diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 3b4ec9ac40da235c2b2e4e6a682442a6dd5d4832..372071eedba04dd24461a81b4806096474a348ad 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -2,3 +2,4 @@
- [ ] Pull request details were added to CHANGELOG.md.
- [ ] Documentation was updated (if required).
- [ ] `parameter_meta` was added/updated (if required).
+- [ ] Submodule branches are on develop or a tagged commit.
diff --git a/.github/lint-environment.yml b/.github/lint-environment.yml
new file mode 100644
index 0000000000000000000000000000000000000000..63b538fce9790456e089e63ddda41859a8ba9f06
--- /dev/null
+++ b/.github/lint-environment.yml
@@ -0,0 +1,9 @@
+name: biowdl-lint
+channels:
+ - conda-forge
+ - bioconda
+ - defaults
+dependencies:
+ - cromwell
+ - wdl-aid
+ - miniwdl
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
deleted file mode 100644
index 785661119a9f3d1ca173a9c92a64a52bbf930328..0000000000000000000000000000000000000000
--- a/.github/workflows/ci.yml
+++ /dev/null
@@ -1,30 +0,0 @@
-name: Continuous integration
-
-on:
- pull_request:
- paths_ignore:
- - "docs/**"
-
-defaults:
- run:
- # This is needed for miniconda, see:
- # https://github.com/marketplace/actions/setup-miniconda#important
- shell: bash -l {0}
-
-jobs:
- lint:
- runs-on: ubuntu-latest
- name: Womtool validate and submodule up to date.
- steps:
- - uses: actions/checkout@v2.3.4
- with:
- submodules: recursive
- - name: install miniconda
- uses: conda-incubator/setup-miniconda@v2.0.1
- with:
- channels: conda-forge,bioconda,defaults
- # Conda-incubator uses 'test' environment by default.
- - name: install requirements
- run: conda install -n test cromwell miniwdl wdl-aid
- - name: run linting
- run: bash scripts/biowdl_lint.sh
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
new file mode 100644
index 0000000000000000000000000000000000000000..e6edbbab42ede61c41f171ec01e21d5acce8d2a9
--- /dev/null
+++ b/.github/workflows/lint.yml
@@ -0,0 +1,93 @@
+name: Linting
+
+on:
+ pull_request:
+ paths_ignore:
+ - "docs/**"
+
+defaults:
+ run:
+ # This is needed for miniconda, see:
+ # https://github.com/marketplace/actions/setup-miniconda#important
+ shell: bash -l {0}
+
+jobs:
+ lint:
+ runs-on: ubuntu-latest
+ name: Linting checks
+ steps:
+ - uses: actions/checkout@v2.3.4
+ with:
+ submodules: recursive
+
+ - name: Set cache date
+ run: echo "DATE=$(date +'%Y%m%d')" >> $GITHUB_ENV
+
+ - name: Cache conda environment
+ uses: actions/cache@v2.1.7
+ env:
+ # Increase this value to manually invalidate the cache
+ CACHE_NUMBER: 0
+ with:
+ path: /usr/share/miniconda/envs/biowdl-lint
+ key:
+ ${{runner.os}}-biowdl-lint-${{ env.CACHE_NUMBER }}-${{env.DATE}}-${{ hashFiles('.github/lint-environment.yml') }}
+ id: env_cache
+
+ # Use the builtin conda. This is the fastest installation. It may not be
+ # the fastest for resolving, but the package cache mitigates that problem.
+ # Since this installs fastest, it is fastest for all runs where a cache
+ # hit occurs.
+ - name: install miniconda
+ uses: conda-incubator/setup-miniconda@v2.1.1
+ with:
+ channels: conda-forge,bioconda,defaults
+ channel-priority: strict
+ auto-activate-base: false
+ use-only-tar-bz2: true # Needed for proper caching according to the documentation.
+ # activate-environment is broken! This always seems to create a new environment.
+ # Activation is therefore done separately.
+
+ - name: Create test environment if no cache is present
+ run: conda env create -n biowdl-lint -f .github/lint-environment.yml
+ if: steps.env_cache.outputs.cache-hit != 'true'
+
+ - name: Activate test environment
+ # The new PATH should be passed to the environment, otherwise it won't register.
+ run: |
+ conda activate biowdl-lint
+ echo "PATH=$PATH" >> $GITHUB_ENV
+
+ - name: Fetch develop branch for comparisons
+ run: git fetch --depth=1 origin develop
+
+ - name: run womtool validate
+ # Only check files that have changed from the base reference.
+ # Womtool validate checks very slowly, so this saves a lot of time.
+ run: |
+ bash -c "
+ for WDL_FILE in $(git diff --name-only origin/${{github.base_ref}} | grep -E '*.wdl$'); do
+ womtool validate $WDL_FILE
+ done
+ "
+ - name: run miniwdl check
+ run: bash -c 'miniwdl check $(git ls-files *.wdl)'
+
+ - name: Check copyright headers
+ run: |
+ bash -c '
+ for WDL_FILE in $(git diff --name-only origin/${{github.base_ref}} | grep -E '*.wdl$'); do
+ grep Copyright $WDL_FILE || bash -c "echo No copyright header in $WDL_FILE && exit 1"
+ done
+ '
+ - name: Check parameter_meta for inputs
+ run: |
+ bash -c "
+ for WDL_FILE in $(git diff --name-only origin/${{github.base_ref}} | grep -E '*.wdl$'); do
+ wdl-aid --strict $WDL_FILE > /dev/null 2> wdl-aid_stderr ||
+ if grep -z 'ValueError: Missing parameter_meta for inputs:' wdl-aid_stderr
+ then
+ exit 1
+ fi
+ done
+ "
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 126f1ed9aa60503f8793f43f60ae2f2b233b9cb2..6c0db94722449604660b6d39e98957fd6380da93 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,43 @@ that users understand how the changes affect the new version.
-->
version 5.1.0-dev
---------------------------
++ Added a task for SnpEff.
++ Adjusted runtime settings for sambamba Markdup.
++ Added a task for sambamba Flagstat.
++ Added a task for Picard CollectWgsMetrics.
++ Added a task for Peach.
++ Added tasks for HMFtools:
+ + Amber
+ + Cobalt
+ + Cuppa
+ + CuppaChart
+ + GripssApplicationKt
+ + GripssHardFilterApplicationKt
+ + HealthChecker
+ + Linx
+ + Protect
+ + Purple
+ + Sage
+ + VirusInterpreter
++ Added a task for VirusBreakend.
++ Added a task for GridssAnnotateVcfRepeatmasker.
++ Bumped GRIDSS version to 2.12.2.
++ Adjusted GRIDSS runtime settings.
++ Added optional inputs to GRIDSS:
+ + blacklistBed
+ + gridssProperties
++ Added a task for GRIDSS AnnotateInsertedSequence.
++ Added a task for ExtractSigPredictHRD.
++ Added a task for DeconstructSigs.
++ Added option useSoftclippingForSupplementary (default false) to
+ BWA mem.
++ Adjusted BWA mem runtime settings.
++ Added a task for bedtools coverage.
++ Added a task for bcftools filter.
++ Adjusted runtime settings for bcftools annotate.
++ Added optional inputs to bcftools annotate:
+ + inputFileIndex
+ + annsFileIndex
+ Update parameter_meta for macs2
+ Add sample position in array task.
diff --git a/bcftools.wdl b/bcftools.wdl
index 02a02563f622766f2481ecfd27c6668c6f0b27d1..88d97cd09465fee1384edc6b498504bbd2adf917 100644
--- a/bcftools.wdl
+++ b/bcftools.wdl
@@ -30,9 +30,11 @@ task Annotate {
Boolean singleOverlaps = false
Array[String] removeAnns = []
File inputFile
+ File? inputFileIndex
String outputPath = "output.vcf.gz"
File? annsFile
+ File? annsFileIndex
String? collapse
String? exclude
File? headerLines
@@ -45,8 +47,8 @@ task Annotate {
File? samplesFile
Int threads = 0
- String memory = "256M"
- Int timeMinutes = 1 + ceil(size(inputFile, "G"))
+ String memory = "4G"
+ Int timeMinutes = 60 + ceil(size(inputFile, "G"))
String dockerImage = "quay.io/biocontainers/bcftools:1.10.2--h4f4756c_2"
}
@@ -102,8 +104,10 @@ task Annotate {
singleOverlaps: {description: "keep memory requirements low with very large annotation files.", category: "advanced"}
removeAnns: {description: "List of annotations to remove (see man page for details).", category: "advanced"}
inputFile: {description: "A vcf or bcf file.", category: "required"}
+ inputFileIndex: {description: "The index for the input vcf or bcf.", category: "common"}
outputPath: {description: "The location the output VCF file should be written.", category: "common"}
- annsFile: {description: "Bgzip-compressed and tabix-indexed file with annotations (see man page for details).", category: "advanced"}
+ annsFile: {description: "Bgzip-compressed and tabix-indexed file with annotations (see man page for details).", category: "common"}
+ annsFileIndex: {description: "The index for annsFile.", category: "common"}
collapse: {description: "Treat as identical records with <snps|indels|both|all|some|none>, see man page for details.", category: "advanced"}
exclude: {description: "Exclude sites for which the expression is true (see man page for details).", category: "advanced"}
headerLines: {description: "Lines to append to the VCF header (see man page for details).", category: "advanced"}
@@ -125,6 +129,57 @@ task Annotate {
}
}
+task Filter {
+ input {
+ File vcf
+ File vcfIndex
+ String? include
+ String? exclude
+ String? softFilter
+ String outputPath = "./filtered.vcf.gz"
+
+ String memory = "256M"
+ Int timeMinutes = 1 + ceil(size(vcf, "G"))
+ String dockerImage = "quay.io/biocontainers/bcftools:1.10.2--h4f4756c_2"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPath})"
+ bcftools \
+ filter \
+ ~{"-i " + include} \
+ ~{"-e " + exclude} \
+ ~{"-s " + softFilter} \
+ ~{vcf} \
+ -O z \
+ -o ~{outputPath}
+ bcftools index --tbi ~{outputPath}
+ }
+
+ output {
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ vcf: {description: "The VCF file to operate on.", category: "required"}
+ vcfIndex: {description: "The index for the VCF file.", category: "required"}
+ include: {description: "Equivalent to the `-i` option.", category: "common"}
+ outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+
+ 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"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ }
+}
+
task Sort {
input {
File inputFile
diff --git a/bedtools.wdl b/bedtools.wdl
index 3dbf93cbaea7386e9c695b658e55038173c74f6a..1d956cab25c793161adee4ff00999690a42178db 100644
--- a/bedtools.wdl
+++ b/bedtools.wdl
@@ -66,6 +66,55 @@ task Complement {
}
}
+task Coverage {
+ input {
+ File genomeFile
+ File a
+ File? aIndex
+ File b
+ File? bIndex
+ String outputPath = "./coverage.tsv"
+
+ String memory = "8G"
+ Int timeMinutes = 120
+ String dockerImage = "quay.io/biocontainers/bedtools:2.30.0--h7d7f7ad_2"
+ }
+
+ command {
+ bedtools coverage \
+ -sorted \
+ -g ~{genomeFile} \
+ -a ~{a} \
+ -b ~{b} \
+ -d \
+ > ~{outputPath}
+ }
+
+ output {
+ File coverageTsv = outputPath
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ genomeFile: {description: "A file listing the chromosomes and their lengths.", category: "required"}
+ a: {description: "The file containing the regions for which the coverage will be counted.", category: "required"}
+ aIndex: {description: "An index for the file given as `a`.", category: "common"}
+ b: {description: "The file in which the coverage will be counted. Likely a BAM file.", category: "required"}
+ bIndex: {description: "An index for the file given as `b`.", category: "common"}
+ outputPath: {description: "The path the ouptu will be written to.", category: "common"}
+
+ memory: {description: "The amount of memory needed for the job.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Merge {
input {
File inputBed
diff --git a/bwa.wdl b/bwa.wdl
index e87fd82ab7ad276b231f28bfd13fb06661339358..1cb170b70b5dc19321ea6094a31aa53418e6aab8 100644
--- a/bwa.wdl
+++ b/bwa.wdl
@@ -28,6 +28,7 @@ task Mem {
String outputPrefix
Boolean sixtyFour = false
Boolean usePostalt = false
+ Boolean useSoftclippingForSupplementary = false
Int sortMemoryPerThreadGb = 2
Int compressionLevel = 1
@@ -36,7 +37,7 @@ task Mem {
Int threads = 4
Int? memoryGb
- Int timeMinutes = 1 + ceil(size([read1, read2], "G") * 220 / threads)
+ Int timeMinutes = 10 + ceil(size([read1, read2], "G") * 300 / threads)
# Contains bwa 0.7.17 bwakit 0.7.17.dev1 and samtools 1.10.
String dockerImage = "quay.io/biocontainers/mulled-v2-ad317f19f5881324e963f6a6d464d696a2825ab6:c59b7a73c87a9fe81737d5d628e10a3b5807f453-0"
}
@@ -47,7 +48,7 @@ task Mem {
Int estimatedSortThreads = if threads == 1 then 1 else 1 + ceil(threads / 4.0)
Int totalSortThreads = select_first([sortThreads, estimatedSortThreads])
# BWA needs slightly more memory than the size of the index files (~10%). Add a margin for safety here.
- Int estimatedMemoryGb = 1 + ceil(size(bwaIndex.indexFiles, "G") * 1.2) + sortMemoryPerThreadGb * totalSortThreads
+ Int estimatedMemoryGb = 10 + ceil(size(bwaIndex.indexFiles, "G") * 2) + sortMemoryPerThreadGb * totalSortThreads
# The bwa postalt script is out commented as soon as usePostalt = false.
# This hack was tested with bash, dash and ash. It seems that comments in between pipes work for all of them.
@@ -56,6 +57,7 @@ task Mem {
mkdir -p "$(dirname ~{outputPrefix})"
bwa mem \
-t ~{threads} \
+ ~{if useSoftclippingForSupplementary then "-Y" else ""} \
~{"-R '" + readgroup}~{true="'" false="" defined(readgroup)} \
~{bwaIndex.fastaFile} \
~{read1} \
diff --git a/deconstructsigs.wdl b/deconstructsigs.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..ef47e3e3d821d18ec2bbbcd46d58d87ba224f6c3
--- /dev/null
+++ b/deconstructsigs.wdl
@@ -0,0 +1,66 @@
+# Copyright (c) 2021 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.
+
+version 1.0
+
+task DeconstructSigs {
+ input {
+ File signaturesMatrix
+ File signaturesReference
+ String outputPath = "./signatures.rds"
+
+ Int timeMinutes = 15
+ String memory = "4G"
+ String dockerImage = "quay.io/biocontainers/r-deconstructsigs:1.9.0--r41hdfd78af_1"
+ }
+
+ command {
+ R --no-echo << EOF
+ library(deconstructSigs)
+ tumor <- read.table("~{signaturesMatrix}", check.names=F)
+ ref <- data.frame(t(read.table("~{signaturesReference}", check.names=F, header=T, row.names="Type")), check.names=F)
+ tumor <- tumor[,colnames(ref)]
+
+ sigs <- whichSignatures(tumor.ref=tumor, row.names(tumor), signatures.ref=ref, contexts.needed=T)
+ saveRDS(sigs, "~{outputPath}")
+ EOF
+ }
+
+ output {
+ File signatureRDS = outputPath
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ signaturesMatrix: {description: "A table containing columns represtenting mutation types (matching the types in the signatures reference) and one row with the counts for each of these types for the sample of intrest.",
+ category: "required"}
+ signaturesReference: {description: "A table describing the mutational signatures, formatted like those provided by COSMIC.",
+ category: "required"}
+ outputPath: {description: "The location the output will be written to.", category: "common"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", 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"}
+ }
+}
\ No newline at end of file
diff --git a/extractSigPredictHRD.wdl b/extractSigPredictHRD.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..2b5d97815bc74fd35f127b1e02a7855acb6042a3
--- /dev/null
+++ b/extractSigPredictHRD.wdl
@@ -0,0 +1,71 @@
+version 1.0
+
+# Copyright (c) 2021 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 ExtractSigPredictHRD {
+ input {
+ String outputDir = "."
+ String sampleName
+ File snvIndelVcf
+ File snvIndelVcfIndex
+ File svVcf
+ File svVcfIndex
+ Boolean hg38 = false
+
+ String memory = "3G"
+ Int timeMinutes = 10
+ String dockerImage = "quay.io/biowdl/chord-mutsigextractor:2.00_1.14"
+ }
+
+ command {
+ extractSigPredictHRD.R \
+ ~{outputDir} \
+ ~{sampleName} \
+ ~{snvIndelVcf} \
+ ~{svVcf} \
+ ~{if hg38 then "RG_38" else "RG_37"}
+ }
+
+ output {
+ File chordPrediction = "~{outputDir}/~{sampleName}_chord_prediction.txt"
+ File chordSignatures = "~{outputDir}/~{sampleName}_chord_signatures.txt"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ outputDir: {description: "The directory the outout will be written to.", category: "required"}
+ sampleName: {description: "The name of the sample.", category: "required"}
+ snvIndelVcf: {description: "A VCF file with SNVs and indels.", category: "required"}
+ snvIndelVcfIndex: {description: "The index for the SNV/indel VCF file.", category: "required"}
+ svVcf: {description: "A VCF file with SVs.", category: "required"}
+ svVcfIndex: {description: "The index for the SV VCF file.", category: "required"}
+
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
+ }
+}
\ No newline at end of file
diff --git a/gridss.wdl b/gridss.wdl
index 5f48afac6df43a6e3eedfdbdc9c740622e954d58..d3d251a5b2a811d38db2776784e2a41a60f1578c 100644
--- a/gridss.wdl
+++ b/gridss.wdl
@@ -1,6 +1,6 @@
version 1.0
-# Copyright (c) 2017 Leiden University Medical Center
+# Copyright (c) 2020 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
@@ -22,6 +22,63 @@ version 1.0
import "bwa.wdl" as bwa
+task AnnotateInsertedSequence {
+ input {
+ File inputVcf
+ String outputPath = "gridss.annotated.vcf.gz"
+ File viralReference
+ File viralReferenceFai
+ File viralReferenceDict
+ File viralReferenceImg
+
+ Int threads = 8
+ String javaXmx = "8G"
+ String memory = "9G"
+ String dockerImage = "quay.io/biowdl/gridss:2.12.2"
+ Int timeMinutes = 120
+ }
+
+ command {
+ set -e
+ _JAVA_OPTIONS="$_JAVA_OPTIONS -Xmx~{javaXmx}"
+ AnnotateInsertedSequence \
+ REFERENCE_SEQUENCE=~{viralReference} \
+ INPUT=~{inputVcf} \
+ OUTPUT=~{outputPath} \
+ ALIGNMENT=APPEND \
+ WORKING_DIR='.' \
+ WORKER_THREADS=~{threads}
+ }
+
+ output {
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
+ }
+
+ runtime {
+ cpu: threads
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ inputVcf: {description: "The input VCF file.", category: "required"}
+ outputPath: {description: "The path the output will be written to.", category: "common"}
+ viralReference: {description: "A fasta file with viral sequences.", category: "required"}
+ viralReferenceFai: {description: "The index for the viral reference fasta.", category: "required"}
+ viralReferenceDict: {description: "The dict file for the viral reference.", category: "required"}
+ viralReferenceImg: {description: "The BWA index image (generated with GATK BwaMemIndexImageCreator) of the viral reference.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 GRIDSS {
input {
File tumorBam
@@ -33,25 +90,31 @@ task GRIDSS {
File? normalBam
File? normalBai
String? normalLabel
+ File? blacklistBed
+ File? gridssProperties
- Int jvmHeapSizeGb = 30
- Int threads = 1
- String dockerImage = "quay.io/biocontainers/gridss:2.9.4--0"
+ Int jvmHeapSizeGb = 300
+ Int nonJvmMemoryGb = 50
+ Int threads = 4
+ Int timeMinutes = ceil(7200 / threads) + 1800
+ String dockerImage = "quay.io/biowdl/gridss:2.12.2"
}
command {
set -e
mkdir -p "$(dirname ~{outputPrefix})"
gridss \
+ -w . \
--reference ~{reference.fastaFile} \
--output ~{outputPrefix}.vcf.gz \
--assembly ~{outputPrefix}_assembly.bam \
+ ~{"-c " + gridssProperties} \
~{"-t " + threads} \
~{"--jvmheap " + jvmHeapSizeGb + "G"} \
- --label ~{normalLabel}~{true="," false="" defined(normalLabel)}~{tumorLabel} \
+ --labels ~{normalLabel}~{true="," false="" defined(normalLabel)}~{tumorLabel} \
+ ~{"--blacklist " + blacklistBed} \
~{normalBam} \
~{tumorBam}
- tabix -p vcf ~{outputPrefix}.vcf.gz
samtools index ~{outputPrefix}_assembly.bam ~{outputPrefix}_assembly.bai
}
@@ -64,7 +127,8 @@ task GRIDSS {
runtime {
cpu: threads
- memory: "~{jvmHeapSizeGb + 1}G"
+ memory: "~{jvmHeapSizeGb + nonJvmMemoryGb}G"
+ time_minutes: timeMinutes # !UnknownRuntimeKey
docker: dockerImage
}
@@ -78,8 +142,13 @@ task GRIDSS {
normalBam: {description: "The BAM file for the normal/control sample.", category: "advanced"}
normalBai: {description: "The index for normalBam.", category: "advanced"}
normalLabel: {description: "The name of the normal sample.", category: "advanced"}
- jvmHeapSizeGb: {description: "The size of JVM heap for assembly and variant calling.",category: "advanced"}
+ blacklistBed: {description: "A bed file with blaclisted regins.", category: "advanced"}
+ gridssProperties: {description: "A properties file for gridss.", category: "advanced"}
+
threads: {description: "The number of the threads to use.", category: "advanced"}
+ jvmHeapSizeGb: {description: "The size of JVM heap for assembly and variant calling", category: "advanced"}
+ nonJvmMemoryGb: {description: "The amount of memory in Gb to be requested besides JVM memory.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
# outputs
@@ -89,3 +158,106 @@ task GRIDSS {
assemblyIndex: {description: "Index of output BAM file."}
}
}
+
+task GridssAnnotateVcfRepeatmasker {
+ input {
+ File gridssVcf
+ File gridssVcfIndex
+ String outputPath = "./gridss.repeatmasker_annotated.vcf.gz"
+
+ String memory = "25G"
+ Int threads = 8
+ String dockerImage = "quay.io/biowdl/gridss:2.12.2"
+ Int timeMinutes = 1440
+ }
+
+ command {
+ gridss_annotate_vcf_repeatmasker \
+ --output ~{outputPath} \
+ --jar /usr/local/share/gridss-2.12.2-0/gridss.jar \
+ -w . \
+ -t ~{threads} \
+ ~{gridssVcf}
+ }
+
+ output {
+ File annotatedVcf = outputPath
+ File annotatedVcfIndex = "~{outputPath}.tbi"
+ }
+
+ runtime {
+ cpu: threads
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ gridssVcf: {description: "The GRIDSS output.", category: "required"}
+ gridssVcfIndex: {description: "The index for the GRIDSS output.", category: "required"}
+ outputPath: {description: "The path the output should be written to.", category: "common"}
+ threads: {description: "The number of the threads to use.", category: "advanced"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Virusbreakend {
+ input {
+ File bam
+ File bamIndex
+ File referenceFasta
+ File referenceFastaFai
+ File referenceFastaDict
+ File referenceImg
+ File virusbreakendDB
+ String outputPath = "./virusbreakend.vcf"
+
+ String memory = "75G"
+ Int threads = 8
+ String dockerImage = "quay.io/biowdl/gridss:2.12.2"
+ Int timeMinutes = 180
+ }
+
+ command {
+ set -e
+ mkdir virusbreakenddb
+ tar -xzvf ~{virusbreakendDB} -C virusbreakenddb --strip-components 1
+ virusbreakend \
+ --output ~{outputPath} \
+ --workingdir . \
+ --reference ~{referenceFasta} \
+ --db virusbreakenddb \
+ --jar /usr/local/share/gridss-2.12.2-0/gridss.jar \
+ -t ~{threads} \
+ ~{bam}
+ }
+
+ output {
+ File vcf = outputPath
+ File summary = "~{outputPath}.summary.tsv"
+ }
+
+ runtime {
+ cpu: threads
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ bam: {description: "A BAM file.", category: "required"}
+ bamIndex: {description: "The index for the BAM file.", category: "required"}
+ referenceFasta: {description: "The fasta of the reference genome.", category: "required"}
+ referenceImg: {description: "The BWA index image (generated with GATK BwaMemIndexImageCreator) of the reference.", category: "required"}
+ virusbreakendDB: {description: "A .tar.gz containing the virusbreakend database.", category: "required"}
+ outputPath: {description: "The path the output should be written to.", category: "common"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ threads: {description: "The number of the threads to use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
+ }
+}
diff --git a/hmftools.wdl b/hmftools.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..76620e3cc37e291d826561a13db437ae9fa13c6a
--- /dev/null
+++ b/hmftools.wdl
@@ -0,0 +1,930 @@
+version 1.0
+
+# Copyright (c) 2020 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 Amber {
+ input {
+ String referenceName
+ File referenceBam
+ File referenceBamIndex
+ String tumorName
+ File tumorBam
+ File tumorBamIndex
+ String outputDir = "./amber"
+ File loci
+ File referenceFasta
+ File referenceFastaFai
+ File referenceFastaDict
+
+ Int threads = 2
+ String memory = "70G"
+ String javaXmx = "64G"
+ Int timeMinutes = 240
+ String dockerImage = "quay.io/biocontainers/hmftools-amber:3.5--0"
+ }
+
+ command {
+ AMBER -Xmx~{javaXmx} \
+ -reference ~{referenceName} \
+ -reference_bam ~{referenceBam} \
+ -tumor ~{tumorName} \
+ -tumor_bam ~{tumorBam} \
+ -output_dir ~{outputDir} \
+ -threads ~{threads} \
+ -ref_genome ~{referenceFasta} \
+ -loci ~{loci}
+ }
+
+ output {
+ File version = "~{outputDir}/amber.version"
+ File tumorBafPcf = "~{outputDir}/~{tumorName}.amber.baf.pcf"
+ File tumorBafTsv = "~{outputDir}/~{tumorName}.amber.baf.tsv"
+ File tumorBafVcf = "~{outputDir}/~{tumorName}.amber.baf.vcf.gz"
+ File tumorBafVcfIndex = "~{outputDir}/~{tumorName}.amber.baf.vcf.gz.tbi"
+ File tumorContaminationVcf = "~{outputDir}/~{tumorName}.amber.contamination.vcf.gz"
+ File tumorContaminationVcfIndex = "~{outputDir}/~{tumorName}.amber.contamination.vcf.gz.tbi"
+ File tumorContaminationTsv = "~{outputDir}/~{tumorName}.amber.contamination.tsv"
+ File tumorQc = "~{outputDir}/~{tumorName}.amber.qc"
+ File normalSnpVcf = "~{outputDir}/~{referenceName}.amber.snp.vcf.gz"
+ File normalSnpVcfIndex = "~{outputDir}/~{referenceName}.amber.snp.vcf.gz.tbi"
+ Array[File] outputs = [version, tumorBafPcf, tumorBafTsv, tumorBafVcf, tumorBafVcfIndex,
+ tumorContaminationVcf, tumorContaminationVcfIndex, tumorContaminationTsv, tumorQc,
+ normalSnpVcf, normalSnpVcfIndex]
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ cpu: threads
+ }
+
+ parameter_meta {
+ referenceName: {description: "the name of the normal sample.", category: "required"}
+ referenceBam: {description: "The normal BAM file.", category: "required"}
+ referenceBamIndex: {description: "The index for the normal BAM file.", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ tumorBam: {description: "The tumor BAM file.", category: "required"}
+ tumorBamIndex: {description: "The index for the tumor BAM file.", category: "required"}
+ outputDir: {description: "The path to the output directory.", category: "common"}
+ loci: {description: "A VCF file containing likely heterozygous sites.", 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"}
+ threads: {description: "The number of threads the program will use.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Cobalt {
+ input {
+ String referenceName
+ File referenceBam
+ File referenceBamIndex
+ String tumorName
+ File tumorBam
+ File tumorBamIndex
+ String outputDir = "./cobalt"
+ File gcProfile
+
+ Int threads = 1
+ String memory = "5G"
+ String javaXmx = "4G"
+ Int timeMinutes = 240
+ String dockerImage = "quay.io/biocontainers/hmftools-cobalt:1.11--0"
+ }
+
+ command {
+ COBALT -Xmx~{javaXmx} \
+ -reference ~{referenceName} \
+ -reference_bam ~{referenceBam} \
+ -tumor ~{tumorName} \
+ -tumor_bam ~{tumorBam} \
+ -output_dir ~{outputDir} \
+ -threads ~{threads} \
+ -gc_profile ~{gcProfile}
+ }
+
+ output {
+ File version = "~{outputDir}/cobalt.version"
+ File normalGcMedianTsv = "~{outputDir}/~{referenceName}.cobalt.gc.median.tsv"
+ File normalRationMedianTsv = "~{outputDir}/~{referenceName}.cobalt.ratio.median.tsv"
+ File normalRationPcf = "~{outputDir}/~{referenceName}.cobalt.ratio.pcf"
+ File tumorGcMedianTsv = "~{outputDir}/~{tumorName}.cobalt.gc.median.tsv"
+ File tumorRatioPcf = "~{outputDir}/~{tumorName}.cobalt.ratio.pcf"
+ File tumorRatioTsv = "~{outputDir}/~{tumorName}.cobalt.ratio.tsv"
+ File tumorChrLen = "~{outputDir}/~{tumorName}.chr.len"
+ Array[File] outputs = [version, normalGcMedianTsv, normalRationMedianTsv,
+ normalRationPcf, tumorGcMedianTsv, tumorRatioPcf, tumorRatioTsv, tumorChrLen]
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ cpu: threads
+ }
+
+ parameter_meta {
+ referenceName: {description: "the name of the normal sample.", category: "required"}
+ referenceBam: {description: "The normal BAM file.", category: "required"}
+ referenceBamIndex: {description: "The index for the normal BAM file.", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ tumorBam: {description: "The tumor BAM file.", category: "required"}
+ tumorBamIndex: {description: "The index for the tumor BAM file.", category: "required"}
+ outputDir: {description: "The path to the output directory.", category: "common"}
+ gcProfile: {description: "A file describing the GC profile of the reference genome.", category: "required"}
+ threads: {description: "The number of threads the program will use.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Cuppa {
+ input {
+ Array[File]+ linxOutput
+ Array[File]+ purpleOutput
+ String sampleName
+ Array[String]+ categories = ["DNA"]
+ Array[File]+ referenceData
+ File purpleSvVcf
+ File purpleSvVcfIndex
+ File purpleSomaticVcf
+ File purpleSomaticVcfIndex
+ String outputDir = "./cuppa"
+
+ String javaXmx = "4G"
+ String memory = "5G"
+ Int timeMinutes = 10
+ String dockerImage = "quay.io/biowdl/cuppa:1.4"
+ }
+
+ command {
+ set -e
+ mkdir -p sampleData ~{outputDir}
+ ln -s -t sampleData ~{sep=" " linxOutput} ~{sep=" " purpleOutput}
+ cuppa -Xmx~{javaXmx} \
+ -output_dir ~{outputDir} \
+ -output_id ~{sampleName} \
+ -categories '~{sep="," categories}' \
+ -ref_data_dir ~{sub(referenceData[0], basename(referenceData[0]), "")} \
+ -sample_data_dir sampleData \
+ -sample_data ~{sampleName} \
+ -sample_sv_file ~{purpleSvVcf} \
+ -sample_somatic_vcf ~{purpleSomaticVcf}
+ }
+
+ output {
+ File cupData = "~{outputDir}/~{sampleName}.cup.data.csv"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ linxOutput: {description: "The files produced by linx.", category: "required"}
+ purpleOutput: {description: "The files produced by purple.", category: "required"}
+ sampleName: {description: "The name of the sample.", category: "required"}
+ categories: {description: "The classifiers to use.", category: "advanced"}
+ referenceData : {description: "The reference data.", category: "required"}
+ purpleSvVcf: {description: "The VCF file produced by purple which contains structural variants.", category: "required"}
+ purpleSvVcfIndex: {description: "The index of the structural variants VCF file produced by purple.", category: "required"}
+ purpleSomaticVcf: {description: "The VCF file produced by purple which contains somatic variants.", category: "required"}
+ purpleSomaticVcfIndex: {description: "The index of the somatic VCF file produced by purple.", category: "required"}
+ outputDir: {description: "The directory the ouput will be placed in.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 CuppaChart {
+ input {
+ String sampleName
+ File cupData
+ String outputDir = "./cuppa"
+
+ String memory = "4G"
+ Int timeMinutes = 5
+ String dockerImage = "quay.io/biowdl/cuppa:1.4"
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ cuppa-chart \
+ -sample ~{sampleName} \
+ -sample_data ~{cupData} \
+ -output_dir ~{outputDir}
+ }
+
+ output {
+ File cuppaChart = "~{outputDir}/~{sampleName}.cuppa.chart.png"
+ File cuppaConclusion = "~{outputDir}/~{sampleName}.cuppa.conclusion.txt"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ sampleName: {description: "The name of the sample.", category:"common"}
+ cupData: {description: "The cuppa output.", category: "required"}
+ outputDir: {description: "The directory the output will be written to.", category:"common"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 GripssApplicationKt {
+ input {
+ File inputVcf
+ String outputPath = "gripss.vcf.gz"
+ String tumorName
+ String referenceName
+ File referenceFasta
+ File referenceFastaFai
+ File referenceFastaDict
+ File breakpointHotspot
+ File breakendPon
+ File breakpointPon
+
+ String memory = "32G"
+ String javaXmx = "31G"
+ Int timeMinutes = 45
+ String dockerImage = "quay.io/biocontainers/hmftools-gripss:1.11--hdfd78af_0"
+ }
+
+ command {
+ java -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -cp /usr/local/share/hmftools-gripss-1.11-0/gripss.jar \
+ com.hartwig.hmftools.gripss.GripssApplicationKt \
+ -tumor ~{tumorName} \
+ -reference ~{referenceName} \
+ -ref_genome ~{referenceFasta} \
+ -breakpoint_hotspot ~{breakpointHotspot} \
+ -breakend_pon ~{breakendPon} \
+ -breakpoint_pon ~{breakpointPon} \
+ -input_vcf ~{inputVcf} \
+ -output_vcf ~{outputPath} \
+ -paired_normal_tumor_ordinals
+ }
+
+ output {
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ inputVcf: {description: "The input VCF.", category: "required"}
+ outputPath: {description: "The path where th eoutput VCF will be written.", category: "common"}
+ 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"}
+ breakpointHotspot: {description: "Equivalent to the `-breakpoint_hotspot` option.", category: "required"}
+ breakendPon: {description: "Equivalent to the `-breakend_pon` option.", category: "required"}
+ breakpointPon: {description: "Equivalent to the `breakpoint_pon` option.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 GripssHardFilterApplicationKt {
+ input {
+ File inputVcf
+ String outputPath = "gripss_hard_filter.vcf.gz"
+
+ String memory = "3G"
+ String javaXmx = "2G"
+ Int timeMinutes = 15
+ String dockerImage = "quay.io/biocontainers/hmftools-gripss:1.11--hdfd78af_0"
+ }
+
+ command {
+ java -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -cp /usr/local/share/hmftools-gripss-1.11-0/gripss.jar \
+ com.hartwig.hmftools.gripss.GripssHardFilterApplicationKt \
+ -input_vcf ~{inputVcf} \
+ -output_vcf ~{outputPath}
+ }
+
+ output {
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ inputVcf: {description: "The input VCF.", category: "required"}
+ outputPath: {description: "The path where th eoutput VCF will be written.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 HealthChecker {
+ input {
+ String outputDir = "."
+ String referenceName
+ File referenceFlagstats
+ File referenceMetrics
+ String tumorName
+ File tumorFlagstats
+ File tumorMetrics
+ Array[File]+ purpleOutput
+
+ String javaXmx = "2G"
+ String memory = "1G"
+ Int timeMinutes = 1
+ String dockerImage = "quay.io/biowdl/health-checker:3.2"
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ health-checker -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -reference ~{referenceName} \
+ -ref_flagstat_file ~{referenceFlagstats} \
+ -ref_wgs_metrics_file ~{referenceMetrics} \
+ -tumor ~{tumorName} \
+ -tum_flagstat_file ~{tumorFlagstats} \
+ -tum_wgs_metrics_file ~{tumorMetrics} \
+ -purple_dir ~{sub(purpleOutput[0], basename(purpleOutput[0]), "")} \
+ -output_dir ~{outputDir}
+ test -e '~{outputDir}/~{tumorName}.HealthCheckSucceeded' && echo 'true' > '~{outputDir}/succeeded'
+ test -e '~{outputDir}/~{tumorName}.HealthCheckFailed' && echo 'false' > '~{outputDir}/succeeded'
+ }
+
+ output {
+ Boolean succeeded = read_boolean("result")
+ File outputFile = if succeeded
+ then "~{outputDir}/~{tumorName}.HealthCheckSucceeded"
+ else "~{outputDir}/~{tumorName}.HealthCheckFailed"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ outputDir: {description: "The path the output will be written to.", category:"required"}
+ referenceName: {description: "The name of the normal sample.", category: "required"}
+ referenceFlagstats: {description: "The flagstats for the normal sample.", category: "required"}
+ referenceMetrics: {description: "The picard WGS metrics for the normal sample.", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ tumorFlagstats: {description: "The flagstats for the tumor sample.", category: "required"}
+ tumorMetrics: {description: "The picard WGS metrics for the tumor sample.", category: "required"}
+ purpleOutput: {description: "The files from purple's output directory.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Linx {
+ input {
+ String sampleName
+ File svVcf
+ File svVcfIndex
+ Array[File]+ purpleOutput
+ String refGenomeVersion
+ String outputDir = "./linx"
+ File fragileSiteCsv
+ File lineElementCsv
+ File replicationOriginsBed
+ File viralHostsCsv
+ File knownFusionCsv
+ File driverGenePanel
+ #The following should be in the same directory.
+ File geneDataCsv
+ File proteinFeaturesCsv
+ File transExonDataCsv
+ File transSpliceDataCsv
+
+ String memory = "5G"
+ String javaXmx = "4G"
+ Int timeMinutes = 10
+ String dockerImage = "quay.io/biocontainers/hmftools-linx:1.16--hdfd78af_0"
+ }
+
+ command {
+ linx -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -sample ~{sampleName} \
+ -sv_vcf ~{svVcf} \
+ -purple_dir ~{sub(purpleOutput[0], basename(purpleOutput[0]), "")} \
+ -ref_genome_version ~{refGenomeVersion} \
+ -output_dir ~{outputDir} \
+ -fragile_site_file ~{fragileSiteCsv} \
+ -line_element_file ~{lineElementCsv} \
+ -replication_origins_file ~{replicationOriginsBed} \
+ -viral_hosts_file ~{viralHostsCsv} \
+ -gene_transcripts_dir ~{sub(geneDataCsv, basename(geneDataCsv), "")} \
+ -check_fusions \
+ -known_fusion_file ~{knownFusionCsv} \
+ -check_drivers \
+ -driver_gene_panel ~{driverGenePanel} \
+ -chaining_sv_limit 0 \
+ -write_vis_data
+ }
+
+ output {
+ File driverCatalog = "~{outputDir}/~{sampleName}.linx.driver.catalog.tsv"
+ File linxBreakend = "~{outputDir}/~{sampleName}.linx.breakend.tsv"
+ File linxClusters = "~{outputDir}/~{sampleName}.linx.clusters.tsv"
+ File linxDrivers = "~{outputDir}/~{sampleName}.linx.drivers.tsv"
+ File linxFusion = "~{outputDir}/~{sampleName}.linx.fusion.tsv"
+ File linxLinks = "~{outputDir}/~{sampleName}.linx.links.tsv"
+ File linxSvs = "~{outputDir}/~{sampleName}.linx.svs.tsv"
+ File linxViralInserts = "~{outputDir}/~{sampleName}.linx.viral_inserts.tsv"
+ File linxVisCopyNumber = "~{outputDir}/~{sampleName}.linx.vis_copy_number.tsv"
+ File linxVisFusion = "~{outputDir}/~{sampleName}.linx.vis_fusion.tsv"
+ File linxVisGeneExon = "~{outputDir}/~{sampleName}.linx.vis_gene_exon.tsv"
+ File linxVisProteinDomain = "~{outputDir}/~{sampleName}.linx.vis_protein_domain.tsv"
+ File linxVisSegments = "~{outputDir}/~{sampleName}.linx.vis_segments.tsv"
+ File linxVisSvData = "~{outputDir}/~{sampleName}.linx.vis_sv_data.tsv"
+ File linxVersion = "~{outputDir}/linx.version"
+ Array[File] outputs = [driverCatalog, linxBreakend, linxClusters, linxDrivers, linxFusion,
+ linxLinks, linxSvs, linxViralInserts, linxVisCopyNumber,
+ linxVisFusion, linxVisGeneExon, linxVisProteinDomain,
+ linxVisSegments, linxVisSvData, linxVersion]
+ }
+
+ runtime {
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ sampleName: {description: "The name of the sample.", category: "required"}
+ svVcf: {description: "A VCF file containing structural variants, produced using GRIDSS, annotated for viral insertions and postprocessed with GRIPSS.", category: "required"}
+ svVcfIndex: {description: "Index for the structural variants VCf file.", category: "required"}
+ purpleOutput: {description: "The files produced by PURPLE.", category: "required"}
+ refGenomeVersion: {description: "The version of the genome assembly used for alignment. Either \"HG19\" or \"HG38\".", category: "required"}
+ outputDir: {description: "The directory the outputs will be written to.", category: "required"}
+ fragileSiteCsv: {description: "A list of known fragile sites.", category: "required"}
+ lineElementCsv: {description: "A list of known LINE source regions.", category: "required"}
+ replicationOriginsBed: {description: "Replication timing input in BED format with replication timing as the 4th column.", category: "required"}
+ viralHostsCsv: {description: "A list of the viruses which were used for annotation of the GRIDSS results.", category: "required"}
+ knownFusionCsv: {description: "A CSV file describing known fusions.", category: "required"}
+ driverGenePanel: {description: "A TSV file describing the driver gene panel.", category: "required"}
+ geneDataCsv: {description: "A CSV file containing gene information, must be in the same directory as `proteinFeaturesCsv`, `transExonDataCsv` and `transSpliceDataCsv`.", category: "required"}
+ proteinFeaturesCsv: {description: "A CSV file containing protein feature information, must be in the same directory as `geneDataCsv`, `transExonDataCsv` and `transSpliceDataCsv`.", category: "required"}
+ transExonDataCsv: {description: "A CSV file containing transcript exon information, must be in the same directory as `geneDataCsv`, `proteinFeaturesCsv` and `transSpliceDataCsv`.", category: "required"}
+ transSpliceDataCsv: {description: "A CSV file containing transcript splicing information, must be in the same directory as `geneDataCsv`, `proteinFeaturesCsv` and `transExonDataCsv`.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Protect {
+ input {
+ String refGenomeVersion
+ String tumorName
+ String referenceName
+ Array[String]+ sampleDoids
+ String outputDir = "."
+ Array[File]+ serveActionability
+ File doidJson
+ File purplePurity
+ File purpleQc
+ File purpleDriverCatalogSomatic
+ File purpleDriverCatalogGermline
+ File purpleSomaticVariants
+ File purpleSomaticVariantsIndex
+ File purpleGermlineVariants
+ File purpleGermlineVariantsIndex
+ File purpleGeneCopyNumber
+ File linxFusion
+ File linxBreakend
+ File linxDriversCatalog
+ File chordPrediction
+ File annotatedVirus
+
+ String memory = "9G"
+ String javaXmx = "8G"
+ Int timeMinutes = 60
+ String dockerImage = "quay.io/biowdl/protect:v1.4"
+ }
+
+ command {
+ protect -Xmx~{javaXmx} \
+ -ref_genome_version ~{refGenomeVersion} \
+ -tumor_sample_id ~{tumorName} \
+ -reference_sample_id ~{referenceName} \
+ -primary_tumor_doids '~{sep=";" sampleDoids}' \
+ -output_dir ~{outputDir} \
+ -serve_actionability_dir ~{sub(serveActionability[0], basename(serveActionability[0]), "")} \
+ -doid_json ~{doidJson} \
+ -purple_purity_tsv ~{purplePurity} \
+ -purple_qc_file ~{purpleQc} \
+ -purple_somatic_driver_catalog_tsv ~{purpleDriverCatalogSomatic} \
+ -purple_germline_driver_catalog_tsv ~{purpleDriverCatalogGermline} \
+ -purple_somatic_variant_vcf ~{purpleSomaticVariants} \
+ -purple_germline_variant_vcf ~{purpleGermlineVariants} \
+ -purple_gene_copy_number_tsv ~{purpleGeneCopyNumber} \
+ -linx_fusion_tsv ~{linxFusion} \
+ -linx_breakend_tsv ~{linxBreakend} \
+ -linx_driver_catalog_tsv ~{linxDriversCatalog} \
+ -chord_prediction_txt ~{chordPrediction} \
+ -annotated_virus_tsv ~{annotatedVirus}
+ }
+
+ output {
+ File protectTsv = "~{outputDir}/~{tumorName}.protect.tsv"
+ }
+
+ runtime {
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ refGenomeVersion: {description: "The version of the genome assembly used for alignment. Either \"37\" or \"38\".", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ referenceName: {description: "The name of the normal sample.", category: "required"}
+ sampleDoids: {description: "The DOIDs (Human Disease Ontology) for the primary tumor.", category: "required"}
+ outputDir: {description: "The directory the outputs will be written to.", category: "required"}
+ serveActionability: {description: "The actionability files generated by hmftools' serve.", category: "required"}
+ doidJson: {description: "A json with the DOID (Human Disease Ontology) tree.", category: "required"}
+ purplePurity: {description: "The purity file generated by purple.", category: "required"}
+ purpleQc: {description: "The QC file generated by purple.", category: "required"}
+ purpleDriverCatalogSomatic: {description: "The somatic driver catalog generated by purple.", category: "required"}
+ purpleDriverCatalogGermline: {description: "The germline driver catalog generated by purple.", category: "required"}
+ purpleSomaticVariants: {description: "The somatic VCF generated by purple.", category: "required"}
+ purpleSomaticVariantsIndex: {description: "The index for the somatic VCF generated by purple.", category: "required"}
+ purpleGermlineVariants: {description: "The germline VCF generated by purple.", category: "required"}
+ purpleGermlineVariantsIndex: {description: "The index of the germline VCF generated by purple.", category: "required"}
+ purpleGeneCopyNumber: {description: "The gene copy number file generated by purple.", category: "required"}
+ linxFusion: {description: "The fusion file generated by linx.", category: "required"}
+ linxBreakend: {description: "The breakend file generated by linx.", category: "required"}
+ linxDriversCatalog: {description: "The driver catalog generated generated by linx.", category: "required"}
+ chordPrediction: {description: "The chord prediction file.", category: "required"}
+ annotatedVirus: {description: "The virus-interpreter output.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Purple {
+ input {
+ String referenceName
+ String tumorName
+ String outputDir = "./purple"
+ Array[File]+ amberOutput
+ Array[File]+ cobaltOutput
+ File gcProfile
+ File somaticVcf
+ File germlineVcf
+ File filteredSvVcf
+ File? fullSvVcf
+ File? fullSvVcfIndex
+ File referenceFasta
+ File referenceFastaFai
+ File referenceFastaDict
+ File driverGenePanel
+ File somaticHotspots
+ File germlineHotspots
+
+ Int threads = 1
+ Int timeMinutes = 30
+ String memory = "9G"
+ String javaXmx = "8G"
+ # clone of quay.io/biocontainers/hmftools-purple:3.1--hdfd78af_0 with 'ln -s /usr/local/lib/libwebp.so.7 /usr/local/lib/libwebp.so.6'
+ String dockerImage = "quay.io/biowdl/hmftools-purple:3.1"
+ }
+
+ command {
+ PURPLE -Xmx~{javaXmx} \
+ -reference ~{referenceName} \
+ -tumor ~{tumorName} \
+ -output_dir ~{outputDir} \
+ -amber ~{sub(amberOutput[0], basename(amberOutput[0]), "")} \
+ -cobalt ~{sub(cobaltOutput[0], basename(cobaltOutput[0]), "")} \
+ -gc_profile ~{gcProfile} \
+ -somatic_vcf ~{somaticVcf} \
+ -germline_vcf ~{germlineVcf} \
+ -structural_vcf ~{filteredSvVcf} \
+ ~{"-sv_recovery_vcf " + fullSvVcf} \
+ -circos /usr/local/bin/circos \
+ -ref_genome ~{referenceFasta} \
+ -driver_catalog \
+ -driver_gene_panel ~{driverGenePanel} \
+ -somatic_hotspots ~{somaticHotspots} \
+ -germline_hotspots ~{germlineHotspots} \
+ -threads ~{threads}
+ }
+
+ output {
+ File driverCatalogSomaticTsv = "~{outputDir}/~{tumorName}.driver.catalog.somatic.tsv"
+ File driverCatalogGermlineTsv = "~{outputDir}/~{tumorName}.driver.catalog.germline.tsv"
+ File purpleCnvGeneTsv = "~{outputDir}/~{tumorName}.purple.cnv.gene.tsv"
+ File purpleCnvGermlineTsv = "~{outputDir}/~{tumorName}.purple.cnv.germline.tsv"
+ File purpleCnvSomaticTsv = "~{outputDir}/~{tumorName}.purple.cnv.somatic.tsv"
+ File purplePurityRangeTsv = "~{outputDir}/~{tumorName}.purple.purity.range.tsv"
+ File purplePurityTsv = "~{outputDir}/~{tumorName}.purple.purity.tsv"
+ File purpleQc = "~{outputDir}/~{tumorName}.purple.qc"
+ File purpleSegmentTsv = "~{outputDir}/~{tumorName}.purple.segment.tsv"
+ File purpleSomaticClonalityTsv = "~{outputDir}/~{tumorName}.purple.somatic.clonality.tsv"
+ File purpleSomaticHistTsv = "~{outputDir}/~{tumorName}.purple.somatic.hist.tsv"
+ File purpleSomaticVcf = "~{outputDir}/~{tumorName}.purple.somatic.vcf.gz"
+ File purpleSomaticVcfIndex = "~{outputDir}/~{tumorName}.purple.somatic.vcf.gz.tbi"
+ File purpleGermlineVcf = "~{outputDir}/~{tumorName}.purple.germline.vcf.gz"
+ File purpleGermlineVcfIndex = "~{outputDir}/~{tumorName}.purple.germline.vcf.gz.tbi"
+ File purpleSvVcf = "~{outputDir}/~{tumorName}.purple.sv.vcf.gz"
+ File purpleSvVcfIndex = "~{outputDir}/~{tumorName}.purple.sv.vcf.gz.tbi"
+ File circosPlot = "~{outputDir}/plot/~{tumorName}.circos.png"
+ File copynumberPlot = "~{outputDir}/plot/~{tumorName}.copynumber.png"
+ File inputPlot = "~{outputDir}/plot/~{tumorName}.input.png"
+ File mapPlot = "~{outputDir}/plot/~{tumorName}.map.png"
+ File purityRangePlot = "~{outputDir}/plot/~{tumorName}.purity.range.png"
+ File segmentPlot = "~{outputDir}/plot/~{tumorName}.segment.png"
+ File somaticClonalityPlot = "~{outputDir}/plot/~{tumorName}.somatic.clonality.png"
+ File somaticPlot = "~{outputDir}/plot/~{tumorName}.somatic.png"
+ File purpleVersion = "~{outputDir}/purple.version"
+ File circosNormalRatio = "~{outputDir}/circos/~{referenceName}.ratio.circos"
+ File circosConf = "~{outputDir}/circos/~{tumorName}.circos.conf"
+ File circosIndel = "~{outputDir}/circos/~{tumorName}.indel.circos"
+ File circosLink = "~{outputDir}/circos/~{tumorName}.link.circos"
+ File circosTumorRatio = "~{outputDir}/circos/~{tumorName}.ratio.circos"
+ File circosGaps = "~{outputDir}/circos/gaps.txt"
+ File circosBaf = "~{outputDir}/circos/~{tumorName}.baf.circos"
+ File circosCnv = "~{outputDir}/circos/~{tumorName}.cnv.circos"
+ File circosInputConf = "~{outputDir}/circos/~{tumorName}.input.conf"
+ File circosMap = "~{outputDir}/circos/~{tumorName}.map.circos"
+ File circosSnp = "~{outputDir}/circos/~{tumorName}.snp.circos"
+ Array[File] outputs = [driverCatalogSomaticTsv, purpleCnvGeneTsv, purpleCnvGermlineTsv,
+ purpleCnvSomaticTsv, purplePurityRangeTsv, purplePurityTsv, purpleQc,
+ purpleSegmentTsv, purpleSomaticClonalityTsv, purpleSomaticHistTsv,
+ purpleSomaticVcf, purpleSomaticVcfIndex, purpleSvVcf, purpleSvVcfIndex,
+ purpleVersion, purpleGermlineVcf, purpleGermlineVcfIndex, driverCatalogGermlineTsv]
+ Array[File] plots = [circosPlot, copynumberPlot, inputPlot, mapPlot, purityRangePlot,
+ segmentPlot, somaticClonalityPlot, somaticPlot]
+ Array[File] circos = [circosNormalRatio, circosConf, circosIndel, circosLink,
+ circosTumorRatio, circosGaps, circosBaf, circosCnv, circosInputConf, circosMap,
+ circosSnp]
+ }
+
+ runtime {
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ cpu: threads
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ referenceName: {description: "the name of the normal sample.", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ outputDir: {description: "The path to the output directory.", category: "common"}
+ amberOutput: {description: "The output files of hmftools amber.", category: "required"}
+ cobaltOutput: {description: "The output files of hmftools cobalt", category: "required"}
+ gcProfile: {description: "A file describing the GC profile of the reference genome.", category: "required"}
+ somaticVcf: {description: "The somatic variant calling results.", category: "required"}
+ germlineVcf: {description: "The germline variant calling results.", category: "required"}
+ filteredSvVcf: {description: "The filtered structural variant calling results.", category: "required"}
+ fullSvVcf: {description: "The unfiltered structural variant calling results.", 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"}
+ driverGenePanel: {description: "A TSV file describing the driver gene panel.", category: "required"}
+ somaticHotspots: {description: "A vcf file with hotspot somatic variant sites.", category: "required"}
+ germlineHotspots: {description: "A vcf file with hotspot germline variant sites.", category: "required"}
+
+ threads: {description: "The number of threads the program will use.", 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Sage {
+ input {
+ String tumorName
+ File tumorBam
+ File tumorBamIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ File hotspots
+ File panelBed
+ File highConfidenceBed
+ Boolean hg38 = false
+ Boolean panelOnly = false
+ String outputPath = "./sage.vcf.gz"
+
+ String? referenceName
+ File? referenceBam
+ File? referenceBamIndex
+ Int? hotspotMinTumorQual
+ Int? panelMinTumorQual
+ Int? hotspotMaxGermlineVaf
+ Int? hotspotMaxGermlineRelRawBaseQual
+ Int? panelMaxGermlineVaf
+ Int? panelMaxGermlineRelRawBaseQual
+ String? mnvFilterEnabled
+ File? coverageBed
+
+ Int threads = 4
+ String javaXmx = "50G"
+ String memory = "51G"
+ Int timeMinutes = 1 + ceil(size(select_all([tumorBam, referenceBam]), "G") * 9 / threads)
+ String dockerImage = "quay.io/biocontainers/hmftools-sage:2.8--hdfd78af_0"
+ }
+
+ command {
+ SAGE -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -tumor ~{tumorName} \
+ -tumor_bam ~{tumorBam} \
+ ~{"-reference " + referenceName} \
+ ~{"-reference_bam " + referenceBam} \
+ -ref_genome ~{referenceFasta} \
+ -hotspots ~{hotspots} \
+ -panel_bed ~{panelBed} \
+ -high_confidence_bed ~{highConfidenceBed} \
+ -assembly ~{true="hg38" false="hg19" hg38} \
+ ~{"-hotspot_min_tumor_qual " + hotspotMinTumorQual} \
+ ~{"-panel_min_tumor_qual " + panelMinTumorQual} \
+ ~{"-hotspot_max_germline_vaf " + hotspotMaxGermlineVaf} \
+ ~{"-hotspot_max_germline_rel_raw_base_qual " + hotspotMaxGermlineRelRawBaseQual} \
+ ~{"-panel_max_germline_vaf " + panelMaxGermlineVaf} \
+ ~{"-panel_max_germline_rel_raw_base_qual " + panelMaxGermlineRelRawBaseQual} \
+ ~{"-mnv_filter_enabled " + mnvFilterEnabled} \
+ ~{"-coverage_bed " + coverageBed} \
+ ~{true="-panel_only" false="" panelOnly} \
+ -threads ~{threads} \
+ -out ~{outputPath}
+ }
+
+ output {
+ File outputVcf = outputPath
+ File outputVcfIndex = outputPath + ".tbi"
+ # There is some plots as well, but in the current container the labels in the plots are just series of `â–¡`s.
+ # This seems to be a systemic issue with R generated plots in biocontainers...
+ }
+
+ runtime {
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ cpu: threads
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ tumorBam: {description: "The BAM file for the tumor sample.", category: "required"}
+ tumorBamIndex: {description: "The index of the BAM file for the tumor sample.", category: "required"}
+ referenceName: {description: "The name of the normal/reference sample.", category: "common"}
+ referenceBam: {description: "The BAM file for the normal sample.", category: "common"}
+ referenceBamIndex: {description: "The index of the BAM file for the normal sample.", category: "common"}
+ 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"}
+ hotspots: {description: "A vcf file with hotspot variant sites.", category: "required"}
+ panelBed: {description: "A bed file describing coding regions to search for in frame indels.", category: "required"}
+ highConfidenceBed: {description: "A bed files describing high confidence mapping regions.", category: "required"}
+ hotspotMinTumorQual: {description: "Equivalent to sage's `hotspot_min_tumor_qual` option.", category: "advanced"}
+ panelMinTumorQual: {description: "Equivalent to sage's `panel_min_tumor_qual` option.", category: "advanced"}
+ hotspotMaxGermlineVaf: {description: "Equivalent to sage's `hotspot_max_germline_vaf` option.", category: "advanced"}
+ hotspotMaxGermlineRelRawBaseQual: {description: "Equivalent to sage's `hotspot_max_germline_rel_raw_base_qual` option.", category: "advanced"}
+ panelMaxGermlineVaf: {description: "Equivalent to sage's `panel_max_germline_vaf` option.", category: "advanced"}
+ panelMaxGermlineRelRawBaseQual: {description: "Equivalent to sage's `panel_max_germline_vaf` option.", category: "advanced"}
+ mnvFilterEnabled: {description: "Equivalent to sage's `mnv_filter_enabled` 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 VirusInterpreter {
+ input {
+ String sampleId
+ File virusBreakendTsv
+ File taxonomyDbTsv
+ File virusInterpretationTsv
+ File virusBlacklistTsv
+ String outputDir = "."
+
+ String memory = "3G"
+ String javaXmx = "2G"
+ Int timeMinutes = 15
+ String dockerImage = "quay.io/biowdl/virus-interpreter:1.0"
+ }
+
+ command {
+ virus-interpreter -Xmx~{javaXmx} \
+ -sample_id ~{sampleId} \
+ -virus_breakend_tsv ~{virusBreakendTsv} \
+ -taxonomy_db_tsv ~{taxonomyDbTsv} \
+ -virus_interpretation_tsv ~{virusInterpretationTsv} \
+ -virus_blacklist_tsv ~{virusBlacklistTsv} \
+ -output_dir ~{outputDir}
+ }
+
+ output {
+ File virusAnnotatedTsv = "~{outputDir}/~{sampleId}.virus.annotated.tsv"
+ }
+
+ runtime {
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ memory: memory
+ }
+
+ parameter_meta {
+ sampleId: {description: "The name of the sample.", category: "required"}
+ virusBreakendTsv: {description: "The TSV output from virusbreakend.", category: "required"}
+ taxonomyDbTsv: {description: "A taxonomy database tsv.", category: "required"}
+ virusInterpretationTsv: {description: "A virus interpretation tsv.", category: "required"}
+ virusBlacklistTsv: {description: "A virus blacklist tsv.", category: "required"}
+ outputDir: {description: "The directory the output will 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
+ }
+}
diff --git a/peach.wdl b/peach.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..af44daecfc342630d78866d93767b260147d1a0e
--- /dev/null
+++ b/peach.wdl
@@ -0,0 +1,77 @@
+version 1.0
+
+# Copyright (c) 2021 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 Peach {
+ input {
+ File transcriptTsv
+ File germlineVcf
+ File germlineVcfIndex
+ String tumorName
+ String normalName
+ String outputDir = "./peach"
+ File panelJson
+
+ String memory = "2G"
+ String dockerImage = "quay.io/biowdl/peach:v1.0"
+ Int timeMinutes = 5
+ }
+
+ command {
+ peach \
+ --recreate_bed \
+ --transcript_tsv ~{transcriptTsv} \
+ ~{germlineVcf} \
+ ~{tumorName} \
+ ~{normalName} \
+ 1.0 \
+ ~{outputDir} \
+ ~{panelJson} \
+ vcftools
+ }
+
+ output {
+ File callsTsv = "~{outputDir}/~{tumorName}.peach.calls.tsv"
+ File filteredVcf = "~{outputDir}/~{tumorName}.peach.filtered.vcf"
+ File genotypeTsv = "~{outputDir}/~{tumorName}.peach.genotype.tsv"
+ Array[File] outputs = [callsTsv, filteredVcf, genotypeTsv]
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ transcriptTsv: {description: "A tsv file describing transcripts.", category: "required"}
+ germlineVcf: {description: "The germline VCF file from hmftools' purple.", category: "required"}
+ germlineVcfIndex: {description: "The germline VCF's index.", category: "required"}
+ tumorName: {description: "The name of the tumor sample.", category: "required"}
+ normalName: {description: "The name of the normal sample", category: "required"}
+ outputDir: {description: "The directory the ouput should be written to.", category: "required"}
+ panelJson: {description: "A JSON describing the panel.", category: "required"}
+
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", 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"}
+ }
+}
\ No newline at end of file
diff --git a/picard.wdl b/picard.wdl
index f75fdc326133675c7a95286a14c09cba8079987c..9a935045bd9804ce37f7773b5f8db480fa3563b2 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -446,6 +446,70 @@ task CollectVariantCallingMetrics {
}
}
+task CollectWgsMetrics {
+ input {
+ File inputBam
+ File inputBamIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ String outputPath = "./wgs_metrics.txt"
+
+ Int? minimumMappingQuality
+ Int? minimumBaseQuality
+ Int? coverageCap
+
+ String memory = "5G"
+ String javaXmx = "4G"
+ Int timeMinutes = 1 + ceil(size(inputBam, "G") * 6)
+ String dockerImage = "quay.io/biocontainers/picard:2.23.2--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPath})"
+
+ picard -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ CollectWgsMetrics \
+ REFERENCE_SEQUENCE=~{referenceFasta} \
+ INPUT=~{inputBam} \
+ OUTPUT=~{outputPath} \
+ ~{"MINIMUM_MAPPING_QUALITY=" + minimumMappingQuality} \
+ ~{"MINIMUM_BASE_QUALITY=" + minimumBaseQuality} \
+ ~{"COVERAGE_CAP=" + coverageCap}
+ }
+
+ output {
+ File metrics = outputPath
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ parameter_meta {
+ # inputs
+ inputBam: {description: "The input BAM file for which metrics will be collected.", category: "required"}
+ inputBamIndex: {description: "The index of the input BAM file.", 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"}
+ outputPath: {description: "The path picard CollectWgsMetrics' output should be written to.", category: "common"}
+ minimumMappingQuality: {description: "Equivalent to picard CollectWgsMetrics' MINIMUM_MAPPING_QUALITY option.", category: "advanced"}
+ minimumBaseQuality: {description: "Equivalent to picard CollectWgsMetrics' MINIMUM_BASE_QUALITY option.", category: "advanced"}
+ coverageCap: {description: "Equivalent to picard CollectWgsMetrics' OVERAGE_CAP 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 CreateSequenceDictionary {
input {
File inputFile
diff --git a/sambamba.wdl b/sambamba.wdl
index df5ab4d1accd5568093587d1ca58bd4287e71bb3..4c2115e07dd95b2d126488a36846338b745b48fd 100644
--- a/sambamba.wdl
+++ b/sambamba.wdl
@@ -20,13 +20,56 @@ version 1.0
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
+task Flagstat {
+ input {
+ File inputBam
+ File inputBamIndex
+ String outputPath = "./flagstat.txt"
+
+ Int threads = 2
+ String memory = "8G"
+ Int timeMinutes = 120
+ String dockerImage = "quay.io/biocontainers/sambamba:0.7.1--h148d290_2"
+ }
+
+ command {
+ sambamba flagstat \
+ -t ~{threads} \
+ ~{inputBam} \
+ > ~{outputPath}
+ }
+
+ output {
+ File stats = outputPath
+ }
+
+ runtime {
+ cpu: threads
+ memory: memory
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ inputBam: {description: "The input BAM file.", category: "required"}
+ inputBamIndex: {description: "The index for the BAM file.", category: "required"}
+ outputPath: {description: "The path to write the ouput to.", category: "required"}
+
+ threads: {description: "The number of threads that will be used for this task.", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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 Markdup {
input {
Array[File] inputBams
String outputPath
Int compressionLevel = 1
# sortBufferSize and ioBufferSize taken from markdup defaults as of sambamba 0.7.1.
- Int sortBufferSize = 2048
+ Int sortBufferSize = 4096
Int ioBufferSize = 128
Boolean removeDuplicates = false
@@ -38,10 +81,10 @@ task Markdup {
# 2 threads reduces wall clock time by more than 40%.
Int threads = 2
# According to the manual sambamba markdup uses the sortbufferSize + 2 times the ioBuffer size.
- # Added 1024 mb as a margin of safety. Real life use with this setting uses 2.7 GiB.
- Int memoryMb = 1024 + sortBufferSize + 2 * ioBufferSize
+ # Added 8192 mb as a margin of safety. Real life use with this setting uses 2.7 GiB.
+ Int memoryMb = 8192 + sortBufferSize + 2 * ioBufferSize
# Time minute calculation does not work well for higher number of threads.
- Int timeMinutes = 1 + ceil(size(inputBams, "G") * 8) / threads
+ Int timeMinutes = 1 + ceil(size(inputBams, "G") * 25) / threads
String dockerImage = "quay.io/biocontainers/sambamba:0.7.1--h148d290_2"
}
diff --git a/snpeff.wdl b/snpeff.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..4a3640c7a8b5ea2a9da742bb76f7e1e0e48e38a6
--- /dev/null
+++ b/snpeff.wdl
@@ -0,0 +1,96 @@
+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2020 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 SnpEff {
+ input {
+ File vcf
+ File vcfIndex
+ String genomeVersion
+ File datadirZip
+ String outputPath = "./snpeff.vcf"
+ Boolean hgvs = true
+ Boolean lof = true
+ Boolean noDownstream = false
+ Boolean noIntergenic = false
+ Boolean noShiftHgvs = false
+ Int? upDownStreamLen
+
+ String memory = "9G"
+ String javaXmx = "8G"
+ Int timeMinutes = 60
+ String dockerImage = "quay.io/biocontainers/snpeff:5.0--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPath})"
+ unzip ~{datadirZip}
+ snpEff -Xmx~{javaXmx} -XX:ParallelGCThreads=1 \
+ -v \
+ ~{genomeVersion} \
+ -noDownload \
+ -dataDir $PWD/data \
+ ~{vcf} \
+ ~{true="-hgvs" false="-noHgvs" hgvs} \
+ ~{true="-lof" false="-noLof" lof} \
+ ~{true="-no-downstream" false="" noDownstream} \
+ ~{true="-no-intergenic" false="" noIntergenic} \
+ ~{true="-noShiftHgvs" false="" noShiftHgvs} \
+ ~{"-upDownStreamLen " + upDownStreamLen} \
+ > ~{outputPath}
+ rm -r $PWD/data
+ }
+
+ output {
+ File outputVcf = outputPath
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes # !UnknownRuntimeKey
+ memory: memory
+ }
+
+ parameter_meta {
+ vcf: {description: "A VCF file to analyse.", category: "required"}
+ vcfIndex: {description: "The index for the VCF file.", category: "required"}
+ genomeVersion: {description: "The version of the genome to be used. The database for this genome must be present in the datadirZip.", category: "required"}
+ datadirZip: {description: "A zip file containing the directory of databases. This zip file must contain a directory called `data`, with the database mentioned in the genomeVersion input as subdirectory.",
+ category: "required"}
+ outputPath: {description: "The path to write the output to.", category: "common"}
+ hgvs: {description: "Equivalent to `-hgvs` if true or `-noHgvs` if false.", category: "advanced"}
+ lof: {description: "Equivalent to `-lof` if true or `-noLof` if false.", category: "advanced"}
+ noDownstream: {description: "Equivalent to the `-no-downstream` flag.", category: "advanced"}
+ noIntergenic: {description: "Equivalent to the `-no-intergenic` flag.", category: "advanced"}
+ noShiftHgvs: {description: "Equivalent to the `-noShiftHgvs` flag.", category: "advanced"}
+ upDownStreamLen: {descriptoin: "Equivalent to the `-upDownStreamLen` 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"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
+ }
+}