{"--maximum-length " + maximumLength} \
+ ~{"--max-n " + maxN} \
+ ~{true="--discard-untrimmed" false="" discardUntrimmed} \
+ ~{"--info-file " + infoFilePath } \
+ ~{"--rest-file " + restFilePath } \
+ ~{"--wildcard-file " + wildcardFilePath} \
+ ~{true="--match-read-wildcards" false="" matchReadWildcards} \
+ ~{true="--no-match-adapter-wildcards" false="" noMatchAdapterWildcards} \
+ ~{true="--no-trim" false="" noTrim} \
+ ~{true="--mask-adapter" false="" maskAdapter} \
+ ~{true="--no-indels" false="" noIndels} \
+ ~{true="--trim-n" false="" trimN} \
+ ~{true="--interleaved" false="" interleaved} \
+ ~{true="--discard-trimmed" false="" discardTrimmed } \
+ ~{true="--colorspace" false="" colorspace} \
+ ~{true="--double-encode" false="" doubleEncode} \
+ ~{true="--strip-f3" false="" stripF3} \
+ ~{true="--maq" false="" maq} \
+ ~{true="--bwa" false="" bwa} \
+ ~{true="--zero-cap" false="" zeroCap} \
+ ~{true="--no-zero-cap" false="" noZeroCap} \
+ ~{read1} \
+ ~{read2} \
+ ~{"> " + reportPath}
}
+
output{
File report = if defined(reportPath) then select_first([reportPath]) else stdout()
File cutRead1 = read1output
@@ -118,8 +136,9 @@ task cutadapt {
File? restFile=restFilePath
File? wildcardFile=wildcardFilePath
}
+
runtime {
- cpu: select_first([cores])
- memory: select_first([memory])
+ cpu: cores
+ memory: memory
}
}
diff --git a/fastqc.wdl b/fastqc.wdl
index d9135f73197bf1e985f5a096c45f449f37e42d94..6d924cf550a84640fcf3e8f9e1b555d2cf239dd7 100644
--- a/fastqc.wdl
+++ b/fastqc.wdl
@@ -1,46 +1,51 @@
-task fastqc {
- File seqFile
- String outdirPath
- String? preCommand
- Boolean? casava
- Boolean? nano
- Boolean? noFilter
- Boolean? extract = true
- Boolean? nogroup
- Int? minLength
- String? format
- Int? threads = 1
- File? contaminants
- File? adapters
- File? limits
- Int? kmers
- String? dir
+version 1.0
+
+task Fastqc {
+ input {
+ File seqFile
+ String outdirPath
+ String? preCommand
+ Boolean? casava
+ Boolean? nano
+ Boolean? noFilter
+ Boolean extract = true
+ Boolean? nogroup
+ Int? minLength
+ String? format
+ Int threads = 1
+ File? contaminants
+ File? adapters
+ File? limits
+ Int? kmers
+ String? dir
+ }
+
# Chops of the .gz extension if present.
String name = sub(seqFile, "\\.gz$","")
# This regex chops of the extension and replaces it with _fastqc for the reportdir.
# Just as fastqc does it.
String reportDir = outdirPath + "/" + sub(basename(name), "\\.[^\\.]*$", "_fastqc")
- command {
- set -e -o pipefail
- ${preCommand}
- mkdir -p ${outdirPath}
- fastqc \
- ${"--outdir " + outdirPath} \
- ${true="--casava" false="" casava} \
- ${true="--nano" false="" nano} \
- ${true="--nofilter" false="" noFilter} \
- ${true="--extract" false="" extract} \
- ${true="--nogroup" false="" nogroup} \
- ${"--min_length " + minLength } \
- ${"--format " + format} \
- ${"--threads " + threads} \
- ${"--contaminants " + contaminants} \
- ${"--adapters " + adapters} \
- ${"--limits " + limits} \
- ${"--kmers " + kmers} \
- ${"--dir " + dir} \
- ${seqFile}
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ mkdir -p ~{outdirPath}
+ fastqc \
+ ~{"--outdir " + outdirPath} \
+ ~{true="--casava" false="" casava} \
+ ~{true="--nano" false="" nano} \
+ ~{true="--nofilter" false="" noFilter} \
+ ~{true="--extract" false="" extract} \
+ ~{true="--nogroup" false="" nogroup} \
+ ~{"--min_length " + minLength } \
+ ~{"--format " + format} \
+ ~{"--threads " + threads} \
+ ~{"--contaminants " + contaminants} \
+ ~{"--adapters " + adapters} \
+ ~{"--limits " + limits} \
+ ~{"--kmers " + kmers} \
+ ~{"--dir " + dir} \
+ ~{seqFile}
}
output {
@@ -51,18 +56,20 @@ task fastqc {
}
runtime {
- cpu: select_first([threads])
+ cpu: threads
}
}
-task getConfiguration {
- String? preCommand
- String? fastqcDirFile = "fastqcDir.txt"
+task GetConfiguration {
+ input {
+ String? preCommand
+ String fastqcDirFile = "fastqcDir.txt"
+ }
command {
set -e -o pipefail
- ${preCommand}
- echo $(dirname $(readlink -f $(which fastqc))) > ${fastqcDirFile}
+ ~{preCommand}
+ echo $(dirname $(readlink -f $(which fastqc))) > ~{fastqcDirFile}
}
output {
diff --git a/flash.wdl b/flash.wdl
index c081d49cdd3841e91991b0c90ac894d61d965e40..3d3eecdf3820be7c841ca44f0f4de580df5e61d1 100644
--- a/flash.wdl
+++ b/flash.wdl
@@ -1,27 +1,31 @@
-task flash {
- String? preCommand
- File inputR1
- File inputR2
- String outdirPath
- String? outPrefix = "flash"
- Int? minOverlap
- Int? maxOverlap
- Boolean? compress = true
- Int? threads
- Int? memory
+version 1.0
+
+task Flash {
+ input {
+ String? preCommand
+ File inputR1
+ File inputR2
+ String outdirPath
+ String outPrefix = "flash"
+ Int? minOverlap
+ Int? maxOverlap
+ Boolean compress = true
+ Int threads = 2
+ Int memory = 2
+ }
command {
set -e -o pipefail
- mkdir -p ${outdirPath}
- ${preCommand}
+ mkdir -p ~{outdirPath}
+ ~{preCommand}
flash \
- ${"--threads=" + threads} \
- ${"--output-directory=" + outdirPath} \
- ${"--output-prefix=" + outPrefix} \
- ${true="--compress " false="" defined(compress)} \
- ${"--min-overlap=" + minOverlap} \
- ${"--max-overlap=" + maxOverlap} \
- ${inputR1} ${inputR2}
+ ~{"--threads=" + threads} \
+ ~{"--output-directory=" + outdirPath} \
+ ~{"--output-prefix=" + outPrefix} \
+ ~{true="--compress " false="" compress} \
+ ~{"--min-overlap=" + minOverlap} \
+ ~{"--max-overlap=" + maxOverlap} \
+ ~{inputR1} ~{inputR2}
}
output {
@@ -33,8 +37,8 @@ task flash {
}
runtime {
- cpu: select_first([threads, 2])
- memory: select_first([memory, 2])
+ cpu: threads
+ memory: memory
}
}
\ No newline at end of file
diff --git a/gatk.wdl b/gatk.wdl
index fbbc8138342e1e37aafb7289129d775e6aec962f..68281f386d0dab5e69f734415711a570f657382b 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -1,40 +1,44 @@
+version 1.0
+
# Apply Base Quality Score Recalibration (BQSR) model
task ApplyBQSR {
- String? preCommand
- File? gatkJar
- File inputBam
- File inputBamIndex
- String outputBamPath
- File recalibrationReport
- Array[File]+ sequenceGroupInterval
- File refDict
- File refFasta
- File refFastaIndex
- Int? compressionLevel
-
- Float? memory
- Float? memoryMultiplier
-
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ File? gatkJar
+ File inputBam
+ File inputBamIndex
+ String outputBamPath
+ File recalibrationReport
+ Array[File]+ sequenceGroupInterval
+ File refDict
+ File refFasta
+ File refFastaIndex
+ Int? compressionLevel
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
- ApplyBQSR \
- --create-output-bam-md5 \
- --add-output-sam-program-record \
- -R ${refFasta} \
- -I ${inputBam} \
- --use-original-qualities \
- -O ${outputBamPath} \
- -bqsr ${recalibrationReport} \
- --static-quantized-quals 10 --static-quantized-quals 20 --static-quantized-quals 30 \
- -L ${sep=" -L " sequenceGroupInterval}
+ ~{preCommand}
+ ~{toolCommand} \
+ ApplyBQSR \
+ --create-output-bam-md5 \
+ --add-output-sam-program-record \
+ -R ~{refFasta} \
+ -I ~{inputBam} \
+ --use-original-qualities \
+ -O ~{outputBamPath} \
+ -bqsr ~{recalibrationReport} \
+ --static-quantized-quals 10 \
+ --static-quantized-quals 20 \
+ --static-quantized-quals 30 \
+ -L ~{sep=" -L " sequenceGroupInterval}
}
output {
@@ -43,25 +47,29 @@ task ApplyBQSR {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
# Generate Base Quality Score Recalibration (BQSR) model
task BaseRecalibrator {
- String? preCommand
- File? gatkJar
- File inputBam
- File inputBamIndex
- String recalibrationReportPath
- Array[File]+ sequenceGroupInterval
- Array[File]? knownIndelsSitesVCFs
- Array[File]? knownIndelsSitesIndices
- File? dbsnpVCF
- File? dbsnpVCFindex
- File refDict
- File refFasta
- File refFastaIndex
+ input {
+ String? preCommand
+ File? gatkJar
+ File inputBam
+ File inputBamIndex
+ String recalibrationReportPath
+ Array[File]+ sequenceGroupInterval
+ Array[File]? knownIndelsSitesVCFs
+ Array[File]? knownIndelsSitesIndices
+ File? dbsnpVCF
+ File? dbsnpVCFindex
+ File refDict
+ File refFasta
+ File refFastaIndex
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
Array[File]+ knownIndelsSitesVCFsArg = flatten([
select_first([knownIndelsSitesVCFs, []]),
@@ -72,26 +80,21 @@ task BaseRecalibrator {
select_all([dbsnpVCFindex])
])
- Float? memory
- Float? memoryMultiplier
-
- Int mem = ceil(select_first([memory, 4.0]))
-
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
- BaseRecalibrator \
- -R ${refFasta} \
- -I ${inputBam} \
- --use-original-qualities \
- -O ${recalibrationReportPath} \
- --known-sites ${sep=" --known-sites " knownIndelsSitesVCFsArg} \
- -L ${sep=" -L " sequenceGroupInterval}
+ ~{preCommand}
+ ~{toolCommand} \
+ BaseRecalibrator \
+ -R ~{refFasta} \
+ -I ~{inputBam} \
+ --use-original-qualities \
+ -O ~{recalibrationReportPath} \
+ --known-sites ~{sep=" --known-sites " knownIndelsSitesVCFsArg} \
+ -L ~{sep=" -L " sequenceGroupInterval}
}
output {
@@ -99,48 +102,48 @@ task BaseRecalibrator {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task CombineGVCFs {
- String? preCommand
- Array[File]+ gvcfFiles
- Array[File]+ gvcfFileIndexes
- Array[File]+ intervals
-
- String outputPath
+ input {
+ String? preCommand
+ Array[File]+ gvcfFiles
+ Array[File]+ gvcfFileIndexes
+ Array[File]+ intervals
- String? gatkJar
+ String outputPath
- File refFasta
- File refFastaIndex
- File refDict
+ String? gatkJar
- Int? compressionLevel
- Float? memory
- Float? memoryMultiplier
+ File refFasta
+ File refFastaIndex
+ File refDict
- Int mem = ceil(select_first([memory, 4.0]))
+ Int? compressionLevel #TODO This isn't being used?
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
+ ~{preCommand}
- if [ ${length(gvcfFiles)} -gt 1 ]; then
- ${toolCommand} \
+ if [ ~{length(gvcfFiles)} -gt 1 ]; then
+ ~{toolCommand} \
CombineGVCFs \
- -R ${refFasta} \
- -O ${outputPath} \
- -V ${sep=' -V ' gvcfFiles} \
- -L ${sep=' -L ' intervals}
+ -R ~{refFasta} \
+ -O ~{outputPath} \
+ -V ~{sep=' -V ' gvcfFiles} \
+ -L ~{sep=' -L ' intervals}
else # TODO this should be handeled in wdl
- ln -sf ${select_first(gvcfFiles)} ${outputPath}
- ln -sf ${select_first(gvcfFileIndexes)} ${outputPath}.tbi
+ ln -sf ~{select_first(gvcfFiles)} ~{outputPath}
+ ln -sf ~{select_first(gvcfFileIndexes)} ~{outputPath}.tbi
fi
}
@@ -150,33 +153,33 @@ task CombineGVCFs {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
# Combine multiple recalibration tables from scattered BaseRecalibrator runs
task GatherBqsrReports {
- String? preCommand
- String? gatkJar
- Array[File] inputBQSRreports
- String outputReportPath
-
- Float? memory
- Float? memoryMultiplier
-
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ String? gatkJar
+ Array[File] inputBQSRreports
+ String outputReportPath
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
+ ~{preCommand}
+ ~{toolCommand} \
GatherBQSRReports \
- -I ${sep=' -I ' inputBQSRreports} \
- -O ${outputReportPath}
+ -I ~{sep=' -I ' inputBQSRreports} \
+ -O ~{outputReportPath}
}
output {
@@ -184,51 +187,50 @@ task GatherBqsrReports {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task GenotypeGVCFs {
- String? preCommand
- File gvcfFiles
- File gvcfFileIndexes
- Array[File]+ intervals
+ input {
+ String? preCommand
+ File gvcfFiles
+ File gvcfFileIndexes
+ Array[File]+ intervals
- String outputPath
+ String outputPath
- String? gatkJar
+ String? gatkJar
- File refFasta
- File refFastaIndex
- File refDict
+ File refFasta
+ File refFastaIndex
+ File refDict
- File? dbsnpVCF
- File? dbsnpVCFindex
+ File? dbsnpVCF
+ File? dbsnpVCFindex
- Int? compressionLevel
- Float? memory
- Float? memoryMultiplier
-
- Int mem = ceil(select_first([memory, 4.0]))
+ Int? compressionLevel
+ Int memory = 4
+ Float memoryMultiplier =3.0
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
-
- ${toolCommand} \
- GenotypeGVCFs \
- -R ${refFasta} \
- -O ${outputPath} \
- ${"-D " + dbsnpVCF} \
- -G StandardAnnotation \
- --only-output-calls-starting-in-intervals \
- -new-qual \
- -V ${gvcfFiles} \
- -L ${sep=' -L ' intervals}
+ ~{preCommand}
+ ~{toolCommand} \
+ GenotypeGVCFs \
+ -R ~{refFasta} \
+ -O ~{outputPath} \
+ ~{"-D " + dbsnpVCF} \
+ -G StandardAnnotation \
+ --only-output-calls-starting-in-intervals \
+ -new-qual \
+ -V ~{gvcfFiles} \
+ -L ~{sep=' -L ' intervals}
}
output {
@@ -237,47 +239,48 @@ task GenotypeGVCFs {
}
runtime{
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
# Call variants on a single sample with HaplotypeCaller to produce a GVCF
task HaplotypeCallerGvcf {
- String? preCommand
- Array[File]+ inputBams
- Array[File]+ inputBamsIndex
- Array[File]+ intervalList
- String gvcfPath
- File refDict
- File refFasta
- File refFastaIndex
- Float? contamination
- Int? compressionLevel
- String? gatkJar
-
- File? dbsnpVCF
- File? dbsnpVCFindex
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
+ Array[File]+ intervalList
+ String gvcfPath
+ File refDict
+ File refFasta
+ File refFastaIndex
+ Float contamination = 0.0
+ Int? compressionLevel
+ String? gatkJar
+
+ File? dbsnpVCF
+ File? dbsnpVCFindex
+
+ Int memory = 4
+ Float memoryMultiplier = 3
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
- HaplotypeCaller \
- -R ${refFasta} \
- -O ${gvcfPath} \
- -I ${sep=" -I " inputBams} \
- -L ${sep=' -L ' intervalList} \
- ${"-D " + dbsnpVCF} \
- -contamination ${default=0 contamination} \
- -ERC GVCF
+ ~{preCommand}
+ ~{toolCommand} \
+ HaplotypeCaller \
+ -R ~{refFasta} \
+ -O ~{gvcfPath} \
+ -I ~{sep=" -I " inputBams} \
+ -L ~{sep=' -L ' intervalList} \
+ ~{"-D " + dbsnpVCF} \
+ -contamination ~{contamination} \
+ -ERC GVCF
}
output {
@@ -286,39 +289,40 @@ task HaplotypeCallerGvcf {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task SplitNCigarReads {
- String? preCommand
-
- File inputBam
- File inputBamIndex
- File refFasta
- File refFastaIndex
- File refDict
- String outputBam
- String? gatkJar
- Array[File]+ intervals
-
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 4.0]))
+ input {
+ String? preCommand
+
+ File inputBam
+ File inputBamIndex
+ File refFasta
+ File refFastaIndex
+ File refDict
+ String outputBam
+ String? gatkJar
+ Array[File]+ intervals
+
+ Int memory = 4
+ Float memoryMultiplier = 3
+ }
String toolCommand = if defined(gatkJar)
- then "java -Xmx" + mem + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + gatkJar
+ else "gatk --java-options -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
+ ~{preCommand}
+ ~{toolCommand} \
SplitNCigarReads \
- -I ${inputBam} \
- -R ${refFasta} \
- -O ${outputBam} \
- -L ${sep=' -L ' intervals}
+ -I ~{inputBam} \
+ -R ~{refFasta} \
+ -O ~{outputBam} \
+ -L ~{sep=' -L ' intervals}
}
output {
@@ -327,6 +331,6 @@ task SplitNCigarReads {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
diff --git a/htseq.wdl b/htseq.wdl
index b634bf5ee0f08128729723eaf71e77536bf401f6..db399cc2fb35061e69d280eb2efbcf44e1ccfb6d 100644
--- a/htseq.wdl
+++ b/htseq.wdl
@@ -1,25 +1,29 @@
+version 1.0
+
task HTSeqCount {
- String? preCommand
- Array[File] alignmentFiles
- File gtfFile
- String outputTable
- String? format
- String? order
- String? stranded
+ input {
+ String? preCommand
+ Array[File] alignmentFiles
+ File gtfFile
+ String outputTable
+ String format = "bam"
+ String order = "pos"
+ String stranded = "no"
- Int? memory
+ Int memory = 3
+ }
command {
set -e -o pipefail
- mkdir -p ${sub(outputTable, basename(outputTable), "")}
- ${preCommand}
+ mkdir -p ~{sub(outputTable, basename(outputTable), "")}
+ ~{preCommand}
htseq-count \
- -f ${default="bam" format} \
- -r ${default="pos" order} \
- -s ${default="no" stranded} \
- ${sep=" " alignmentFiles} \
- ${gtfFile} \
- > ${outputTable}
+ -f ~{format} \
+ -r ~{order} \
+ -s ~{stranded} \
+ ~{sep=" " alignmentFiles} \
+ ~{gtfFile} \
+ > ~{outputTable}
}
output {
@@ -27,6 +31,6 @@ task HTSeqCount {
}
runtime {
- memory: select_first([memory, 3])
+ memory: memory
}
}
\ No newline at end of file
diff --git a/macs2.wdl b/macs2.wdl
index 88ae526ceb71223f41967ef45814046d764853d8..9364d9dc4f318bc657d42163925c758b592b2cfd 100644
--- a/macs2.wdl
+++ b/macs2.wdl
@@ -1,20 +1,24 @@
+version 1.0
+
task PeakCalling {
- String? preCommand
- Array[File] bamFiles
- String outDir
- String sampleName
- Int? threads
- Int? memory
- Boolean nomodel = false
+ input {
+ String? preCommand
+ Array[File] bamFiles
+ String outDir
+ String sampleName
+ Int threads = 1
+ Int memory = 8
+ Boolean nomodel = false
+ }
command {
set -e -o pipefail
- ${preCommand}
+ ~{preCommand}
macs2 callpeak \
- --treatment ${sep = ' ' bamFiles} \
- --outdir ${outDir} \
- --name ${sampleName} \
- ${true='--nomodel' false='' nomodel}
+ --treatment ~{sep = ' ' bamFiles} \
+ --outdir ~{outDir} \
+ --name ~{sampleName} \
+ ~{true='--nomodel' false='' nomodel}
}
output {
@@ -22,7 +26,7 @@ task PeakCalling {
}
runtime {
- cpu: select_first([threads,1])
- memory: select_first([memory,8])
+ cpu: threads
+ memory: memory
}
}
\ No newline at end of file
diff --git a/mergecounts.wdl b/mergecounts.wdl
index 8cca5dd494eefdaf208bedeffa051ec0960ed6d9..5de98e799a341e0f1ac3a3b4d2b6323e8e5a8c8c 100644
--- a/mergecounts.wdl
+++ b/mergecounts.wdl
@@ -1,26 +1,30 @@
-task MergeCounts {
- String? preCommand
+version 1.0
- Array[File] inputFiles
- String outputFile
- Int featureColumn
- Int valueColumn
- Boolean inputHasHeader
+task MergeCounts {
+ input {
+ String? preCommand
+
+ Array[File] inputFiles
+ String outputFile
+ Int featureColumn
+ Int valueColumn
+ Boolean inputHasHeader
+ }
# Based on a script by Szymon Kielbasa/Ioannis Moustakas
command <<<
set -e -o pipefail
- mkdir -p ${sub(outputFile, basename(outputFile) + "$", "")}
- ${preCommand}
+ mkdir -p ~{sub(outputFile, basename(outputFile) + "$", "")}
+ ~{preCommand}
R --no-save <<CODE
library(dplyr)
library(reshape2)
- listOfFiles <- c("${sep='", "' inputFiles}")
+ listOfFiles <- c("~{sep='", "' inputFiles}")
- valueI <- ${valueColumn}
- featureI <- ${featureColumn}
- header <- ${true="TRUE" false="FALSE" inputHasHeader}
+ valueI <- ~{valueColumn}
+ featureI <- ~{featureColumn}
+ header <- ~{true="TRUE" false="FALSE" inputHasHeader}
d <- do.call(rbind, lapply(listOfFiles, function(file){
d <- read.table(file, sep="\t", header=header, comment.char="#")
@@ -34,7 +38,7 @@ task MergeCounts {
}))
d <- d %>% dcast(feature ~ sample, value.var="count")
- write.table(d, file="${outputFile}", sep="\t", quote=FALSE, row.names=FALSE)
+ write.table(d, file="~{outputFile}", sep="\t", quote=FALSE, row.names=FALSE)
CODE
>>>
diff --git a/ncbi.wdl b/ncbi.wdl
index f32959ec6ebe01494e2b6faf6ed580c354e6417d..0678d3d4ea2fffcb9207e972779d056679058fe0 100644
--- a/ncbi.wdl
+++ b/ncbi.wdl
@@ -1,41 +1,45 @@
-task genomeDownload {
- String outputPath
- String? section = "refseq"
- String? format = "all"
- String? assemblyLevel = "all"
- String? taxId
- String? refseqCategory
- Boolean? humanReadable
- String? ncbiBaseUri
- Int? parallel
- Int? retries
- Boolean? verbose=true
- Boolean? debug
- String? domain = "all"
+version 1.0
- String? executable = "ncbi-genome-download"
- String? preCommand
+task GenomeDownload {
+ input {
+ String outputPath
+ String? section = "refseq"
+ String? format = "all"
+ String? assemblyLevel = "all"
+ String? taxId
+ String? refseqCategory
+ Boolean? humanReadable
+ String? ncbiBaseUri
+ Int? parallel
+ Int? retries
+ Boolean verbose = true
+ Boolean debug = false
+ String? domain = "all"
+
+ String executable = "ncbi-genome-download"
+ String? preCommand
+ }
command {
set -e -o pipefail
- ${preCommand}
- ${executable} \
- ${"--section " + section} \
- ${"--format " + format} \
- ${"--assembly-level " + assemblyLevel } \
- ${"--taxid " + taxId } \
- ${"--refseq-category " + refseqCategory} \
- ${"--output-folder " + outputPath } \
- ${true="--human-readable" false="" humanReadable} \
- ${"--uri " + ncbiBaseUri } \
- ${"--parallel " + parallel } \
- ${"--retries " + retries } \
- ${true="--verbose" false="" verbose } \
- ${true="--debug" false ="" debug } \
- ${domain}
+ ~{preCommand}
+ ~{executable} \
+ ~{"--section " + section} \
+ ~{"--format " + format} \
+ ~{"--assembly-level " + assemblyLevel } \
+ ~{"--taxid " + taxId } \
+ ~{"--refseq-category " + refseqCategory} \
+ ~{"--output-folder " + outputPath } \
+ ~{true="--human-readable" false="" humanReadable} \
+ ~{"--uri " + ncbiBaseUri } \
+ ~{"--parallel " + parallel } \
+ ~{"--retries " + retries } \
+ ~{true="--verbose" false="" verbose } \
+ ~{true="--debug" false ="" debug } \
+ ~{domain}
# Check md5sums for all downloaded files
- for folder in $(realpath ${outputPath})/*/*/*
+ for folder in $(realpath ~{outputPath})/*/*/*
do
(
md5sums="$(
@@ -68,23 +72,27 @@ task genomeDownload {
}
-task downloadNtFasta{
- String libraryPath
- String seqTaxMapPath
- Boolean? unzip = true
- String ntDir = libraryPath + "/nt"
- String ntFilePath = ntDir + "/nt.fna"
+task DownloadNtFasta{
+ input {
+ String libraryPath
+ String seqTaxMapPath
+ Boolean unzip = true
+ String ntDir = libraryPath + "/nt"
+ String ntFilePath = ntDir + "/nt.fna"
+ }
+
command {
set -e -o pipefail
- mkdir -p ${ntDir}
- rsync -av --partial rsync://ftp.ncbi.nih.gov/blast/db/FASTA/nt.gz* ${ntDir}
- (cd ${ntDir} && md5sum -c nt.gz.md5)
+ mkdir -p ~{ntDir}
+ rsync -av --partial rsync://ftp.ncbi.nih.gov/blast/db/FASTA/nt.gz* ~{ntDir}
+ (cd ~{ntDir} && md5sum -c nt.gz.md5)
# Only unzip when necessary
- if ${true='true' false='false' unzip}
+ if ~{true='true' false='false' unzip}
then
- zcat ${ntDir}/nt.gz > ${ntFilePath}
+ zcat ~{ntDir}/nt.gz > ~{ntFilePath}
fi
- }
+ }
+
output {
File ntFileGz = ntDir + "/nt.gz"
File library = libraryPath
@@ -95,19 +103,27 @@ task downloadNtFasta{
}
}
-task downloadAccessionToTaxId {
- String downloadDir
- Boolean gzip = false
+task DownloadAccessionToTaxId {
+ input {
+ String downloadDir
+ Boolean gzip = false
+ }
+
command {
set -e -o pipefail
- mkdir -p ${downloadDir}
- rsync -av --partial rsync://ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/nucl_*.accession2taxid.gz* ${downloadDir}
- (cd ${downloadDir} && md5sum -c *.md5)
- for file in ${downloadDir}/nucl_*.accession2taxid.gz
+ mkdir -p ~{downloadDir}
+ rsync -av \
+ --partial \
+ rsync://ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/nucl_*.accession2taxid.gz* \
+ ~{downloadDir}
+ (cd ~{downloadDir} && md5sum -c *.md5)
+ for file in ~{downloadDir}/nucl_*.accession2taxid.gz
do
- zcat $file | tail -n +2 | cut -f 2,3 ${true="| gzip " false='' gzip}> $file.seqtaxmap${true='.gz' false='' gzip}
+ zcat $file | tail -n +2 | cut -f 2,3 ~{true="| gzip" false='' gzip} > \
+ $file.seqtaxmap~{true='.gz' false='' gzip}
done
- }
+ }
+
output {
Array[File] seqTaxMaps = glob(downloadDir + "/*.seqtaxmap")
Array[File] seqTaxMapsGz = glob(downloadDir + "/*.seqtaxmap.gz")
diff --git a/picard.wdl b/picard.wdl
index 66916efa9ffb874617e1effea459e3dbb1b0c099..0b13ebe4dbf857f311d5f5836e668ebd0545d62d 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -1,122 +1,253 @@
-task ScatterIntervalList {
- String? preCommand
- File interval_list
- Int scatter_count
- String? picardJar
+version 1.0
+
+task CollectMultipleMetrics {
+ input {
+ String? preCommand
+ File bamFile
+ File bamIndex
+ File refFasta
+ File refDict
+ File refFastaIndex
+ String basename
+
+ Boolean collectAlignmentSummaryMetrics = true
+ Boolean collectInsertSizeMetrics = true
+ Boolean qualityScoreDistribution = true
+ 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
+ Boolean collectSequencingArtifactMetrics = true
+ Boolean collectQualityYieldMetrics = true
+
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
+
+ String toolCommand = if defined(picardJar)
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ mkdir -p $(dirname "~{basename}")
+ ~{preCommand}
+ ~{toolCommand} \
+ CollectMultipleMetrics \
+ I=~{bamFile} \
+ R=~{refFasta} \
+ O=~{basename} \
+ PROGRAM=null \
+ ~{true="PROGRAM=CollectAlignmentSummaryMetrics" false="" collectAlignmentSummaryMetrics} \
+ ~{true="PROGRAM=CollectInsertSizeMetrics" false="" collectInsertSizeMetrics} \
+ ~{true="PROGRAM=QualityScoreDistribution" false="" qualityScoreDistribution} \
+ ~{true="PROGRAM=MeanQualityByCycle" false="" meanQualityByCycle} \
+ ~{true="PROGRAM=CollectBaseDistributionByCycle" false="" collectBaseDistributionByCycle} \
+ ~{true="PROGRAM=CollectGcBiasMetrics" false="" collectGcBiasMetrics} \
+ ~{true="PROGRAM=CollectSequencingArtifactMetrics" false=""
+ collectSequencingArtifactMetrics} \
+ ~{true="PROGRAM=CollectQualityYieldMetrics" false="" collectQualityYieldMetrics}
+ }
+
+ output {
+ File aligmentSummary = basename + ".alignment_summary_metrics"
+ File baitBiasDetail = basename + ".bait_bias_detail_metrics"
+ File baitBiasSummary = basename + ".bait_bias_summary_metrics"
+ File baseDistributionByCycle = basename + ".base_distribution_by_cycle_metrics"
+ File baseDistributionByCyclePdf = basename + ".base_distribution_by_cycle.pdf"
+ File errorSummary = basename + ".error_summary_metrics"
+ File gcBiasDetail = basename + ".gc_bias.detail_metrics"
+ File gcBiasPdf = basename + ".gc_bias.pdf"
+ File gcBiasSummary = basename + ".gc_bias.summary_metrics"
+ File insertSizeHistogramPdf = basename + ".insert_size_histogram.pdf"
+ File insertSize = basename + ".insert_size_metrics"
+ File preAdapterDetail = basename + ".pre_adapter_detail_metrics"
+ File preAdapterSummary = basename + ".pre_adapter_summary_metrics"
+ File qualityByCycle = basename + ".quality_by_cycle_metrics"
+ File qualityByCyclePdf = basename + ".quality_by_cycle.pdf"
+ File qualityDistribution = basename + ".quality_distribution_metrics"
+ File qualityDistributionPdf = basename + ".quality_distribution.pdf"
+ File qualityYield = basename + ".quality_yield_metrics"
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
+
+task CollectRnaSeqMetrics {
+ input {
+ String? preCommand
+ File bamFile
+ File bamIndex
+ File refRefflat
+ String basename
+ String strandSpecificity = "NONE"
- Float? memory
- Float? memoryMultiplier
+ String? picardJar
- Int mem = ceil(select_first([memory, 4.0]))
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(picardJar)
- then "java -Xmx" + mem + "G -jar " + picardJar
- else "picard -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- mkdir scatter_list
- ${toolCommand} \
- IntervalListTools \
- SCATTER_COUNT=${scatter_count} \
- SUBDIVISION_MODE=BALANCING_WITHOUT_INTERVAL_SUBDIVISION_WITH_OVERFLOW \
- UNIQUE=true \
- SORT=true \
- INPUT=${interval_list} \
- OUTPUT=scatter_list
+ mkdir -p $(dirname "~{basename}")
+ ~{preCommand}
+ ~{toolCommand} \
+ CollectRnaSeqMetrics \
+ I=~{bamFile} \
+ O=~{basename}.RNA_Metrics \
+ CHART_OUTPUT=~{basename}.RNA_Metrics.pdf \
+ STRAND_SPECIFICITY=~{strandSpecificity} \
+ REF_FLAT=~{refRefflat}
}
output {
- Array[File] out = glob("scatter_list/*/*.interval_list")
- Int interval_count = read_int(stdout())
+ File chart = basename + ".RNA_Metrics.pdf"
+ File metrics = basename + ".RNA_Metrics"
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
-# Combine multiple recalibrated BAM files from scattered ApplyRecalibration runs
-task GatherBamFiles {
- String? preCommand
- Array[File]+ input_bams
- String output_bam_path
- Int? compression_level
- String? picardJar
+task CollectTargetedPcrMetrics {
+ input {
+ String? preCommand
+ File bamFile
+ File bamIndex
+ File refFasta
+ File refDict
+ File refFastaIndex
+ File ampliconIntervals
+ Array[File]+ targetIntervals
+ String basename
+
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
+
+ String toolCommand = if defined(picardJar)
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ mkdir -p $(dirname "~{basename}")
+ ~{preCommand}
+ ~{toolCommand} \
+ CollectTargetedPcrMetrics \
+ I=~{bamFile} \
+ R=~{refFasta} \
+ AMPLICON_INTERVALS=~{ampliconIntervals} \
+ TARGET_INTERVALS=~{sep=" TARGET_INTERVALS=" targetIntervals} \
+ O=~{basename}.targetPcrMetrics \
+ PER_BASE_COVERAGE=~{basename}.targetPcrPerBaseCoverage \
+ PER_TARGET_COVERAGE=~{basename}.targetPcrPerTargetCoverage
+ }
+
+ output {
+ File perTargetCoverage = basename + ".targetPcrPerTargetCoverage"
+ File perBaseCoverage = basename + ".targetPcrPerBaseCoverage"
+ File metrics = basename + ".targetPcrMetrics"
+ }
- Float? memory
- Float? memoryMultiplier
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
- Int mem = ceil(select_first([memory, 4.0]))
+# Combine multiple recalibrated BAM files from scattered ApplyRecalibration runs
+task GatherBamFiles {
+ input {
+ String? preCommand
+ Array[File]+ input_bams
+ String output_bam_path
+ Int? compression_level
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(picardJar)
- then "java -Xmx" + mem + "G -jar " + picardJar
- else "picard -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
- GatherBamFiles \
- INPUT=${sep=' INPUT=' input_bams} \
- OUTPUT=${output_bam_path} \
- CREATE_INDEX=true \
- CREATE_MD5_FILE=true
+ ~{preCommand}
+ ~{toolCommand} \
+ GatherBamFiles \
+ INPUT=~{sep=' INPUT=' input_bams} \
+ OUTPUT=~{output_bam_path} \
+ CREATE_INDEX=true \
+ CREATE_MD5_FILE=true
}
output {
- File output_bam = "${output_bam_path}"
+ File output_bam = "~{output_bam_path}"
File output_bam_index = sub(output_bam_path, ".bam$", ".bai")
- File output_bam_md5 = "${output_bam_path}.md5"
+ File output_bam_md5 = "~{output_bam_path}.md5"
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
# Mark duplicate reads to avoid counting non-independent observations
task MarkDuplicates {
- String? preCommand
- Array[File] input_bams
- String output_bam_path
- String metrics_path
- Int? compression_level
- String? picardJar
-
- Float? memory
- Float? memoryMultiplier
-
- # The program default for READ_NAME_REGEX is appropriate in nearly every case.
- # Sometimes we wish to supply "null" in order to turn off optical duplicate detection
- # This can be desirable if you don't mind the estimated library size being wrong and optical duplicate detection is taking >7 days and failing
- String? read_name_regex
+ input {
+ String? preCommand
+ Array[File] input_bams
+ String output_bam_path
+ String metrics_path
+ Int? compression_level
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+
+ # The program default for READ_NAME_REGEX is appropriate in nearly every case.
+ # Sometimes we wish to supply "null" in order to turn off optical duplicate detection
+ # This can be desirable if you don't mind the estimated library size being wrong and optical duplicate detection is taking >7 days and failing
+ String? read_name_regex
+ }
# Task is assuming query-sorted input so that the Secondary and Supplementary reads get marked correctly
# This works because the output of BWA is query-grouped and therefore, so is the output of MergeBamAlignment.
# While query-grouped isn't actually query-sorted, it's good enough for MarkDuplicates with ASSUME_SORT_ORDER="queryname"
- Int mem = ceil(select_first([memory, 4.0]))
String toolCommand = if defined(picardJar)
- then "java -Xmx" + mem + "G -jar " + picardJar
- else "picard -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- mkdir -p $(dirname ${output_bam_path})
- ${toolCommand} \
- MarkDuplicates \
- INPUT=${sep=' INPUT=' input_bams} \
- OUTPUT=${output_bam_path} \
- METRICS_FILE=${metrics_path} \
- 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
+ ~{preCommand}
+ mkdir -p $(dirname ~{output_bam_path})
+ ~{toolCommand} \
+ MarkDuplicates \
+ INPUT=~{sep=' INPUT=' input_bams} \
+ OUTPUT=~{output_bam_path} \
+ METRICS_FILE=~{metrics_path} \
+ 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
}
output {
@@ -126,37 +257,38 @@ task MarkDuplicates {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
# Combine multiple VCFs or GVCFs from scattered HaplotypeCaller runs
task MergeVCFs {
- String? preCommand
- Array[File] inputVCFs
- Array[File] inputVCFsIndexes
- String outputVCFpath
- Int? compressionLevel
- String? picardJar
-
- Float? memory
- Float? memoryMultiplier
+ input {
+ String? preCommand
+ Array[File] inputVCFs
+ Array[File] inputVCFsIndexes
+ String outputVCFpath
+ Int? compressionLevel
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
# Using MergeVcfs instead of GatherVcfs so we can create indices
# See https://github.com/broadinstitute/picard/issues/789 for relevant GatherVcfs ticket
- Int mem = ceil(select_first([memory, 4.0]))
String toolCommand = if defined(picardJar)
- then "java -Xmx" + mem + "G -jar " + picardJar
- else "picard -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
- MergeVcfs \
- INPUT=${sep=' INPUT=' inputVCFs} \
- OUTPUT=${outputVCFpath}
+ ~{preCommand}
+ ~{toolCommand} \
+ MergeVcfs \
+ INPUT=~{sep=' INPUT=' inputVCFs} \
+ OUTPUT=~{outputVCFpath}
}
output {
@@ -165,34 +297,36 @@ task MergeVCFs {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
}
}
task SamToFastq {
- String? preCommand
- File inputBam
- String outputRead1
- String? outputRead2
- String? outputUnpaired
- String? picardJar
- Float? memory
- Float? memoryMultiplier
- Int mem = ceil(select_first([memory, 16.0])) # High memory default to avoid crashes.
+ input {
+ String? preCommand
+ File inputBam
+ String outputRead1
+ String? outputRead2
+ String? outputUnpaired
+
+ String? picardJar
+ Int memory = 16 # High memory default to avoid crashes.
+ Float memoryMultiplier = 3.0
+ }
String toolCommand = if defined(picardJar)
- then "java -Xmx" + mem + "G -jar " + picardJar
- else "picard -Xmx" + mem + "G"
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
command {
set -e -o pipefail
- ${preCommand}
- ${toolCommand} \
+ ~{preCommand}
+ ~{toolCommand} \
SamToFastq \
- I=${inputBam} \
- ${"FASTQ=" + outputRead1} \
- ${"SECOND_END_FASTQ=" + outputRead2} \
- ${"UNPAIRED_FASTQ=" + outputUnpaired}
+ I=~{inputBam} \
+ ~{"FASTQ=" + outputRead1} \
+ ~{"SECOND_END_FASTQ=" + outputRead2} \
+ ~{"UNPAIRED_FASTQ=" + outputUnpaired}
}
output {
@@ -202,6 +336,45 @@ task SamToFastq {
}
runtime {
- memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
+
+task ScatterIntervalList {
+ input {
+ String? preCommand
+ File interval_list
+ Int scatter_count
+ String? picardJar
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
+
+ String toolCommand = if defined(picardJar)
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ mkdir scatter_list
+ ~{toolCommand} \
+ IntervalListTools \
+ SCATTER_COUNT=~{scatter_count} \
+ SUBDIVISION_MODE=BALANCING_WITHOUT_INTERVAL_SUBDIVISION_WITH_OVERFLOW \
+ UNIQUE=true \
+ SORT=true \
+ INPUT=~{interval_list} \
+ OUTPUT=scatter_list
+ }
+
+ output {
+ Array[File] out = glob("scatter_list/*/*.interval_list")
+ Int interval_count = read_int(stdout())
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
}
-}
\ No newline at end of file
+}
diff --git a/samplesheet.wdl b/samplesheet.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..e269911ddac6c9c353dcdcee8d95a8abf90713f6
--- /dev/null
+++ b/samplesheet.wdl
@@ -0,0 +1,73 @@
+version 1.0
+struct Readgroup {
+ String id
+ File R1
+ String R1_md5
+ File? R2
+ String R2_md5
+}
+
+struct Library {
+ String id
+ Array[Readgroup]+ readgroups
+}
+
+struct Sample {
+ String id
+ Array[Library]+ libraries
+}
+
+task sampleConfigFileToStruct {
+ input {
+ File sampleConfigFile
+ String outputJson = "output.json"
+ }
+
+ # Below command can convert any samplesheet with a nested dictionary
+ # structure to a list of objects model.
+ # It was specifically designed to run on both python2 and python3.
+ # Only requirement is PyYAML.
+ #
+ # Code maintained in https://github.com/rhpvorderman/samplesheet-to-struct
+ # can be moved to biowdl group later.
+ command {
+ python <<CODE
+
+ import yaml
+ import json
+
+
+ def nested_dicts_to_lists(dictionary):
+ new_dict = dict()
+ for key, value in dictionary.items():
+ if type(value) == dict:
+ new_dict[key] = dict_to_item_list_with_id(value)
+ else:
+ new_dict[key] = value
+ return new_dict
+
+
+ def dict_to_item_list_with_id(dictionary):
+ items = []
+ for sub_key, sub_dictionary in dictionary.items():
+ item_dict = dict(id=sub_key, **nested_dicts_to_lists(sub_dictionary))
+ items.append(item_dict)
+ return items
+
+
+ with open("~{sampleConfigFile}", "r") as samplesheet:
+ samplesheet_dict = yaml.load(samplesheet)
+
+ sample_struct = nested_dicts_to_lists(samplesheet_dict)
+
+ with open("~{outputJson}", "w") as output_json:
+ output_json.write(json.dumps(sample_struct))
+
+ CODE
+ }
+
+ output {
+ Map[String,Array[Sample]] map = read_json(outputJson)
+ Array[Sample] samples = map["samples"]
+ }
+}
\ No newline at end of file
diff --git a/samtools.wdl b/samtools.wdl
index b574ec5f023c13adb366e301e99bd7702d686fd0..2d910379db88bb9402df50c2e0704e08263a9ff7 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -1,28 +1,36 @@
+version 1.0
+
task Index {
- String? preCommand
- File bamFilePath
- String? bamIndexPath
+ input {
+ String? preCommand
+ File bamFilePath
+ String? bamIndexPath
+ }
command {
set -e -o pipefail
- ${preCommand}
- samtools index ${bamFilePath} ${bamIndexPath}
+ ~{preCommand}
+ samtools index ~{bamFilePath} ~{bamIndexPath}
}
output {
- File indexFile = if defined(bamIndexPath) then select_first([bamIndexPath]) else bamFilePath + ".bai"
+ File indexFile = if defined(bamIndexPath)
+ then select_first([bamIndexPath])
+ else bamFilePath + ".bai"
}
}
task Merge {
- String? preCommand
- Array[File]+ bamFiles
- String outputBamPath
+ input {
+ String? preCommand
+ Array[File]+ bamFiles
+ String outputBamPath
+ }
command {
set -e -o pipefail
- ${preCommand}
- samtools merge ${outputBamPath} ${sep=' ' bamFiles}
+ ~{preCommand}
+ samtools merge ~{outputBamPath} ~{sep=' ' bamFiles}
}
output {
@@ -31,14 +39,16 @@ task Merge {
}
task Markdup {
- String? preCommand
- File inputBam
- String outputBamPath
+ input {
+ String? preCommand
+ File inputBam
+ String outputBamPath
+ }
command {
set -e -o pipefail
- ${preCommand}
- samtools markdup ${inputBam} ${outputBamPath}
+ ~{preCommand}
+ samtools markdup ~{inputBam} ~{outputBamPath}
}
output {
@@ -47,15 +57,17 @@ task Markdup {
}
task Flagstat {
- String? preCommand
- File inputBam
- String outputPath
+ input {
+ String? preCommand
+ File inputBam
+ String outputPath
+ }
command {
set -e -o pipefail
- ${preCommand}
- mkdir -p $(dirname ${outputPath})
- samtools flagstat ${inputBam} > ${outputPath}
+ ~{preCommand}
+ mkdir -p $(dirname ~{outputPath})
+ samtools flagstat ~{inputBam} > ~{outputPath}
}
output {
@@ -63,46 +75,50 @@ task Flagstat {
}
}
-task fastq {
- String? preCommand
- File inputBam
- String outputRead1
- String? outputRead2
- String? outputRead0
- Int? includeFilter
- Int? excludeFilter
- Int? excludeSpecificFilter
- Boolean? appendReadNumber
- Boolean? outputQuality
- Int? compressionLevel
- Int? threads
- Int? memory
- Int totalThreads = select_first([threads, 1])
+task Fastq {
+ input {
+ String? preCommand
+ File inputBam
+ String outputRead1
+ String? outputRead2
+ String? outputRead0
+ Int? includeFilter
+ Int? excludeFilter
+ Int? excludeSpecificFilter
+ Boolean? appendReadNumber
+ Boolean? outputQuality
+ Int? compressionLevel
+ Int threads = 1
+ Int memory = 1
+ }
command {
- ${preCommand}
+ ~{preCommand}
samtools fastq \
- ${true="-1" false="-s" defined(outputRead2)} ${outputRead1} \
- ${"-2 " + outputRead2} \
- ${"-0 " + outputRead0} \
- ${"-f " + includeFilter} \
- ${"-F " + excludeFilter} \
- ${"-G " + excludeSpecificFilter} \
- ${true="-N" false="-n" appendReadNumber} \
- ${true="-O" false="" outputQuality} \
- ${"-c " + compressionLevel} \
- ${"--threads " + totalThreads} \
- ${inputBam}
+ ~{true="-1" false="-s" defined(outputRead2)} ~{outputRead1} \
+ ~{"-2 " + outputRead2} \
+ ~{"-0 " + outputRead0} \
+ ~{"-f " + includeFilter} \
+ ~{"-F " + excludeFilter} \
+ ~{"-G " + excludeSpecificFilter} \
+ ~{true="-N" false="-n" appendReadNumber} \
+ ~{true="-O" false="" outputQuality} \
+ ~{"-c " + compressionLevel} \
+ ~{"--threads " + threads} \
+ ~{inputBam}
}
+
output {
File read1 = outputRead1
File? read2 = outputRead2
File? read0 = outputRead0
}
+
runtime {
- cpu: totalThreads
- memory: select_first([memory, 1])
+ cpu: threads
+ memory: memory
}
+
parameter_meta {
preCommand: "A command that is run before the task. Can be used to activate environments"
inputBam: "The bam file to process."
@@ -115,39 +131,41 @@ 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
+task View {
+ input {
+ String? preCommand
+ File inFile
+ File? referenceFasta
+ String outputFileName
+ Boolean? outputBam
+ Boolean? uncompressedBamOutput
+ Int? includeFilter
+ Int? excludeFilter
+ Int? excludeSpecificFilter
+ Int threads = 1
+ Int memory = 1
+ }
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}
+ 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])
+ cpu: threads
+ memory: memory
}
}
diff --git a/seqtk.wdl b/seqtk.wdl
index 35fbedf368a7d62f1c9ed9643ea96fe0dd7a5a12..64c604a5ecfe0beba399605dcabb1bb3de0ee59a 100644
--- a/seqtk.wdl
+++ b/seqtk.wdl
@@ -1,26 +1,32 @@
-task sample {
- File sequenceFile
- String? outFilePath = "subsampledReads.fq.gz"
- String? preCommand
- Int? seed
- Boolean? twoPassMode
- Float? fraction
- Int? number
- Boolean? zip = true
+version 1.0
+
+task Sample {
+ input {
+ File sequenceFile
+ String outFilePath = "subsampledReads.fq.gz"
+ String? preCommand
+ Int? seed
+ Boolean twoPassMode
+ Float? fraction
+ Int? number
+ Boolean zip = true
+ }
command {
- set -e -o pipefail
- ${'mkdir -p $(dirname ' + outFilePath + ')'}
- ${preCommand}
- seqtk sample \
- ${"-s " + seed} \
- ${true="-2 " false="" twoPassMode} \
- ${sequenceFile} \
- ${number} ${fraction} \
- ${true="| gzip" false="" zip} \
- ${"> " + outFilePath}
+ set -e -o pipefail
+ mkdir -p $(dirname outFilePath)
+ ~{preCommand}
+ seqtk sample \
+ ~{"-s " + seed} \
+ ~{true="-2 " false="" twoPassMode} \
+ ~{sequenceFile} \
+ ~{number} \
+ ~{fraction} \
+ ~{true="| gzip" false="" zip} \
+ > ~{outFilePath}
}
+
output {
- File subsampledReads= select_first([outFilePath])
+ File subsampledReads = outFilePath
}
}
\ No newline at end of file
diff --git a/spades.wdl b/spades.wdl
index f0feb573ec4fb71f09ec5cb42f62fe45c4ed7cb8..47195f196967b8b1863b908d9c483ed49df9f978 100644
--- a/spades.wdl
+++ b/spades.wdl
@@ -1,68 +1,71 @@
-task spades {
- String outputDir
- String? preCommand
- File read1
- File? read2
- File? interlacedReads
- File? sangerReads
- File? pacbioReads
- File? nanoporeReads
- File? tslrContigs
- File? trustedContigs
- File? untrustedContigs
- Boolean? singleCell
- Boolean? metagenomic
- Boolean? rna
- Boolean? plasmid
- Boolean? ionTorrent
- Boolean? onlyErrorCorrection
- Boolean? onlyAssembler
- Boolean? careful
- Boolean? disableGzipOutput
- Boolean? disableRepeatResolution
- File? dataset
- Int? threads
- Float? memoryGb
- File? tmpDir
- String? k
- Float? covCutoff
- Int? phredOffset
- Int finalThreads = select_first([threads,1])
- Float totalMemory = select_first([memoryGb, finalThreads * 16.0])
- Int finalMemory = ceil(totalMemory)
- Int clusterMemory = ceil(totalMemory / finalThreads)
+version 1.0
+
+task Spades {
+ input {
+ String outputDir
+ String? preCommand
+ File read1
+ File? read2
+ File? interlacedReads
+ File? sangerReads
+ File? pacbioReads
+ File? nanoporeReads
+ File? tslrContigs
+ File? trustedContigs
+ File? untrustedContigs
+ Boolean? singleCell
+ Boolean? metagenomic
+ Boolean? rna
+ Boolean? plasmid
+ Boolean? ionTorrent
+ Boolean? onlyErrorCorrection
+ Boolean? onlyAssembler
+ Boolean? careful
+ Boolean? disableGzipOutput
+ Boolean? disableRepeatResolution
+ File? dataset
+ Int threads = 1
+ Float memoryGb = 16.0
+ File? tmpDir
+ String? k
+ Float? covCutoff
+ Int? phredOffset
+ }
+
+ Int clusterMemory = ceil(memoryGb / threads)
command {
set -e -o pipefail
- ${preCommand}
+ ~{preCommand}
spades.py \
- ${"-o " + outputDir} \
- ${true="--sc" false="" singleCell} \
- ${true="--meta" false="" metagenomic} \
- ${true="--rna" false="" rna} \
- ${true="--plasmid" false="" plasmid} \
- ${true="--iontorrent" false="" ionTorrent} \
- ${"--12 " + interlacedReads } \
- ${true="-1" false="-s" defined(read2)} ${read1} \
- ${"-2 " + read2 } \
- ${"--sanger " + sangerReads } \
- ${"--pacbio " + pacbioReads } \
- ${"--nanopore " + nanoporeReads } \
- ${"--tslr " + tslrContigs } \
- ${"--trusted-contigs " + trustedContigs } \
- ${"--untrusted-contigs " + untrustedContigs } \
- ${true="--only-error-correction" false="" onlyErrorCorrection } \
- ${true="--only-assembler" false="" onlyAssembler } \
- ${true="--careful" false="" careful } \
- ${true="--disable-gzip-output" false="" disableGzipOutput} \
- ${true="--disable-rr" false="" disableRepeatResolution } \
- ${"--dataset " + dataset } \
- ${"--threads " + finalThreads} \
- ${"--memory " + finalMemory } \
- ${"-k " + k } \
- ${"--cov-cutoff " + covCutoff } \
- ${"--phred-offset " + phredOffset }
+ ~{"-o " + outputDir} \
+ ~{true="--sc" false="" singleCell} \
+ ~{true="--meta" false="" metagenomic} \
+ ~{true="--rna" false="" rna} \
+ ~{true="--plasmid" false="" plasmid} \
+ ~{true="--iontorrent" false="" ionTorrent} \
+ ~{"--12 " + interlacedReads} \
+ ~{true="-1" false="-s" defined(read2)} ~{read1} \
+ ~{"-2 " + read2} \
+ ~{"--sanger " + sangerReads} \
+ ~{"--pacbio " + pacbioReads} \
+ ~{"--nanopore " + nanoporeReads} \
+ ~{"--tslr " + tslrContigs} \
+ ~{"--trusted-contigs " + trustedContigs} \
+ ~{"--untrusted-contigs " + untrustedContigs} \
+ ~{true="--only-error-correction" false="" onlyErrorCorrection} \
+ ~{true="--only-assembler" false="" onlyAssembler} \
+ ~{true="--careful" false="" careful} \
+ ~{true="--disable-gzip-output" false="" disableGzipOutput} \
+ ~{true="--disable-rr" false="" disableRepeatResolution} \
+ ~{"--dataset " + dataset} \
+ ~{"--threads " + threads} \
+ ~{"--memory " + memoryGb} \
+ ~{"-k " + k} \
+ ~{"--cov-cutoff " + covCutoff} \
+ ~{"--phred-offset " + phredOffset}
}
+
output {
Array[File] correctedReads = glob(outputDir + "/corrected/*.fastq*")
File scaffolds = outputDir + "/scaffolds.fasta"
@@ -74,8 +77,9 @@ task spades {
File params = outputDir + "/params.txt"
File log = outputDir + "/spades.log"
}
+
runtime {
- cpu: finalThreads
+ cpu: threads
memory: clusterMemory
}
}
\ No newline at end of file
diff --git a/star.wdl b/star.wdl
index 941a1d60137ad31dbc4ab7cbe7d8f6616bbee7b5..e03f6301052b648f2b86cd126e5ecfd9bdd27aed 100644
--- a/star.wdl
+++ b/star.wdl
@@ -1,62 +1,65 @@
+version 1.0
+
task Star {
- String? preCommand
+ input {
+ String? preCommand
- Array[File] inputR1
- Array[File]? inputR2
- String genomeDir
- String outFileNamePrefix
+ Array[File] inputR1
+ Array[File]? inputR2
+ String genomeDir
+ String outFileNamePrefix
- String? outSAMtype
- String? readFilesCommand
- Int? runThreadN
- String? outStd
- String? twopassMode
- Array[String]? outSAMattrRGline
- Int? limitBAMsortRAM
+ String outSAMtype = "BAM SortedByCoordinate"
+ String readFilesCommand = "zcat"
+ Int runThreadN = 1
+ String? outStd
+ String? twopassMode
+ Array[String]? outSAMattrRGline
+ Int? limitBAMsortRAM
- Int? memory
+ Int memory = 10
+ }
#TODO needs to be extended for all possible output extensions
Map[String, String] samOutputNames = {"BAM SortedByCoordinate": "sortedByCoord.out.bam"}
- # converts String? to String for use as key (for the Map above) in output
- String key = select_first([outSAMtype, "BAM SortedByCoordinate"])
-
command {
set -e -o pipefail
- mkdir -p ${sub(outFileNamePrefix, basename(outFileNamePrefix) + "$", "")}
- ${preCommand}
+ mkdir -p ~{sub(outFileNamePrefix, basename(outFileNamePrefix) + "$", "")}
+ ~{preCommand}
STAR \
- --readFilesIn ${sep=',' inputR1} ${sep="," inputR2} \
- --outFileNamePrefix ${outFileNamePrefix} \
- --genomeDir ${genomeDir} \
- --outSAMtype ${default="BAM SortedByCoordinate" outSAMtype} \
- --readFilesCommand ${default="zcat" readFilesCommand} \
- ${"--runThreadN " + runThreadN} \
- ${"--outStd " + outStd} \
- ${"--twopassMode " + twopassMode} \
- ${"--limitBAMsortRAM " + limitBAMsortRAM} \
- ${true="--outSAMattrRGline " false="" defined(outSAMattrRGline)} ${sep=" , " outSAMattrRGline}
+ --readFilesIn ~{sep=',' inputR1} ~{sep="," inputR2} \
+ --outFileNamePrefix ~{outFileNamePrefix} \
+ --genomeDir ~{genomeDir} \
+ --outSAMtype ~{outSAMtype} \
+ --readFilesCommand ~{readFilesCommand} \
+ ~{"--runThreadN " + runThreadN} \
+ ~{"--outStd " + outStd} \
+ ~{"--twopassMode " + twopassMode} \
+ ~{"--limitBAMsortRAM " + limitBAMsortRAM} \
+ ~{true="--outSAMattrRGline " false="" defined(outSAMattrRGline)} ~{sep=" , " outSAMattrRGline}
}
output {
- File bamFile = outFileNamePrefix + "Aligned." + samOutputNames[key]
+ File bamFile = outFileNamePrefix + "Aligned." + samOutputNames[outSAMtype]
}
runtime {
- cpu: select_first([runThreadN, 1])
- memory: select_first([memory, 10])
+ cpu: runThreadN
+ memory: memory
}
}
-task makeStarRGline {
- String sample
- String library
- String? platform
- String readgroup
+task MakeStarRGline {
+ input {
+ String sample
+ String library
+ String platform = "ILLUMINA"
+ String readgroup
+ }
command {
- printf '"ID:${readgroup}" "LB:${library}" "PL:${default="ILLUMINA" platform}" "SM:${sample}"'
+ printf '"ID:~{readgroup}" "LB:~{library}" "PL:~{platform}" "SM:~{sample}"'
}
output {
diff --git a/stringtie.wdl b/stringtie.wdl
index f5c6854cbacb671113fde7b4a0ac6e459e128ac1..97455da498f722ddf05008fc7102c9eef360335e 100644
--- a/stringtie.wdl
+++ b/stringtie.wdl
@@ -1,26 +1,29 @@
+version 1.0
+
task Stringtie {
- String? preCommand
- File alignedReads
- File? referenceGtf
- Int? threads
- String assembledTranscriptsFile
- Boolean? firstStranded
- Boolean? secondStranded
- String? geneAbundanceFile
+ input {
+ String? preCommand
+ File alignedReads
+ File? referenceGtf
+ Int threads = 1
+ String assembledTranscriptsFile
+ Boolean? firstStranded
+ Boolean? secondStranded
+ String? geneAbundanceFile
+ }
command {
set -e -o pipefail
- mkdir -p $(dirname ${assembledTranscriptsFile})
- ${preCommand}
+ mkdir -p $(dirname ~{assembledTranscriptsFile})
+ ~{preCommand}
stringtie \
- ${"-p " + threads} \
- ${"-G " + referenceGtf} \
- ${true="--rf" false="" firstStranded} \
- ${true="fr" false="" secondStranded} \
- -o ${assembledTranscriptsFile} \
- ${"-A " + geneAbundanceFile} \
- ${alignedReads} \
-
+ ~{"-p " + threads} \
+ ~{"-G " + referenceGtf} \
+ ~{true="--rf" false="" firstStranded} \
+ ~{true="fr" false="" secondStranded} \
+ -o ~{assembledTranscriptsFile} \
+ ~{"-A " + geneAbundanceFile} \
+ ~{alignedReads}
}
output {
@@ -29,6 +32,6 @@ task Stringtie {
}
runtime {
- cpu: select_first([threads, 1])
+ cpu: threads
}
}
\ No newline at end of file
diff --git a/unicycler.wdl b/unicycler.wdl
index f7aa36a48067bcd2f880a843d1a4aa401c7f5078..c5b30ba93c184a1aef7417e16997053ca507101e 100644
--- a/unicycler.wdl
+++ b/unicycler.wdl
@@ -1,102 +1,107 @@
-task unicycler {
- String? preCommand
- File? short1
- File? short2
- File? unpaired
- File? long
- String out
- Int? verbosity
- Int? minFastaLength
- Int? keep
- Boolean? vcf
- Int? threads
- Int? memory
- Int finalThreads = select_first(threads, 1)
- Int finalMemory = select_first(memory, 4)
- String? mode
- Float? minBridgeQual
- Int? linearSeqs
- File? spadesPath
- Boolean? noCorrect
- Float? minKmerFrac
- Float? maxKmerFrac
- Int? kmerCount
- Float? depthFilter
- Boolean? noMiniasm
- File? raconPath
- File? existingLongReadAssembly
- Boolean? noRotate
- File? startGenes
- Float? startGeneId
- Float? startGeneCov
- String? makeblastdbPath
- File? tblastnPath
- Boolean? noPilon
- File? bowtie2Path
- File? bowtie2buildPath
- File? samtoolsPath
- File? pilonPath
- File? javaPath
- Int? minPolishSize
- File? bcftoolsPath
- Int? minComponentSize
- Int? minDeadEndSize
- File? contamination
- String? scores
- String? lowScore
+version 1.0
+
+task Unicycler {
+ input {
+ String? preCommand
+ File? short1
+ File? short2
+ File? unpaired
+ File? long
+ String out
+ Int? verbosity
+ Int? minFastaLength
+ Int? keep
+ Boolean? vcf
+ Int threads = 1
+ Int memory = 4
+ String? mode
+ Float? minBridgeQual
+ Int? linearSeqs
+ File? spadesPath
+ Boolean? noCorrect
+ Float? minKmerFrac
+ Float? maxKmerFrac
+ Int? kmerCount
+ Float? depthFilter
+ Boolean? noMiniasm
+ File? raconPath
+ File? existingLongReadAssembly
+ Boolean? noRotate
+ File? startGenes
+ Float? startGeneId
+ Float? startGeneCov
+ String? makeblastdbPath
+ File? tblastnPath
+ Boolean? noPilon
+ File? bowtie2Path
+ File? bowtie2buildPath
+ File? samtoolsPath
+ File? pilonPath
+ File? javaPath
+ Int? minPolishSize
+ File? bcftoolsPath
+ Int? minComponentSize
+ Int? minDeadEndSize
+ File? contamination
+ String? scores
+ String? lowScore
+ }
+
command {
set -e -o pipefail
- mkdir -p ${out}
- ${preCommand}
+ mkdir -p ~{out}
+ ~{preCommand}
unicycler \
- ${"--short1 " + short1} \
- ${"--short2 " + short2} \
- ${"--unpaired " + unpaired} \
- ${"--long " + long} \
- --out ${out} \
- ${"--min_fasta_length " + minFastaLength} \
- ${"--keep " + keep } \
- ${true="--vcf" false="" vcf } \
- ${"--threads " + finalThreads } \
- ${"--mode " + mode } \
- ${"--min_bridge_qual " + minBridgeQual } \
- ${"--linear_seqs " + linearSeqs } \
- ${"--spades_path " + spadesPath } \
- ${true="--no_correct" false="" noCorrect } \
- ${"--min_kmer_frac " + minKmerFrac } \
- ${"--max_kmer_frac " + maxKmerFrac } \
- ${"--kmer_count " + kmerCount } \
- ${"--depth_filter " + depthFilter } \
- ${true="--no_miniasm" false="" noMiniasm } \
- ${"--racon_path " + raconPath } \
- ${"--existing_long_read_assembly " + existingLongReadAssembly } \
- ${true="--no_rotate" false="" noRotate } \
- ${"--start_genes " + startGenes } \
- ${"--start_gene_id " + startGeneId } \
- ${"--start_gene_cov " + startGeneCov } \
- ${"--makeblastdb_path " + makeblastdbPath } \
- ${"--tblastn_path " + tblastnPath } \
- ${true="--no_pilon" false="" noPilon } \
- ${"--bowtie2_path " + bowtie2Path } \
- ${"--bowtie2_build_path " + bowtie2buildPath } \
- ${"--samtools_path " + samtoolsPath } \
- ${"--pilon_path " + pilonPath } \
- ${"--java_path " + javaPath } \
- ${"--min_polish_size " + minPolishSize } \
- ${"--bcftools_path " + bcftoolsPath } \
- ${"--min_component_size " + minComponentSize } \
- ${"--min_dead_end_size " + minDeadEndSize } \
- ${"--contamination " + contamination } \
- ${"--scores " + scores } \
- ${"--low_score " + lowScore }
+ ~{"--short1 " + short1} \
+ ~{"--short2 " + short2} \
+ ~{"--unpaired " + unpaired} \
+ ~{"--long " + long} \
+ --out ~{out} \
+ ~{"--min_fasta_length " + minFastaLength} \
+ ~{"--keep " + keep } \
+ ~{true="--vcf" false="" vcf } \
+ ~{"--threads " + threads } \
+ ~{"--mode " + mode } \
+ ~{"--min_bridge_qual " + minBridgeQual } \
+ ~{"--linear_seqs " + linearSeqs } \
+ ~{"--spades_path " + spadesPath } \
+ ~{true="--no_correct" false="" noCorrect } \
+ ~{"--min_kmer_frac " + minKmerFrac } \
+ ~{"--max_kmer_frac " + maxKmerFrac } \
+ ~{"--kmer_count " + kmerCount } \
+ ~{"--depth_filter " + depthFilter } \
+ ~{true="--no_miniasm" false="" noMiniasm } \
+ ~{"--racon_path " + raconPath } \
+ ~{"--existing_long_read_assembly " + existingLongReadAssembly } \
+ ~{true="--no_rotate" false="" noRotate } \
+ ~{"--start_genes " + startGenes } \
+ ~{"--start_gene_id " + startGeneId } \
+ ~{"--start_gene_cov " + startGeneCov } \
+ ~{"--makeblastdb_path " + makeblastdbPath } \
+ ~{"--tblastn_path " + tblastnPath } \
+ ~{true="--no_pilon" false="" noPilon } \
+ ~{"--bowtie2_path " + bowtie2Path } \
+ ~{"--bowtie2_build_path " + bowtie2buildPath } \
+ ~{"--samtools_path " + samtoolsPath } \
+ ~{"--pilon_path " + pilonPath } \
+ ~{"--java_path " + javaPath } \
+ ~{"--min_polish_size " + minPolishSize } \
+ ~{"--bcftools_path " + bcftoolsPath } \
+ ~{"--min_component_size " + minComponentSize } \
+ ~{"--min_dead_end_size " + minDeadEndSize } \
+ ~{"--contamination " + contamination } \
+ ~{"--scores " + scores } \
+ ~{"--low_score " + lowScore }
}
+
output {
File assemblyFasta = out + "/assembly.fasta"
File assemblyGfa = out + "/assembly.gfa"
File log = out + "/unicycler.log"
}
+
runtime {
- cpu: finalThreads
- memory: finalMemory
+ cpu: threads
+ memory: memory
}
}
\ No newline at end of file