diff --git a/gatk.wdl b/gatk.wdl
index f6d42e825356ebd6fb7d3a7de14afc11940f3833..f54934a049d8307d721f36431dcb6c2bee2cd9cf 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -251,6 +251,96 @@ task CalculateContamination {
}
}
+task CallCopyRatioSegments {
+ input {
+ String outputPrefix
+ File copyRatioSegments
+
+ String memory = "21G"
+ String javaXmx = "6G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(~{outputPrefix})"
+ gatk --java-options -Xmx~{javaXmx} \
+ CallCopyRatioSegments \
+ -I ~{copyRatioSegments} \
+ -O ~{outputPrefix}.called.seg
+ }
+
+ output {
+ File calledSegments = outputPrefix + ".called.seg"
+ File calledSegmentsIgv = outputPrefix + ".called.igv.seg"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ outputPrefix: {description: "The prefix for the output files.", category: "required"}
+ copyRatioSegments: {description: "The copy ratios file generated by gatk ModelSegments.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.",
+ category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
+ category: "advanced"}
+ }
+}
+
+task CollectAllelicCounts {
+ input {
+ String allelicCountsPath = "allelic_counts.tsv"
+ File commonVariantSites
+ File inputBam
+ File inputBamIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ String memory = "90G"
+ String javaXmx = "30G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{allelicCountsPath})"
+ gatk --java-options -Xmx~{javaXmx} \
+ CollectAllelicCounts \
+ -L ~{commonVariantSites} \
+ -I ~{inputBam} \
+ -R ~{referenceFasta} \
+ -O ~{allelicCountsPath}
+ }
+
+ output {
+ File allelicCounts = allelicCountsPath
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ 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"}
+ 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 CollectReadCounts {
input {
String countsPath = "readcounts.hdf5"
@@ -290,7 +380,7 @@ task CollectReadCounts {
}
parameter_meta {
- countsPath: {description: "The location the output should be written to.", category: "required"}
+ 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"}
@@ -463,7 +553,7 @@ task CreateReadCountPanelOfNormals {
parameter_meta {
PONpath: {description: "The location the PON should be written to.", category: "common"}
- readCountsFiles: {description: "The read counts files as generated by CollectReadCounts.", category: "advanced"}
+ 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"}
@@ -474,6 +564,54 @@ task CreateReadCountPanelOfNormals {
}
}
+task DenoiseReadCounts {
+ input {
+ File? PON
+ File? annotatedIntervals
+ File readCounts
+ String outputPrefix
+
+ String memory = "39G"
+ String javaXmx = "13G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.2.0--1"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPrefix})"
+ gatk --java-options -Xmx~{javaXmx} \
+ 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 standardizedCopyRatios = outputPrefix + ".standardizedCR.tsv"
+ File denoisedCopyRatios = outputPrefix + ".denoisedCR.tsv"
+ }
+
+ runtime {
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ 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"}
+ 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 FilterMutectCalls {
input {
File referenceFasta
@@ -836,6 +974,73 @@ task MergeStats {
}
}
+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/gatk4:4.1.2.0--1"
+ }
+
+ 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
@@ -911,6 +1116,110 @@ task MuTect2 {
}
}
+task PlotDenoisedCopyRatios {
+ input {
+ File referenceFastaDict
+ String outputDir = "."
+ String outputPrefix
+ File standardizedCopyRatios
+ File denoisedCopyRatios
+
+ String memory = "21G"
+ String javaXmx = "7G"
+ String dockerImage = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ 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 = "quay.io/biocontainers/gatk4:4.1.0.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ gatk --java-option -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