diff --git a/biopet/biopet.wdl b/biopet/biopet.wdl
index 2f6f1c53bef8e7d28002241c5404a17b98d8d4d6..20ada8108243f23c01e9292d484ce4b5564cec73 100644
--- a/biopet/biopet.wdl
+++ b/biopet/biopet.wdl
@@ -205,54 +205,60 @@ task FastqSync {
task ReorderGlobbedScatters {
input {
Array[File]+ scatters
- String scatterDir
+ # Should not be changed from the main pipeline. As it should not influence results.
+ String dockerTag = "3.6"
}
command <<<
+ set -e
+ # Copy all the scatter files to the CWD so the output matches paths in
+ # the cwd.
+ for file in ~{sep=" " scatters}
+ do cp $file .
+ done
python << CODE
from os.path import basename
scatters = ['~{sep="','" scatters}']
splitext = [basename(x).split(".") for x in scatters]
splitnum = [x.split("-") + [y] for x,y in splitext]
ordered = sorted(splitnum, key=lambda x: int(x[1]))
- merged = ["~{scatterDir}/{}-{}.{}".format(x[0],x[1],x[2]) for x in ordered]
+ merged = ["{}-{}.{}".format(x[0],x[1],x[2]) for x in ordered]
for x in merged:
print(x)
CODE
>>>
output {
- Array[String] reorderedScatters = read_lines(stdout())
+ Array[File] reorderedScatters = read_lines(stdout())
}
runtime {
- memory: 1
+ docker: "python:" + dockerTag
+ # 4 gigs of memory to be able to build the docker image in singularity
+ memory: 4
}
}
task ScatterRegions {
input {
- String? preCommand
Reference reference
- String outputDirPath
- File? toolJar
Int? scatterSize
File? regions
Boolean notSplitContigs = false
-
Int memory = 4
Float memoryMultiplier = 3.0
+ String dockerTag = "0.2--0"
}
- String toolCommand = if defined(toolJar)
- then "java -Xmx" + memory + "G -jar " +toolJar
- else "biopet-scatterregions -Xmx" + memory + "G"
+ # OutDirPath must be defined here because the glob process relies on
+ # linking. This path must be in the containers filesystem, otherwise the
+ # linking does not work.
+ String outputDirPath = "scatters"
command {
set -e -o pipefail
- ~{preCommand}
mkdir -p ~{outputDirPath}
- ~{toolCommand} \
+ biopet-scatterregions -Xmx~{memory}G \
-R ~{reference.fasta} \
-o ~{outputDirPath} \
~{"-s " + scatterSize} \
@@ -265,6 +271,7 @@ task ScatterRegions {
}
runtime {
+ docker: "quay.io/biocontainers/biopet-scatterregions:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
diff --git a/gatk.wdl b/gatk.wdl
index b72d9a61c708d4b06c8ff415d6b584285641c718..8c5e42538ec4586c858181b042d109b277eb5cbb 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -5,8 +5,6 @@ import "common.wdl"
# Apply Base Quality Score Recalibration (BQSR) model
task ApplyBQSR {
input {
- String? preCommand
- File? gatkJar
IndexedBamFile inputBam
String outputBamPath
File recalibrationReport
@@ -15,28 +13,25 @@ task ApplyBQSR {
Int memory = 4
Float memoryMultiplier = 3.0
+ String dockerTag = "4.1.0.0--0"
}
- String toolCommand = if defined(gatkJar)
- 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 ~{reference.fasta} \
- -I ~{inputBam.file} \
- --use-original-qualities \
- -O ~{outputBamPath} \
- -bqsr ~{recalibrationReport} \
- --static-quantized-quals 10 \
- --static-quantized-quals 20 \
- --static-quantized-quals 30 \
- -L ~{sep=" -L " sequenceGroupInterval}
+ mkdir -p $(dirname ~{outputBamPath})
+ gatk --java-options -Xmx~{memory}G \
+ ApplyBQSR \
+ --create-output-bam-md5 \
+ --add-output-sam-program-record \
+ -R ~{reference.fasta} \
+ -I ~{inputBam.file} \
+ --use-original-qualities \
+ -O ~{outputBamPath} \
+ -bqsr ~{recalibrationReport} \
+ --static-quantized-quals 10 \
+ --static-quantized-quals 20 \
+ --static-quantized-quals 30 \
+ -L ~{sep=" -L " sequenceGroupInterval}
}
output {
@@ -48,6 +43,7 @@ task ApplyBQSR {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
@@ -55,8 +51,6 @@ task ApplyBQSR {
# Generate Base Quality Score Recalibration (BQSR) model
task BaseRecalibrator {
input {
- String? preCommand
- File? gatkJar
IndexedBamFile inputBam
String recalibrationReportPath
Array[File]+ sequenceGroupInterval
@@ -66,6 +60,7 @@ task BaseRecalibrator {
Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
+ String dockerTag = "4.1.0.0--0"
}
Array[File]+ knownIndelsSitesVCFsArg = flatten([
@@ -73,14 +68,10 @@ task BaseRecalibrator {
[select_first([dbsnpVCF]).file]
])
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{recalibrationReportPath})
+ gatk --java-options -Xmx~{memory}G \
BaseRecalibrator \
-R ~{reference.fasta} \
-I ~{inputBam.file} \
@@ -95,35 +86,28 @@ task BaseRecalibrator {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
task CombineGVCFs {
input {
- String? preCommand
Array[File]+ gvcfFiles
Array[File]+ gvcfFilesIndex
Array[File]+ intervals
-
String outputPath
-
- String? gatkJar
-
Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
+ String dockerTag = "4.1.0.0--0"
}
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{outputPath})
+ gatk --java-options -Xmx~{memory}G \
CombineGVCFs \
-R ~{reference.fasta} \
-O ~{outputPath} \
@@ -139,6 +123,7 @@ task CombineGVCFs {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
@@ -146,23 +131,18 @@ task CombineGVCFs {
# Combine multiple recalibration tables from scattered BaseRecalibrator runs
task GatherBqsrReports {
input {
- String? preCommand
- String? gatkJar
Array[File] inputBQSRreports
String outputReportPath
Int memory = 4
Float memoryMultiplier = 3.0
+ String dockerTag = "4.1.0.0--0"
}
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{outputReportPath})
+ gatk --java-options -Xmx~{memory}G \
GatherBQSRReports \
-I ~{sep=' -I ' inputBQSRreports} \
-O ~{outputReportPath}
@@ -173,39 +153,31 @@ task GatherBqsrReports {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
task GenotypeGVCFs {
input {
- String? preCommand
Array[File]+ gvcfFiles
Array[File]+ gvcfFilesIndex
Array[File]+ intervals
-
String outputPath
-
- String? gatkJar
-
Reference reference
-
IndexedVcfFile? dbsnpVCF
Int memory = 6
Float memoryMultiplier = 2.0
+ String dockerTag = "4.1.0.0--0"
}
File dbsnpFile = if (defined(dbsnpVCF)) then select_first([dbsnpVCF]).file else ""
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{outputPath})
+ gatk --java-options -Xmx~{memory}G \
GenotypeGVCFs \
-R ~{reference.fasta} \
-O ~{outputPath} \
@@ -224,7 +196,8 @@ task GenotypeGVCFs {
}
}
- runtime{
+ runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
@@ -232,31 +205,25 @@ task GenotypeGVCFs {
# Call variants on a single sample with HaplotypeCaller to produce a GVCF
task HaplotypeCallerGvcf {
input {
- String? preCommand
Array[File]+ inputBams
Array[File]+ inputBamsIndex
Array[File]+ intervalList
String gvcfPath
Reference reference
Float contamination = 0.0
- String? gatkJar
-
IndexedVcfFile? dbsnpVCF
Int memory = 4
Float memoryMultiplier = 3
+ String dockerTag = "4.1.0.0--0"
}
File dbsnpFile = if (defined(dbsnpVCF)) then select_first([dbsnpVCF]).file else ""
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{gvcfPath})
+ gatk --java-options -Xmx~{memory}G \
HaplotypeCaller \
-R ~{reference.fasta} \
-O ~{gvcfPath} \
@@ -275,14 +242,13 @@ task HaplotypeCallerGvcf {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
task MuTect2 {
input {
- String? preCommand
-
Array[File]+ inputBams
Array[File]+ inputBamsIndex
Reference reference
@@ -291,19 +257,15 @@ task MuTect2 {
String? normalSample
Array[File]+ intervals
- String? gatkJar
Int memory = 4
Float memoryMultiplier = 3
+ String dockerTag = "4.1.0.0--0"
}
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{outputVcf})
+ gatk --java-options -Xmx~{memory}G \
Mutect2 \
-R ~{reference.fasta} \
-I ~{sep=" -I " inputBams} \
@@ -321,32 +283,27 @@ task MuTect2 {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
task SplitNCigarReads {
input {
- String? preCommand
-
IndexedBamFile inputBam
Reference reference
String outputBam
- String? gatkJar
Array[File]+ intervals
Int memory = 4
Float memoryMultiplier = 4
+ String dockerTag = "4.1.0.0--0"
}
- String toolCommand = if defined(gatkJar)
- then "java -Xmx" + memory + "G -jar " + gatkJar
- else "gatk --java-options -Xmx" + memory + "G"
-
command {
set -e -o pipefail
- ~{preCommand}
- ~{toolCommand} \
+ mkdir -p $(dirname ~{outputBam})
+ gatk --java-options -Xmx~{memory}G \
SplitNCigarReads \
-I ~{inputBam.file} \
-R ~{reference.fasta} \
@@ -362,6 +319,7 @@ task SplitNCigarReads {
}
runtime {
+ docker: "quay.io/biocontainers/gatk4:" + dockerTag
memory: ceil(memory * memoryMultiplier)
}
}
diff --git a/samtools.wdl b/samtools.wdl
index 077631dd99d9b7cfd7c7048c53c20f02cebf4ff8..895041c28b74848813935520a94aa62adfae40a6 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -7,6 +7,7 @@ task BgzipAndIndex {
File inputFile
String outputDir
String type = "vcf"
+ String dockerTag = "0.2.6--ha92aebf_0"
}
String outputGz = outputDir + "/" + basename(inputFile) + ".gz"
@@ -20,6 +21,10 @@ task BgzipAndIndex {
File compressed = outputGz
File index = outputGz + ".tbi"
}
+
+ runtime {
+ docker: "quay.io/biocontainers/tabix:" + dockerTag
+ }
}
task Index {
@@ -185,6 +190,7 @@ task Tabix {
input {
String inputFile
String type = "vcf"
+ String dockerTag = "0.2.6--ha92aebf_0"
}
command {
@@ -194,6 +200,10 @@ task Tabix {
output {
File index = inputFile + ".tbi"
}
+
+ runtime {
+ docker: "quay.io/biocontainers/tabix:" + dockerTag
+ }
}
task View {