diff --git a/CHANGELOG.md b/CHANGELOG.md
index 18a90306edaa4ff27d7da72480e6271c3dbf4eab..05e657222fe9588d0d55231e71f075e4cc0a8437 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,17 @@ that users understand how the changes affect the new version.
version 2.2.0-dev
---------------------------
+ Add `memory` input to fastqc task.
++ Added GATK CNV calling tasks:
+ + AnnotateIntervals
+ + CallCopyRatioSegments
+ + CollectAllelicCounts
+ + CollectReadCounts
+ + CreateReadCountPanelOfNormals
+ + DenoiseReadCounts
+ + ModelSegments
+ + PlotDenoisedCopyRatios
+ + PlotModeledSegments
+ + PreprocessIntervals
+ Add common.TextToFile task.
+ Add bedtools.Intersect.
+ Add `-o pipefail` to bedtools.MergeBedFiles to prevent errors in BED files
diff --git a/gatk.wdl b/gatk.wdl
index 0b4c71c701b6d7a2ef1013b6ddeef8f77ff6c612..eff98bf8b1260f14d9691c2ebb92235916ad4c21 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -1,5 +1,83 @@
version 1.0
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task AnnotateIntervals {
+ input {
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ String annotatedIntervalsPath = "intervals.annotated.tsv"
+ File intervals
+ String intervalMergingRule = "OVERLAPPING_ONLY"
+ File? mappabilityTrack
+ File? segmentalDuplicationTrack
+ Int featureQueryLookahead = 1000000
+
+ String memory = "10G"
+ String javaXmx = "2G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{annotatedIntervalsPath})"
+ gatk --java-options -Xmx~{javaXmx} \
+ AnnotateIntervals \
+ -R ~{referenceFasta} \
+ -L ~{intervals} \
+ ~{"--mappability-track " + mappabilityTrack} \
+ ~{"--segmental-duplication-track " + segmentalDuplicationTrack} \
+ --feature-query-lookahead ~{featureQueryLookahead} \
+ --interval-merging-rule ~{intervalMergingRule} \
+ -O ~{annotatedIntervalsPath}
+ }
+
+ output {
+ File annotatedIntervals = annotatedIntervalsPath
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ referenceFasta: {description: "The reference fasta file.", category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
+ referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ annotatedIntervalsPath: {description: "The location the output should be written to.", category: "advanced"}
+ intervals: {description: "An interval list describinig the intervals to annotate.", category: "required"}
+ intervalMergingRule: {description: "Equivalent to gatk AnnotateIntervals' `--interval-merging-rule` option.", category: "advanced"}
+ mappabilityTrack: {description: "Equivalent to gatk AnnotateIntervals' `--mappability-track` option.", category: "common"}
+ segmentalDuplicationTrack: {description: "Equivalent to gatk AnnotateIntervals' `--segmenta-duplicarion-track` option.", category: "common"}
+ featureQueryLookahead: {description: "Equivalent to gatk AnnotateIntervals' `--feature-query-lookahead` option", category: "advanced"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
# Apply Base Quality Score Recalibration (BQSR) model
task ApplyBQSR {
input {
@@ -132,35 +210,29 @@ task BaseRecalibrator {
}
}
-task CombineGVCFs {
+task CalculateContamination {
input {
- Array[File]+ gvcfFiles
- Array[File]+ gvcfFilesIndex
- Array[File] intervals = []
- String outputPath
- File referenceFasta
- File referenceFastaDict
- File referenceFastaFai
+ File tumorPileups
+ File? normalPileups
String memory = "24G"
String javaXmx = "12G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
}
command {
set -e
- mkdir -p "$(dirname ~{outputPath})"
gatk --java-options -Xmx~{javaXmx} \
- CombineGVCFs \
- -R ~{referenceFasta} \
- -O ~{outputPath} \
- -V ~{sep=' -V ' gvcfFiles} \
- ~{true='-L' false='' length(intervals) > 0} ~{sep=' -L ' intervals}
+ CalculateContamination \
+ -I ~{tumorPileups} \
+ ~{"-matched " + normalPileups} \
+ -O "contamination.table" \
+ --tumor-segmentation "segments.table"
}
output {
- File outputVcf = outputPath
- File outputVcfIndex = outputPath + ".tbi"
+ File contaminationTable = "contamination.table"
+ File mafTumorSegments = "segments.table"
}
runtime {
@@ -169,16 +241,8 @@ task CombineGVCFs {
}
parameter_meta {
- gvcfFiles: {description: "The GVCF files to be combined.", category: "required"}
- gvcfFilesIndex: {description: "The indexes for the GVCF files.", caregory: "required"}
- intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "advanced"}
- outputPath: {description: "The location the combined GVCF should be written to.", category: "required"}
- referenceFasta: {description: "The reference fasta file which was also used for mapping.",
- category: "required"}
- referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
- category: "required"}
- referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
-
+ tumorPileups: {description: "The pileup summary of a tumor/case sample.", category: "required"}
+ normalPileups: {description: "The pileup summary of the normal/control sample.", category: "common"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -187,28 +251,28 @@ task CombineGVCFs {
}
}
-# Combine multiple recalibration tables from scattered BaseRecalibrator runs
-task GatherBqsrReports {
+task CallCopyRatioSegments {
input {
- Array[File] inputBQSRreports
- String outputReportPath
+ String outputPrefix
+ File copyRatioSegments
- String memory = "12G"
- String javaXmx = "4G"
+ String memory = "21G"
+ String javaXmx = "6G"
String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
- mkdir -p "$(dirname ~{outputReportPath})"
+ mkdir -p "$(dirname ~{outputPrefix})"
gatk --java-options -Xmx~{javaXmx} \
- GatherBQSRReports \
- -I ~{sep=' -I ' inputBQSRreports} \
- -O ~{outputReportPath}
+ CallCopyRatioSegments \
+ -I ~{copyRatioSegments} \
+ -O ~{outputPrefix}.called.seg
}
output {
- File outputBQSRreport = outputReportPath
+ File calledSegments = outputPrefix + ".called.seg"
+ File calledSegmentsIgv = outputPrefix + ".called.igv.seg"
}
runtime {
@@ -217,9 +281,8 @@ task GatherBqsrReports {
}
parameter_meta {
- inputBQSRreports: {description: "The BQSR reports to be merged.", category: "required"}
- outputReportPath: {description: "The location of the combined BQSR report.", category: "required"}
-
+ outputPrefix: {description: "The prefix for the output files.", category: "required"}
+ copyRatioSegments: {description: "The copy ratios file generated by gatk ModelSegments.", category: "required"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -228,42 +291,33 @@ task GatherBqsrReports {
}
}
-task GenotypeGVCFs {
+task CollectAllelicCounts {
input {
- Array[File]+ gvcfFiles
- Array[File]+ gvcfFilesIndex
- Array[File]+ intervals
- String outputPath
+ String allelicCountsPath = "allelic_counts.tsv"
+ File commonVariantSites
+ File inputBam
+ File inputBamIndex
File referenceFasta
File referenceFastaDict
File referenceFastaFai
- File? dbsnpVCF
- File? dbsnpVCFIndex
-
- String memory = "18G"
- String javaXmx = "6G"
+ String memory = "90G"
+ String javaXmx = "30G"
String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
- mkdir -p "$(dirname ~{outputPath})"
+ mkdir -p "$(dirname ~{allelicCountsPath})"
gatk --java-options -Xmx~{javaXmx} \
- GenotypeGVCFs \
+ CollectAllelicCounts \
+ -L ~{commonVariantSites} \
+ -I ~{inputBam} \
-R ~{referenceFasta} \
- -O ~{outputPath} \
- ~{true="-D" false="" defined(dbsnpVCF)} ~{dbsnpVCF} \
- -G StandardAnnotation \
- --only-output-calls-starting-in-intervals \
- -new-qual \
- -V ~{sep=' -V ' gvcfFiles} \
- -L ~{sep=' -L ' intervals}
+ -O ~{allelicCountsPath}
}
output {
- File outputVCF = outputPath
- File outputVCFIndex = outputPath + ".tbi"
-
+ File allelicCounts = allelicCountsPath
}
runtime {
@@ -272,18 +326,13 @@ task GenotypeGVCFs {
}
parameter_meta {
- gvcfFiles: {description: "The GVCF files to be genotypes.", category: "required"}
- gvcfFilesIndex: {description: "The index of the input GVCF files.", category: "required"}
- intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "required"}
- outputPath: {description: "The location to write the output VCF file to.", category: "required"}
- referenceFasta: {description: "The reference fasta file which was also used for mapping.",
- category: "required"}
- referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
- category: "required"}
+ allelicCountsPath: {description: "The path the output should be written to.", category: "advanced"}
+ commonVariantSites: {description: "Interval list of common vairat sies (to retrieve the allelic counts for).", category: "required"}
+ inputBam: {description: "The BAM file to generate counts for.", category: "required"}
+ inputBamIndex: {description: "The index of the input BAM file.", category: "required"}
+ referenceFasta: {description: "The reference fasta file.", category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- dbsnpVCF: {description: "A dbSNP VCF.", category: "common"}
- dbsnpVCFIndex: {description: "The index for the dbSNP VCF.", category: "common"}
-
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -292,46 +341,37 @@ task GenotypeGVCFs {
}
}
-# Call variants on a single sample with HaplotypeCaller to produce a GVCF
-task HaplotypeCallerGvcf {
+task CollectReadCounts {
input {
- Array[File]+ inputBams
- Array[File]+ inputBamsIndex
- Array[File]+? intervalList
- Array[File]+? excludeIntervalList
- String gvcfPath
+ String countsPath = "readcounts.hdf5"
+ File intervals
+ File inputBam
+ File inputBamIndex
File referenceFasta
- File referenceFastaIndex
File referenceFastaDict
- Float contamination = 0.0
- File? dbsnpVCF
- File? dbsnpVCFIndex
- Int? ploidy
+ File referenceFastaFai
+ String intervalMergingRule = "OVERLAPPING_ONLY"
- String memory = "12G"
- String javaXmx = "4G"
+ String memory = "35G"
+ String javaXmx = "7G"
String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
- mkdir -p "$(dirname ~{gvcfPath})"
+ mkdir -p "$(dirname ~{countsPath})"
gatk --java-options -Xmx~{javaXmx} \
- HaplotypeCaller \
+ CollectReadCounts \
+ -L ~{intervals} \
+ -I ~{inputBam} \
-R ~{referenceFasta} \
- -O ~{gvcfPath} \
- -I ~{sep=" -I " inputBams} \
- ~{"--sample-ploidy " + ploidy} \
- ~{true="-L" false="" defined(intervalList)} ~{sep=' -L ' intervalList} \
- ~{true="-XL" false="" defined(excludeIntervalList)} ~{sep=' -XL ' excludeIntervalList} \
- ~{true="-D" false="" defined(dbsnpVCF)} ~{dbsnpVCF} \
- -contamination ~{contamination} \
- -ERC GVCF
+ --format HDF5 \
+ --interval-merging-rule ~{intervalMergingRule} \
+ -O ~{countsPath}
}
output {
- File outputGVCF = gvcfPath
- File outputGVCFIndex = gvcfPath + ".tbi"
+ File counts = countsPath
}
runtime {
@@ -340,21 +380,14 @@ task HaplotypeCallerGvcf {
}
parameter_meta {
- inputBams: {description: "The BAM files on which to perform variant calling.", category: "required"}
- inputBamsIndex: {description: "The indexes for the input BAM files.", category: "required"}
- intervalList: {description: "Bed files or interval lists describing the regions to operate on.", category: "common"}
- excludeIntervalList: {description: "Bed files or interval lists describing the regions to NOT operate on.", category: "common"}
- gvcfPath: {description: "The location to write the output GVCF to.", category: "required"}
- ploidy: {description: "The ploidy with which the variants should be called.", category: "common"}
- referenceFasta: {description: "The reference fasta file which was also used for mapping.",
- category: "required"}
- referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
- category: "required"}
- referenceFastaIndex: {description: "The index for the reference fasta file.", category: "required"}
- contamination: {description: "Equivalent to HaplotypeCaller's `-contamination` option.", category: "advanced"}
- dbsnpVCF: {description: "A dbSNP VCF.", category: "common"}
- dbsnpVCFIndex: {description: "The index for the dbSNP VCF.", category: "common"}
-
+ countsPath: {description: "The location the output should be written to.", category: "advanced"}
+ intervals: {description: "The intervals to collect counts for.", category: "required"}
+ inputBam: {description: "The BAM file to determine the coverage for.", category: "required"}
+ inputBamIndex: {description: "The input BAM file's index.", category: "required"}
+ referenceFasta: {description: "The reference fasta file.", category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
+ referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ intervalMergingRule: {description: "Equivalent to gatk CollectReadCounts' `--interval-merging-rule` option.", category: "advanced"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -363,50 +396,35 @@ task HaplotypeCallerGvcf {
}
}
-task MuTect2 {
+task CombineGVCFs {
input {
- Array[File]+ inputBams
- Array[File]+ inputBamsIndex
+ Array[File]+ gvcfFiles
+ Array[File]+ gvcfFilesIndex
+ Array[File] intervals = []
+ String outputPath
File referenceFasta
File referenceFastaDict
File referenceFastaFai
- String outputVcf
- String tumorSample
- String? normalSample
- File? germlineResource
- File? germlineResourceIndex
- File? panelOfNormals
- File? panelOfNormalsIndex
- String f1r2TarGz = "f1r2.tar.gz"
- Array[File]+ intervals
- String outputStats = outputVcf + ".stats"
- String memory = "16G"
- String javaXmx = "4G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ String memory = "24G"
+ String javaXmx = "12G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
- mkdir -p "$(dirname ~{outputVcf})"
+ mkdir -p "$(dirname ~{outputPath})"
gatk --java-options -Xmx~{javaXmx} \
- Mutect2 \
+ CombineGVCFs \
-R ~{referenceFasta} \
- -I ~{sep=" -I " inputBams} \
- -tumor ~{tumorSample} \
- ~{"-normal " + normalSample} \
- ~{"--germline-resource " + germlineResource} \
- ~{"--panel-of-normals " + panelOfNormals} \
- ~{"--f1r2-tar-gz " + f1r2TarGz} \
- -O ~{outputVcf} \
- -L ~{sep=" -L " intervals}
+ -O ~{outputPath} \
+ -V ~{sep=' -V ' gvcfFiles} \
+ ~{true='-L' false='' length(intervals) > 0} ~{sep=' -L ' intervals}
}
output {
- File vcfFile = outputVcf
- File vcfFileIndex = outputVcf + ".tbi"
- File f1r2File = f1r2TarGz
- File stats = outputStats
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
}
runtime {
@@ -415,21 +433,16 @@ task MuTect2 {
}
parameter_meta {
- inputBams: {description: "The BAM files on which to perform variant calling.", category: "required"}
- inputBamsIndex: {description: "The indexes for the input BAM files.", category: "required"}
- referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
- referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
+ gvcfFiles: {description: "The GVCF files to be combined.", category: "required"}
+ gvcfFilesIndex: {description: "The indexes for the GVCF files.", caregory: "required"}
+ intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "advanced"}
+ outputPath: {description: "The location the combined GVCF should be written to.", category: "required"}
+ referenceFasta: {description: "The reference fasta file which was also used for mapping.",
+ category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
+ category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- outputVcf: {description: "The location to write the output VCF file to.", category: "required"}
- tumorSample: {description: "The name of the tumor/case sample.", category: "required"}
- normalSample: {description: "The name of the normal/control sample.", category: "common"}
- germlineResource: {description: "Equivalent to Mutect2's `--germline-resource` option.", category: "advanced"}
- germlineResourceIndex: {description: "The index for the germline resource.", category: "advanced"}
- panelOfNormals: {description: "Equivalent to Mutect2's `--panel-of-normals` option.", category: "advanced"}
- panelOfNormalsIndex: {description: "The index for the panel of normals.", category: "advanced"}
- f1r2TarGz: {description: "Equivalent to Mutect2's `--f1r2-tar-gz` option.", category: "advanced"}
- intervals: {description: "Bed files describing the regiosn to operate on.", category: "required"}
- outputStats: {description: "The location the output statistics should be written to.", category: "advanced"}
+
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -438,61 +451,50 @@ task MuTect2 {
}
}
-task LearnReadOrientationModel {
+task CombineVariants {
input {
- Array[File]+ f1r2TarGz
+ File referenceFasta
+ File referenceFastaFai
+ File referenceFastaDict
+ String genotypeMergeOption = "UNIQUIFY"
+ String filteredRecordsMergeType = "KEEP_IF_ANY_UNFILTERED"
+ Array[String]+ identifiers
+ Array[File]+ variantVcfs # follow "identifiers" array order
+ Array[File]+ variantIndexes
+ String outputPath
String memory = "24G"
String javaXmx = "12G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
- command {
+ command <<<
set -e
- gatk --java-options -Xmx~{javaXmx} \
- LearnReadOrientationModel \
- -I ~{sep=" -I " f1r2TarGz} \
- -O "artifact-priors.tar.gz"
- }
-
- output {
- File artifactPriorsTable = "artifact-priors.tar.gz"
- }
-
- runtime {
- docker: dockerImage
- memory: memory
- }
-
- parameter_meta {
- f1r2TarGz: {description: "A f1r2TarGz file outputed by mutect2.", category: "required"}
- memory: {description: "The amount of memory this job will use.", category: "advanced"}
- javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
- category: "advanced"}
- dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
- category: "advanced"}
- }
-}
-
-task MergeStats {
- input {
- Array[File]+ stats
-
- String memory = "28G"
- String javaXmx = "14G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
- }
+ mkdir -p "$(dirname ~{outputPath})"
- command {
- set -e
- gatk --java-options -Xmx~{javaXmx} \
- MergeMutectStats \
- -stats ~{sep=" -stats " stats} \
- -O "merged.stats"
- }
+ # build "-V:<ID> <file.vcf>" arguments according to IDs and VCFs to merge
+ # Make sure commands are run in bash
+ V_args=$(bash -c '
+ set -eu
+ ids=(~{sep=" " identifiers})
+ vars=(~{sep=" " variantVcfs})
+ for (( i = 0; i < ${#ids[@]}; ++i ))
+ do
+ printf -- "-V:%s %s " "${ids[i]}" "${vars[i]}"
+ done
+ ')
+ java -Xmx~{javaXmx} -jar /usr/GenomeAnalysisTK.jar \
+ -T CombineVariants \
+ -R ~{referenceFasta} \
+ --genotypemergeoption ~{genotypeMergeOption} \
+ --filteredrecordsmergetype ~{filteredRecordsMergeType} \
+ --out ~{outputPath} \
+ $V_args
+ >>>
output {
- File mergedStats = "merged.stats"
+ File combinedVcf = outputPath
+ File combinedVcfIndex = outputPath + ".tbi"
}
runtime {
@@ -501,7 +503,16 @@ task MergeStats {
}
parameter_meta {
- stats: {description: "Statistics files to be merged.", category: "required"}
+ referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
+ referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ genotypeMergeOption: {description: "Equivalent to CombineVariants' `--genotypemergeoption` option.", category: "advanced"}
+ filteredRecordsMergeType: {description: "Equivalent to CombineVariants' `--filteredrecordsmergetype` option.", category: "advanced"}
+ identifiers: {description: "The sample identifiers in the same order as variantVcfs.", category: "required"}
+ variantVcfs: {description: "The input VCF files in the same order as identifiers.", category: "required"}
+ variantIndexes: {description: "The indexes of the input VCF files.", category: "required"}
+ outputPath: {description: "The location the output should be written to", category: "required"}
+
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -510,33 +521,29 @@ task MergeStats {
}
}
-task GetPileupSummaries {
+task CreateReadCountPanelOfNormals {
input {
- File sampleBam
- File sampleBamIndex
- File variantsForContamination
- File variantsForContaminationIndex
- File sitesForContamination
- File sitesForContaminationIndex
- String outputPrefix
+ String PONpath = "PON.hdf5"
+ Array[File]+ readCountsFiles
+ File? annotatedIntervals
- String memory = "24G"
- String javaXmx = "12G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ String memory = "21G"
+ String javaXmx = "7G"
+ String dockerImage = "broadinstitute/gatk:4.1.4.0" # The biocontainer causes a spark related error for some reason...
}
command {
set -e
+ mkdir -p "$(dirname ~{PONpath})"
gatk --java-options -Xmx~{javaXmx} \
- GetPileupSummaries \
- -I ~{sampleBam} \
- -V ~{variantsForContamination} \
- -L ~{sitesForContamination} \
- -O ~{outputPrefix + "-pileups.table"}
+ CreateReadCountPanelOfNormals \
+ -I ~{sep=" -I " readCountsFiles} \
+ ~{"--annotated-intervals " + annotatedIntervals} \
+ -O ~{PONpath}
}
output {
- File pileups = outputPrefix + "-pileups.table"
+ File PON = PONpath
}
runtime {
@@ -545,14 +552,10 @@ task GetPileupSummaries {
}
parameter_meta {
- sampleBam: {description: "A BAM file for which a pileup should be created.", category: "required"}
- sampleBamIndex: {description: "The index of the input BAM file.", category: "required"}
- variantsForContamination: {description: "A VCF file with common variants.", category: "required"}
- variantsForContaminationIndex: {description: "The index for the common variants VCF file.", category: "required"}
- sitesForContamination: {description: "A bed file describing regions to operate on.", category: "required"}
- sitesForContaminationIndex: {description: "The index for the bed file.", category: "required"}
- outputPrefix: {description: "The prefix for the ouput.", category: "required"}
-
+ PONpath: {description: "The location the PON should be written to.", category: "common"}
+ readCountsFiles: {description: "The read counts files as generated by CollectReadCounts.", category: "required"}
+ annotatedIntervals: {description: "An annotation set of intervals as generated by AnnotateIntervals. If provided, explicit GC correction will be performed.",
+ category: "advanced"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -561,29 +564,33 @@ task GetPileupSummaries {
}
}
-task CalculateContamination {
+task DenoiseReadCounts {
input {
- File tumorPileups
- File? normalPileups
+ File? PON
+ File? annotatedIntervals
+ File readCounts
+ String outputPrefix
- String memory = "24G"
- String javaXmx = "12G"
- String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ String memory = "39G"
+ String javaXmx = "13G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
+ mkdir -p "$(dirname ~{outputPrefix})"
gatk --java-options -Xmx~{javaXmx} \
- CalculateContamination \
- -I ~{tumorPileups} \
- ~{"-matched " + normalPileups} \
- -O "contamination.table" \
- --tumor-segmentation "segments.table"
+ DenoiseReadCounts \
+ -I ~{readCounts} \
+ ~{"--count-panel-of-normals " + PON} \
+ ~{"--annotated-intervals " + annotatedIntervals} \
+ --standardized-copy-ratios ~{outputPrefix}.standardizedCR.tsv \
+ --denoised-copy-ratios ~{outputPrefix}.denoisedCR.tsv
}
output {
- File contaminationTable = "contamination.table"
- File mafTumorSegments = "segments.table"
+ File standardizedCopyRatios = outputPrefix + ".standardizedCR.tsv"
+ File denoisedCopyRatios = outputPrefix + ".denoisedCR.tsv"
}
runtime {
@@ -592,8 +599,11 @@ task CalculateContamination {
}
parameter_meta {
- tumorPileups: {description: "The pileup summary of a tumor/case sample.", category: "required"}
- normalPileups: {description: "The pileup summary of the normal/control sample.", category: "common"}
+ PON: {description: "A panel of normals as generated by CreateReadCountPanelOfNormals.", category: "advanced"}
+ annotatedIntervals: {description: "An annotated set of intervals as generated by AnnotateIntervals. Will be ignored if PON is provided.",
+ category: "advanced"}
+ readCounts: {description: "The read counts file as generated by CollectReadCounts.", category: "required"}
+ outputPrefix: {description: "The prefix for the output files.", category: "required"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
category: "advanced"}
@@ -670,35 +680,83 @@ task FilterMutectCalls {
}
}
-task SplitNCigarReads {
+# Combine multiple recalibration tables from scattered BaseRecalibrator runs
+task GatherBqsrReports {
input {
- File inputBam
- File inputBamIndex
+ Array[File] inputBQSRreports
+ String outputReportPath
+
+ String memory = "12G"
+ String javaXmx = "4G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputReportPath})"
+ gatk --java-options -Xmx~{javaXmx} \
+ GatherBQSRReports \
+ -I ~{sep=' -I ' inputBQSRreports} \
+ -O ~{outputReportPath}
+ }
+
+ output {
+ File outputBQSRreport = outputReportPath
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ inputBQSRreports: {description: "The BQSR reports to be merged.", category: "required"}
+ outputReportPath: {description: "The location of the combined BQSR report.", category: "required"}
+
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task GenotypeGVCFs {
+ input {
+ Array[File]+ gvcfFiles
+ Array[File]+ gvcfFilesIndex
+ Array[File]+ intervals
+ String outputPath
File referenceFasta
File referenceFastaDict
File referenceFastaFai
- String outputBam
- Array[File] intervals = []
+ File? dbsnpVCF
+ File? dbsnpVCFIndex
- String memory = "16G"
- String javaXmx = "4G"
+ String memory = "18G"
+ String javaXmx = "6G"
String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
}
command {
set -e
- mkdir -p "$(dirname ~{outputBam})"
+ mkdir -p "$(dirname ~{outputPath})"
gatk --java-options -Xmx~{javaXmx} \
- SplitNCigarReads \
- -I ~{inputBam} \
+ GenotypeGVCFs \
-R ~{referenceFasta} \
- -O ~{outputBam} \
- ~{true="-L" false="" length(intervals) > 0} ~{sep=' -L ' intervals}
+ -O ~{outputPath} \
+ ~{true="-D" false="" defined(dbsnpVCF)} ~{dbsnpVCF} \
+ -G StandardAnnotation \
+ --only-output-calls-starting-in-intervals \
+ -new-qual \
+ -V ~{sep=' -V ' gvcfFiles} \
+ -L ~{sep=' -L ' intervals}
}
output {
- File bam = outputBam
- File bamIndex = sub(outputBam, "\.bam$", ".bai")
+ File outputVCF = outputPath
+ File outputVCFIndex = outputPath + ".tbi"
+
}
runtime {
@@ -707,15 +765,17 @@ task SplitNCigarReads {
}
parameter_meta {
- inputBam: {description: "The BAM file for which spliced reads should be split.", category: "required"}
- inputBamIndex: {description: "The input BAM file's index.", category: "required"}
+ gvcfFiles: {description: "The GVCF files to be genotypes.", category: "required"}
+ gvcfFilesIndex: {description: "The index of the input GVCF files.", category: "required"}
+ intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "required"}
+ outputPath: {description: "The location to write the output VCF file to.", category: "required"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.",
category: "required"}
referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- outputBam: {description: "The location the output BAM file should be written.", category: "required"}
- intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "advanced"}
+ dbsnpVCF: {description: "A dbSNP VCF.", category: "common"}
+ dbsnpVCFIndex: {description: "The index for the dbSNP VCF.", category: "common"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
@@ -725,50 +785,33 @@ task SplitNCigarReads {
}
}
-task CombineVariants {
+task GetPileupSummaries {
input {
- File referenceFasta
- File referenceFastaFai
- File referenceFastaDict
- String genotypeMergeOption = "UNIQUIFY"
- String filteredRecordsMergeType = "KEEP_IF_ANY_UNFILTERED"
- Array[String]+ identifiers
- Array[File]+ variantVcfs # follow "identifiers" array order
- Array[File]+ variantIndexes
- String outputPath
+ File sampleBam
+ File sampleBamIndex
+ File variantsForContamination
+ File variantsForContaminationIndex
+ File sitesForContamination
+ File sitesForContaminationIndex
+ String outputPrefix
String memory = "24G"
String javaXmx = "12G"
- String dockerImage = "broadinstitute/gatk3:3.8-1"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
}
- command <<<
+ command {
set -e
- mkdir -p "$(dirname ~{outputPath})"
-
- # build "-V:<ID> <file.vcf>" arguments according to IDs and VCFs to merge
- # Make sure commands are run in bash
- V_args=$(bash -c '
- set -eu
- ids=(~{sep=" " identifiers})
- vars=(~{sep=" " variantVcfs})
- for (( i = 0; i < ${#ids[@]}; ++i ))
- do
- printf -- "-V:%s %s " "${ids[i]}" "${vars[i]}"
- done
- ')
- java -Xmx~{javaXmx} -jar /usr/GenomeAnalysisTK.jar \
- -T CombineVariants \
- -R ~{referenceFasta} \
- --genotypemergeoption ~{genotypeMergeOption} \
- --filteredrecordsmergetype ~{filteredRecordsMergeType} \
- --out ~{outputPath} \
- $V_args
- >>>
+ gatk --java-options -Xmx~{javaXmx} \
+ GetPileupSummaries \
+ -I ~{sampleBam} \
+ -V ~{variantsForContamination} \
+ -L ~{sitesForContamination} \
+ -O ~{outputPrefix + "-pileups.table"}
+ }
output {
- File combinedVcf = outputPath
- File combinedVcfIndex = outputPath + ".tbi"
+ File pileups = outputPrefix + "-pileups.table"
}
runtime {
@@ -777,15 +820,514 @@ task CombineVariants {
}
parameter_meta {
+ sampleBam: {description: "A BAM file for which a pileup should be created.", category: "required"}
+ sampleBamIndex: {description: "The index of the input BAM file.", category: "required"}
+ variantsForContamination: {description: "A VCF file with common variants.", category: "required"}
+ variantsForContaminationIndex: {description: "The index for the common variants VCF file.", category: "required"}
+ sitesForContamination: {description: "A bed file describing regions to operate on.", category: "required"}
+ sitesForContaminationIndex: {description: "The index for the bed file.", category: "required"}
+ outputPrefix: {description: "The prefix for the ouput.", category: "required"}
+
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+# Call variants on a single sample with HaplotypeCaller to produce a GVCF
+task HaplotypeCallerGvcf {
+ input {
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
+ Array[File]+? intervalList
+ Array[File]+? excludeIntervalList
+ String gvcfPath
+ File referenceFasta
+ File referenceFastaIndex
+ File referenceFastaDict
+ Float contamination = 0.0
+ File? dbsnpVCF
+ File? dbsnpVCFIndex
+ Int? ploidy
+
+ String memory = "12G"
+ String javaXmx = "4G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{gvcfPath})"
+ gatk --java-options -Xmx~{javaXmx} \
+ HaplotypeCaller \
+ -R ~{referenceFasta} \
+ -O ~{gvcfPath} \
+ -I ~{sep=" -I " inputBams} \
+ ~{"--sample-ploidy " + ploidy} \
+ ~{true="-L" false="" defined(intervalList)} ~{sep=' -L ' intervalList} \
+ ~{true="-XL" false="" defined(excludeIntervalList)} ~{sep=' -XL ' excludeIntervalList} \
+ ~{true="-D" false="" defined(dbsnpVCF)} ~{dbsnpVCF} \
+ -contamination ~{contamination} \
+ -ERC GVCF
+ }
+
+ output {
+ File outputGVCF = gvcfPath
+ File outputGVCFIndex = gvcfPath + ".tbi"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ inputBams: {description: "The BAM files on which to perform variant calling.", category: "required"}
+ inputBamsIndex: {description: "The indexes for the input BAM files.", category: "required"}
+ intervalList: {description: "Bed files or interval lists describing the regions to operate on.", category: "common"}
+ excludeIntervalList: {description: "Bed files or interval lists describing the regions to NOT operate on.", category: "common"}
+ gvcfPath: {description: "The location to write the output GVCF to.", category: "required"}
+ ploidy: {description: "The ploidy with which the variants should be called.", category: "common"}
+ referenceFasta: {description: "The reference fasta file which was also used for mapping.",
+ category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
+ category: "required"}
+ referenceFastaIndex: {description: "The index for the reference fasta file.", category: "required"}
+ contamination: {description: "Equivalent to HaplotypeCaller's `-contamination` option.", category: "advanced"}
+ dbsnpVCF: {description: "A dbSNP VCF.", category: "common"}
+ dbsnpVCFIndex: {description: "The index for the dbSNP VCF.", category: "common"}
+
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+
+task LearnReadOrientationModel {
+ input {
+ Array[File]+ f1r2TarGz
+
+ String memory = "24G"
+ String javaXmx = "12G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ }
+
+ command {
+ set -e
+ gatk --java-options -Xmx~{javaXmx} \
+ LearnReadOrientationModel \
+ -I ~{sep=" -I " f1r2TarGz} \
+ -O "artifact-priors.tar.gz"
+ }
+
+ output {
+ File artifactPriorsTable = "artifact-priors.tar.gz"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ f1r2TarGz: {description: "A f1r2TarGz file outputed by mutect2.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task MergeStats {
+ input {
+ Array[File]+ stats
+
+ String memory = "28G"
+ String javaXmx = "14G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ gatk --java-options -Xmx~{javaXmx} \
+ MergeMutectStats \
+ -stats ~{sep=" -stats " stats} \
+ -O "merged.stats"
+ }
+
+ output {
+ File mergedStats = "merged.stats"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ stats: {description: "Statistics files to be merged.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task ModelSegments {
+ input {
+ String outputDir = "."
+ String outputPrefix
+ File denoisedCopyRatios
+ File allelicCounts
+ File? normalAllelicCounts
+ Int minimumTotalAlleleCountCase = if defined(normalAllelicCounts)
+ then 0
+ else 30
+ Int maximumNumberOfSmoothingIterations = 10
+
+ String memory = "64G"
+ String javaXmx = "10G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ gatk --java-options -Xmx~{javaXmx} \
+ ModelSegments \
+ --denoised-copy-ratios ~{denoisedCopyRatios} \
+ --allelic-counts ~{allelicCounts} \
+ ~{"--normal-allelic-counts " + normalAllelicCounts} \
+ --minimum-total-allele-count-case ~{minimumTotalAlleleCountCase} \
+ --maximum-number-of-smoothing-iterations ~{maximumNumberOfSmoothingIterations} \
+ --output ~{outputDir} \
+ --output-prefix ~{outputPrefix}
+ }
+
+ output {
+ File hetrozygousAllelicCounts = outputDir + "/" + outputPrefix + ".hets.tsv"
+ File? normalHetrozygousAllelicCounts = outputDir + "/" + outputPrefix + ".hets.normal.tsv"
+ File copyRatioSegments = outputDir + "/" + outputPrefix + ".cr.seg"
+ File copyRatioCBS = outputDir + "/" + outputPrefix + ".cr.igv.seg"
+ File alleleFractionCBS = outputDir + "/" + outputPrefix + ".af.igv.seg"
+ File unsmoothedModeledSegments = outputDir + "/" + outputPrefix + ".modelBegin.seg"
+ File unsmoothedCopyRatioParameters = outputDir + "/" + outputPrefix + ".modelBegin.cr.param"
+ File unsmoothedAlleleFractionParameters = outputDir + "/" + outputPrefix + ".modelBegin.af.param"
+ File modeledSegments = outputDir + "/" + outputPrefix + ".modelFinal.seg"
+ File copyRatioParameters = outputDir + "/" + outputPrefix + ".modelFinal.cr.param"
+ File alleleFractionParameters = outputDir + "/" + outputPrefix + ".modelFinal.af.param"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ outputDir: {description: "The directory to write the ouput to.", category: "common"}
+ outputPrefix: {description: "The prefix of the output files. Should not include directories.", category: "required"}
+ denoisedCopyRatios: {description: "The denoised copy ratios as generated by DenoiseReadCounts.", category: "required"}
+ allelicCounts: {description: "The allelicCounts as generate by CollectAllelicCounts.", category: "required" }
+ normalAllelicCounts: {description: "The allelicCounts as generate by CollectAllelicCounts for a matched normal.", category: "common"}
+ minimumTotalAlleleCountCase: {description: "Equivalent to gatk ModelSeqments' `--minimum-total-allele-count-case` option.", category: "advanced"}
+ maximumNumberOfSmoothingIterations: {description: "Equivalent to gatk ModelSeqments' `--maximum-number-of-smoothing-iterations` option.", category: "advanced"}
+
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task MuTect2 {
+ input {
+ Array[File]+ inputBams
+ Array[File]+ inputBamsIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ String outputVcf
+ String tumorSample
+ String? normalSample
+ File? germlineResource
+ File? germlineResourceIndex
+ File? panelOfNormals
+ File? panelOfNormalsIndex
+ String f1r2TarGz = "f1r2.tar.gz"
+ Array[File]+ intervals
+ String outputStats = outputVcf + ".stats"
+
+ String memory = "16G"
+ String javaXmx = "4G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputVcf})"
+ gatk --java-options -Xmx~{javaXmx} \
+ Mutect2 \
+ -R ~{referenceFasta} \
+ -I ~{sep=" -I " inputBams} \
+ -tumor ~{tumorSample} \
+ ~{"-normal " + normalSample} \
+ ~{"--germline-resource " + germlineResource} \
+ ~{"--panel-of-normals " + panelOfNormals} \
+ ~{"--f1r2-tar-gz " + f1r2TarGz} \
+ -O ~{outputVcf} \
+ -L ~{sep=" -L " intervals}
+ }
+
+ output {
+ File vcfFile = outputVcf
+ File vcfFileIndex = outputVcf + ".tbi"
+ File f1r2File = f1r2TarGz
+ File stats = outputStats
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ inputBams: {description: "The BAM files on which to perform variant calling.", category: "required"}
+ inputBamsIndex: {description: "The indexes for the input BAM files.", category: "required"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- genotypeMergeOption: {description: "Equivalent to CombineVariants' `--genotypemergeoption` option.", category: "advanced"}
- filteredRecordsMergeType: {description: "Equivalent to CombineVariants' `--filteredrecordsmergetype` option.", category: "advanced"}
- identifiers: {description: "The sample identifiers in the same order as variantVcfs.", category: "required"}
- variantVcfs: {description: "The input VCF files in the same order as identifiers.", category: "required"}
- variantIndexes: {description: "The indexes of the input VCF files.", category: "required"}
- outputPath: {description: "The location the output should be written to", category: "required"}
+ outputVcf: {description: "The location to write the output VCF file to.", category: "required"}
+ tumorSample: {description: "The name of the tumor/case sample.", category: "required"}
+ normalSample: {description: "The name of the normal/control sample.", category: "common"}
+ germlineResource: {description: "Equivalent to Mutect2's `--germline-resource` option.", category: "advanced"}
+ germlineResourceIndex: {description: "The index for the germline resource.", category: "advanced"}
+ panelOfNormals: {description: "Equivalent to Mutect2's `--panel-of-normals` option.", category: "advanced"}
+ panelOfNormalsIndex: {description: "The index for the panel of normals.", category: "advanced"}
+ f1r2TarGz: {description: "Equivalent to Mutect2's `--f1r2-tar-gz` option.", category: "advanced"}
+ intervals: {description: "Bed files describing the regiosn to operate on.", category: "required"}
+ outputStats: {description: "The location the output statistics should be written to.", category: "advanced"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task PlotDenoisedCopyRatios {
+ input {
+ File referenceFastaDict
+ String outputDir = "."
+ String outputPrefix
+ File standardizedCopyRatios
+ File denoisedCopyRatios
+
+ String memory = "32G"
+ String javaXmx = "7G"
+ String dockerImage = "broadinstitute/gatk:4.1.4.0" # The biocontainer doesn't seem to contain R.
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ gatk --java-options -Xmx~{javaXmx} \
+ PlotDenoisedCopyRatios \
+ --standardized-copy-ratios ~{standardizedCopyRatios} \
+ --denoised-copy-ratios ~{denoisedCopyRatios} \
+ --sequence-dictionary ~{referenceFastaDict} \
+ --output ~{outputDir} \
+ --output-prefix ~{outputPrefix}
+ }
+
+ output {
+ File denoisedCopyRatiosPlot = outputDir + "/" + outputPrefix + ".denoised.png"
+ File denoisedCopyRatiosLimitedPlot = outputDir + "/" + outputPrefix + ".denoisedLimit4.png"
+ File standardizedMedianAbsoluteDeviation = outputDir + "/" + outputPrefix + ".standardizedMAD.txt"
+ File denoisedMedianAbsoluteDeviation = outputDir + "/" + outputPrefix + ".denoisedMAD.txt"
+ File deltaMedianAbsoluteDeviation = outputDir + "/" + outputPrefix + ".deltaMAD.txt"
+ File deltaScaledMedianAbsoluteDeviation = outputDir + "/" + outputPrefix + ".scaledDeltaMAD.txt"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file used for the analyses.", category: "required"}
+ outputDir: {description: "The directory to write the ouput to.", category: "common"}
+ outputPrefix: {description: "The prefix of the output files. Should not include directories.", category: "required"}
+ denoisedCopyRatios: {description: "The denoised copy ratios as generated by DenoiseReadCounts.", category: "required"}
+ standardizedCopyRatios: {description: "The standardized copy ratios as generated by DenoiseReadCounts.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task PlotModeledSegments {
+ input {
+ File referenceFastaDict
+ String outputDir = "."
+ String outputPrefix
+ File denoisedCopyRatios
+ File segments
+ File allelicCounts
+
+ String memory = "21G"
+ String javaXmx = "7G"
+ String dockerImage = "broadinstitute/gatk:4.1.4.0" # The biocontainer doesn't seem to contain R.
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ gatk --java-options -Xmx~{javaXmx} \
+ PlotModeledSegments \
+ --denoised-copy-ratios ~{denoisedCopyRatios} \
+ --allelic-counts ~{allelicCounts} \
+ --segments ~{segments} \
+ --sequence-dictionary ~{referenceFastaDict} \
+ --output ~{outputDir} \
+ --output-prefix ~{outputPrefix}
+ }
+
+ output {
+ File modeledSegmentsPlot = outputDir + "/" + outputPrefix + ".modeled.png"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file used for the analyses.", category: "required"}
+ outputDir: {description: "The directory to write the ouput to.", category: "common"}
+ outputPrefix: {description: "The prefix of the output files. Should not include directories.", category: "required"}
+ denoisedCopyRatios: {description: "The denoised copy ratios as generated by DenoiseReadCounts.", category: "required"}
+ segments: {description: "The modeled segments as generated by ModelSegments.", category: "required"}
+ allelicCounts: {description: "The hetrozygous allelic counts as generated by ModelSegments.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task PreprocessIntervals {
+ input {
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ File? intervals
+ String outputIntervalList = "bins.interval_list"
+ Int binLength = if defined(intervals) then 0 else 1000
+ Int padding = if defined(intervals) then 250 else 0
+ String intervalMergingRule = "OVERLAPPING_ONLY"
+
+ String memory = "10G"
+ String javaXmx = "2G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputIntervalList})"
+ gatk --java-options -Xmx~{javaXmx} \
+ PreprocessIntervals \
+ -R ~{referenceFasta} \
+ --sequence-dictionary ~{referenceFastaDict} \
+ --bin-length ~{binLength} \
+ --padding ~{padding} \
+ ~{"-L " + intervals} \
+ --interval-merging-rule ~{intervalMergingRule} \
+ -O ~{outputIntervalList}
+ }
+
+ output {
+ File intervalList = outputIntervalList
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ referenceFasta: {description: "The reference fasta file..", category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.", category: "required"}
+ referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ intervals: {description: "Bed files describing the regiosn to operate on.", category: "common"}
+ outputIntervalList: {description: "The location the output should be written to.", category: "advanced"}
+ binLength: {description: "The size of the bins to be created. Should be 0 for targeted/exome sequencing.", category: "advanced"}
+ padding: {description: "The padding to be added to the bins. Should be 0 if contiguos binning is used, eg with WGS.", category: "advanced"}
+ intervalMergingRule: {description: "Equivalent to gatk PreprocessIntervals' `--interval-merging-rule` option.", category: "advanced"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task SplitNCigarReads {
+ input {
+ File inputBam
+ File inputBamIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ String outputBam
+ Array[File] intervals = []
+
+ String memory = "16G"
+ String javaXmx = "4G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputBam})"
+ gatk --java-options -Xmx~{javaXmx} \
+ SplitNCigarReads \
+ -I ~{inputBam} \
+ -R ~{referenceFasta} \
+ -O ~{outputBam} \
+ ~{true="-L" false="" length(intervals) > 0} ~{sep=' -L ' intervals}
+ }
+
+ output {
+ File bam = outputBam
+ File bamIndex = sub(outputBam, "\.bam$", ".bai")
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ inputBam: {description: "The BAM file for which spliced reads should be split.", category: "required"}
+ inputBamIndex: {description: "The input BAM file's index.", category: "required"}
+ referenceFasta: {description: "The reference fasta file which was also used for mapping.",
+ category: "required"}
+ referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",
+ category: "required"}
+ referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ outputBam: {description: "The location the output BAM file should be written.", category: "required"}
+ intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "advanced"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",