From d101e77cf3211079a7b7ca50c0203ffea811919b Mon Sep 17 00:00:00 2001
From: JasperBoom <jboom@infernum.nl>
Date: Mon, 2 Nov 2020 15:38:52 +0100
Subject: [PATCH] Add last set of updates.
---
.github/PULL_REQUEST_TEMPLATE.md | 3 +-
CHANGELOG.md | 2 +
pacbio.wdl | 89 +++++++++++++++++++++++++
samtools.wdl | 2 +-
seqtk.wdl | 9 +--
smoove.wdl | 9 +--
somaticseq.wdl | 89 ++++++++++++-------------
spades.wdl | 12 ++--
star.wdl | 20 +++---
strelka.wdl | 34 +++++-----
stringtie.wdl | 18 ++---
survivor.wdl | 19 +++---
talon.wdl | 10 +--
transcriptclean.wdl | 21 +++---
umi-tools.wdl | 41 ++++++------
unicycler.wdl | 5 +-
vardict.wdl | 41 ++++++------
vt.wdl | 20 +++---
whatshap.wdl | 111 ++++++++++++++++---------------
wisestork.wdl | 44 ++++++------
20 files changed, 351 insertions(+), 248 deletions(-)
create mode 100644 pacbio.wdl
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 199344f..1d52f50 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -1,4 +1,3 @@
-
### Checklist
-- [ ] Pull request details were added to CHANGELOG.md
+- [ ] Pull request details were added to CHANGELOG.md.
- [ ] `parameter_meta` for each task is up to date.
diff --git a/CHANGELOG.md b/CHANGELOG.md
index f0dfaf1..e7d7fed 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ that users understand how the changes affect the new version.
version 5.0.0-dev
---------------------------
++ Samtools: `Sort` task now has `threads` in runtime instead of `1`.
+ Picard: Add parameter_meta to `SortSam`.
+ pbmm2: Add parameter_meta for `sample`.
+ Centrifuge: Rename output in task `KReport` to `KrakenReport` to resolve
@@ -20,6 +21,7 @@ version 5.0.0-dev
+ Bam2fastx: Add localisation of input files to Bam2Fasta task.
+ isoseq3: `cores` input has been renamed to `threads` to match tool naming.
+ CCS: `cores` input has been renamed to `threads` to match tool naming.
++ Add PacBio preprocessing specific tasks `mergePacBio` & `ccsChunks`.
+ CCS: Update CCS to version 5.
+ deepvariant: Add task for DeepVariant.
+ gatk: Make intervals optional for GenotypeGVCFs.
diff --git a/pacbio.wdl b/pacbio.wdl
new file mode 100644
index 0000000..01f6d4f
--- /dev/null
+++ b/pacbio.wdl
@@ -0,0 +1,89 @@
+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 mergePacBio {
+ input {
+ Array[File]+ reports
+ String mergedReport
+
+ String memory = "4G"
+ String dockerImage = "lumc/pacbio-merge:0.2"
+ }
+
+ command {
+ set -e
+ mkdir -p $(dirname ~{mergedReport})
+ pacbio_merge \
+ --reports ~{sep=" " reports} \
+ --json-output ~{mergedReport}
+ }
+
+ runtime {
+ memory: memory
+ docker: dockerImage
+ }
+
+ output {
+ File MergedReport = mergedReport
+ }
+
+ parameter_meta {
+ # inputs
+ reports: {description: "The PacBio report files to merge.", category: "required"}
+ mergedReport: {description: "The location the merged PacBio report file should be written to.", category: "common"}
+ memory: {description: "The amount of memory this job will use.", 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 ccsChunks {
+ input {
+ Int chunkCount
+
+ String memory = "4G"
+ String dockerImage = "python:3.7-slim"
+ }
+
+ command {
+ set -e
+ python <<CODE
+ for i in range(1, ~{chunkCount} + 1):
+ print(i, ~{chunkCount}, sep="/")
+ CODE
+ }
+
+ runtime {
+ memory: memory
+ docker: dockerImage
+ }
+
+ output {
+ Array[String] chunks = read_lines(stdout())
+ }
+
+ parameter_meta {
+ # inputs
+ chunkCount: {description: "The number of chunks to create.", category: "required"}
+ memory: {description: "The amount of memory this job will use.", 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/samtools.wdl b/samtools.wdl
index 496cf23..e274cf5 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -431,7 +431,7 @@ task Sort {
# outputs
outputBam: {description: "Sorted BAM file."}
- outputBamIndex: {description "Sorted BAM file index."}
+ outputBamIndex: {description: "Sorted BAM file index."}
}
}
diff --git a/seqtk.wdl b/seqtk.wdl
index 321ab13..f6fa422 100644
--- a/seqtk.wdl
+++ b/seqtk.wdl
@@ -24,11 +24,12 @@ task Sample {
input {
File sequenceFile
String outFilePath = "subsampledReads.fq.gz"
- String? preCommand
- Int? seed
Boolean twoPassMode = false
- Float fractionOrNumber # when above 1.0 is the number of reads, otherwise it's a fraction
+ Float fractionOrNumber # When above 1.0 is the number of reads, otherwise it's a fraction.
Boolean zip = true
+
+ String? preCommand
+ Int? seed
}
command {
@@ -47,4 +48,4 @@ task Sample {
output {
File subsampledReads = outFilePath
}
-}
\ No newline at end of file
+}
diff --git a/smoove.wdl b/smoove.wdl
index e8846f7..244c2ca 100644
--- a/smoove.wdl
+++ b/smoove.wdl
@@ -1,7 +1,5 @@
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
@@ -32,8 +30,8 @@ task Call {
String outputDir = "./smoove"
String memory = "15G"
- String dockerImage = "quay.io/biocontainers/smoove:0.2.5--0"
Int timeMinutes = 1440
+ String dockerImage = "quay.io/biocontainers/smoove:0.2.5--0"
}
command {
@@ -52,9 +50,8 @@ task Call {
runtime {
memory: memory
- docker: dockerImage
time_minutes: timeMinutes
-
+ docker: dockerImage
}
parameter_meta {
@@ -63,8 +60,8 @@ task Call {
bamIndex: {description: "The index of the bam file.", category: "required"}
referenceFasta: {description: "The reference fasta file also used for mapping.", category: "required"}
referenceFastaFai: {description: "Fasta index (.fai) file of the reference.", category: "required" }
- outputDir: {description: "The location the output VCF file should be written.", category: "common"}
sample: {description: "The name of the sample.", category: "required"}
+ outputDir: {description: "The location the output VCF file should be written.", category: "common"}
memory: {description: "The memory required to run the programs.", category: "advanced"}
timeMinutes: {description: "The maximum duration (in minutes) the tool is allowed to run.", 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/somaticseq.wdl b/somaticseq.wdl
index 7b9a440..1c73fc5 100644
--- a/somaticseq.wdl
+++ b/somaticseq.wdl
@@ -22,17 +22,18 @@ version 1.0
task ParallelPaired {
input {
- File? classifierSNV
- File? classifierIndel
String outputDir
File referenceFasta
File referenceFastaFai
- File? inclusionRegion
- File? exclusionRegion
File tumorBam
File tumorBamIndex
File normalBam
File normalBamIndex
+
+ File? classifierSNV
+ File? classifierIndel
+ File? inclusionRegion
+ File? exclusionRegion
File? mutect2VCF
File? varscanSNV
File? varscanIndel
@@ -95,17 +96,18 @@ task ParallelPaired {
}
parameter_meta {
- classifierSNV: {description: "A somaticseq SNV classifier.", category: "common"}
- classifierIndel: {description: "A somaticseq Indel classifier.", category: "common"}
+ # inputs
outputDir: {description: "The directory to write the output to.", category: "common"}
referenceFasta: {description: "The reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
- exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
- normalBam: {description: "The normal/control sample's BAM file.", category: "required"}
- normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "required"}
tumorBam: {description: "The tumor/case sample's BAM file.", category: "required"}
tumorBamIndex: {description: "The index for the tumor/case sample's BAM file.", category: "required"}
+ normalBam: {description: "The normal/control sample's BAM file.", category: "required"}
+ normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "required"}
+ classifierSNV: {description: "A somaticseq SNV classifier.", category: "common"}
+ classifierIndel: {description: "A somaticseq Indel classifier.", category: "common"}
+ inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
+ exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
mutect2VCF: {description: "A VCF as produced by mutect2.", category: "advanced"}
varscanSNV: {description: "An SNV VCF as produced by varscan.", category: "advanced"}
varscanIndel: {description: "An indel VCF as produced by varscan.", category: "advanced"}
@@ -118,11 +120,9 @@ task ParallelPaired {
scalpelVCF: {description: "A VCF as produced by scalpel.", category: "advanced"}
strelkaSNV: {description: "An SNV VCF as produced by strelka.", category: "advanced"}
strelkaIndel: {description: "An indel VCF as produced by somaticsniper.", category: "advanced"}
-
threads: {description: "The number of 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"}
+ 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"}
}
}
@@ -133,12 +133,13 @@ task ParallelPairedTrain {
String outputDir
File referenceFasta
File referenceFastaFai
- File? inclusionRegion
- File? exclusionRegion
File tumorBam
File tumorBamIndex
File normalBam
File normalBamIndex
+
+ File? inclusionRegion
+ File? exclusionRegion
File? mutect2VCF
File? varscanSNV
File? varscanIndel
@@ -200,17 +201,18 @@ task ParallelPairedTrain {
}
parameter_meta {
+ # inputs
truthSNV: {description: "A VCF of true SNVs.", category: "required"}
truthIndel: {description: "A VCF of true indels.", category: "required"}
outputDir: {description: "The directory to write the output to.", category: "common"}
referenceFasta: {description: "The reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
- exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
- normalBam: {description: "The normal/control sample's BAM file.", category: "required"}
- normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "required"}
tumorBam: {description: "The tumor/case sample's BAM file.", category: "required"}
tumorBamIndex: {description: "The index for the tumor/case sample's BAM file.", category: "required"}
+ normalBam: {description: "The normal/control sample's BAM file.", category: "required"}
+ normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "required"}
+ inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
+ exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
mutect2VCF: {description: "A VCF as produced by mutect2.", category: "advanced"}
varscanSNV: {description: "An SNV VCF as produced by varscan.", category: "advanced"}
varscanIndel: {description: "An indel VCF as produced by varscan.", category: "advanced"}
@@ -223,25 +225,24 @@ task ParallelPairedTrain {
scalpelVCF: {description: "A VCF as produced by scalpel.", category: "advanced"}
strelkaSNV: {description: "An SNV VCF as produced by strelka.", category: "advanced"}
strelkaIndel: {description: "An indel VCF as produced by somaticsniper.", category: "advanced"}
-
threads: {description: "The number of 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"}
+ 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 ParallelSingle {
input {
- File? classifierSNV
- File? classifierIndel
+ File bam
+ File bamIndex
String outputDir
File referenceFasta
File referenceFastaFai
+
+ File? classifierSNV
+ File? classifierIndel
File? inclusionRegion
File? exclusionRegion
- File bam
- File bamIndex
File? mutect2VCF
File? varscanVCF
File? vardictVCF
@@ -291,40 +292,40 @@ task ParallelSingle {
}
parameter_meta {
- classifierSNV: {description: "A somaticseq SNV classifier.", category: "common"}
- classifierIndel: {description: "A somaticseq Indel classifier.", category: "common"}
+ # inputs
+ bam: {description: "The input BAM file.", category: "required"}
+ bamIndex: {description: "The index for the input BAM file.", category: "required"}
outputDir: {description: "The directory to write the output to.", category: "common"}
referenceFasta: {description: "The reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ classifierSNV: {description: "A somaticseq SNV classifier.", category: "common"}
+ classifierIndel: {description: "A somaticseq Indel classifier.", category: "common"}
inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
- bam: {description: "The input BAM file.", category: "required"}
- bamIndex: {description: "The index for the input BAM file.", category: "required"}
mutect2VCF: {description: "A VCF as produced by mutect2.", category: "advanced"}
varscanVCF: {description: "A VCF as produced by varscan.", category: "advanced"}
vardictVCF: {description: "A VCF as produced by vardict.", category: "advanced"}
lofreqVCF: {description: "A VCF as produced by lofreq.", category: "advanced"}
scalpelVCF: {description: "A VCF as produced by scalpel.", category: "advanced"}
strelkaVCF: {description: "A VCF as produced by strelka.", category: "advanced"}
-
threads: {description: "The number of 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"}
+ 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 ParallelSingleTrain {
input {
+ File bam
+ File bamIndex
File truthSNV
File truthIndel
String outputDir
File referenceFasta
File referenceFastaFai
+
File? inclusionRegion
File? exclusionRegion
- File bam
- File bamIndex
File? mutect2VCF
File? varscanVCF
File? vardictVCF
@@ -373,6 +374,9 @@ task ParallelSingleTrain {
}
parameter_meta {
+ # inputs
+ bam: {description: "The input BAM file.", category: "required"}
+ bamIndex: {description: "The index for the input BAM file.", category: "required"}
truthSNV: {description: "A VCF of true SNVs.", category: "required"}
truthIndel: {description: "A VCF of true indels.", category: "required"}
outputDir: {description: "The directory to write the output to.", category: "common"}
@@ -380,19 +384,15 @@ task ParallelSingleTrain {
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
inclusionRegion: {description: "A bed file describing regions to include.", category: "common"}
exclusionRegion: {description: "A bed file describing regions to exclude.", category: "common"}
- bam: {description: "The input BAM file.", category: "required"}
- bamIndex: {description: "The index for the input BAM file.", category: "required"}
mutect2VCF: {description: "A VCF as produced by mutect2.", category: "advanced"}
varscanVCF: {description: "A VCF as produced by varscan.", category: "advanced"}
vardictVCF: {description: "A VCF as produced by vardict.", category: "advanced"}
lofreqVCF: {description: "A VCF as produced by lofreq.", category: "advanced"}
scalpelVCF: {description: "A VCF as produced by scalpel.", category: "advanced"}
strelkaVCF: {description: "A VCF as produced by strelka.", category: "advanced"}
-
threads: {description: "The number of 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"}
+ 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"}
}
}
@@ -400,17 +400,16 @@ task ModifyStrelka {
input {
File strelkaVCF
String outputVCFName = basename(strelkaVCF, ".gz")
- String dockerImage = "lethalfang/somaticseq:3.1.0"
+
Int timeMinutes = 20
+ String dockerImage = "lethalfang/somaticseq:3.1.0"
}
command {
set -e
-
/opt/somaticseq/vcfModifier/modify_Strelka.py \
-infile ~{strelkaVCF} \
-outfile "modified_strelka.vcf"
-
first_FORMAT_line_num=$(grep -n -m 1 '##FORMAT' "modified_strelka.vcf" | cut -d : -f 1)
sed "$first_FORMAT_line_num"'i##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">' "modified_strelka.vcf" > ~{outputVCFName}
}
@@ -425,10 +424,10 @@ task ModifyStrelka {
}
parameter_meta {
+ # inputs
strelkaVCF: {description: "A vcf file as produced by strelka.", category: "required"}
outputVCFName: {description: "The location the output VCF file should be written to.", 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"}
+ 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/spades.wdl b/spades.wdl
index 204dbfe..7cc16d2 100644
--- a/spades.wdl
+++ b/spades.wdl
@@ -22,10 +22,11 @@ version 1.0
task Spades {
input {
- String outputDir
- String? preCommand
File read1
File? read2
+ String outputDir
+
+ String? preCommand
File? interlacedReads
File? sangerReads
File? pacbioReads
@@ -44,12 +45,13 @@ task Spades {
Boolean? disableGzipOutput
Boolean? disableRepeatResolution
File? dataset
- Int threads = 1
- Int memoryGb = 16
File? tmpDir
String? k
Float? covCutoff
Int? phredOffset
+
+ Int threads = 1
+ Int memoryGb = 16
}
command {
@@ -100,4 +102,4 @@ task Spades {
cpu: threads
memory: "~{memoryGb}G"
}
-}
\ No newline at end of file
+}
diff --git a/star.wdl b/star.wdl
index 3d0e2eb..68193fc 100644
--- a/star.wdl
+++ b/star.wdl
@@ -24,6 +24,7 @@ task GenomeGenerate {
input {
String genomeDir = "STAR_index"
File referenceFasta
+
File? referenceGtf
Int? sjdbOverhang
@@ -61,8 +62,10 @@ task GenomeGenerate {
File? sjdbListFromGtfOut = "~{genomeDir}/sjdbList.fromGTF.out.tab"
File? sjdbListOut = "~{genomeDir}/sjdbList.out.tab"
File? transcriptInfo = "~{genomeDir}/transcriptInfo.tab"
- Array[File] starIndex = select_all([chrLength, chrNameLength, chrName, chrStart, genome, genomeParameters,
- sa, saIndex, exonGeTrInfo, exonInfo, geneInfo, sjdbInfo, sjdbListFromGtfOut,
+ Array[File] starIndex = select_all([chrLength, chrNameLength, chrName,
+ chrStart, genome, genomeParameters,
+ sa, saIndex, exonGeTrInfo, exonInfo,
+ geneInfo, sjdbInfo, sjdbListFromGtfOut,
sjdbListOut, transcriptInfo])
}
@@ -74,16 +77,15 @@ task GenomeGenerate {
}
parameter_meta {
+ # inputs
genomeDir: {description:"The directory the STAR index should be written to.", categroy: "common"}
referenceFasta: {description: "The reference Fasta file.", category: "required"}
referenceGtf: {description: "The reference GTF file.", category: "common"}
sjdbOverhang: {description: "Equivalent to STAR's `--sjdbOverhang` option.", category: "advanced"}
-
threads: {description: "The number of 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"}
+ 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"}
}
}
@@ -95,6 +97,8 @@ task Star {
String outFileNamePrefix
String outSAMtype = "BAM SortedByCoordinate"
String readFilesCommand = "zcat"
+ Int outBAMcompression = 1
+
Int? outFilterScoreMin
Float? outFilterScoreMinOverLread
Int? outFilterMatchNmin
@@ -103,7 +107,6 @@ task Star {
String? twopassMode = "Basic"
Array[String]? outSAMattrRGline
String? outSAMunmapped = "Within KeepPairs"
- Int outBAMcompression = 1
Int? limitBAMsortRAM
Int runThreadN = 4
@@ -119,7 +122,7 @@ task Star {
# So we solve it with an optional memory string and using select_first
# in the runtime section.
- #TODO Could be extended for all possible output extensions
+ #TODO: Could be extended for all possible output extensions.
Map[String, String] samOutputNames = {"BAM SortedByCoordinate": "sortedByCoord.out.bam"}
command {
@@ -157,12 +160,14 @@ task Star {
}
parameter_meta {
+ # inputs
inputR1: {description: "The first-/single-end FastQ files.", category: "required"}
inputR2: {description: "The second-end FastQ files (in the same order as the first-end files).", category: "common"}
indexFiles: {description: "The star index files.", category: "required"}
outFileNamePrefix: {description: "The prefix for the output files. May include directories.", category: "required"}
outSAMtype: {description: "The type of alignment file to be produced. Currently only `BAM SortedByCoordinate` is supported.", category: "advanced"}
readFilesCommand: {description: "Equivalent to star's `--readFilesCommand` option.", category: "advanced"}
+ outBAMcompression: {description: "The compression level of the output BAM.", category: "advanced"}
outFilterScoreMin: {description: "Equivalent to star's `--outFilterScoreMin` option.", category: "advanced"}
outFilterScoreMinOverLread: {description: "Equivalent to star's `--outFilterScoreMinOverLread` option.", category: "advanced"}
outFilterMatchNmin: {description: "Equivalent to star's `--outFilterMatchNmin` option.", category: "advanced"}
@@ -174,7 +179,6 @@ task Star {
limitBAMsortRAM: {description: "Equivalent to star's `--limitBAMsortRAM` option.", category: "advanced"}
runThreadN: {description: "The number of threads to use.", category: "advanced"}
memory: {description: "The amount of memory this job will use.", category: "advanced"}
- outBAMcompression: {description: "The compression level of the output BAM.", 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/strelka.wdl b/strelka.wdl
index 50c38b5..f4b9888 100644
--- a/strelka.wdl
+++ b/strelka.wdl
@@ -29,11 +29,12 @@ task Germline {
Array[File]+ indexes
File referenceFasta
File referenceFastaFai
- File? callRegions
- File? callRegionsIndex
Boolean exome = false
Boolean rna = false
+ File? callRegions
+ File? callRegionsIndex
+
Int cores = 1
Int memoryGb = 4
Int timeMinutes = 90
@@ -61,28 +62,27 @@ task Germline {
}
runtime {
- docker: dockerImage
cpu: cores
- time_minutes: timeMinutes
memory: "~{memoryGb}G"
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
+ # inputs
runDir: {description: "The directory to use as run/output directory.", category: "common"}
bams: {description: "The input BAM files.", category: "required"}
indexes: {description: "The indexes for the input BAM files.", category: "required"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
- callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
rna: {description: "Whether or not the data is from RNA sequencing.", category: "common"}
-
+ callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
+ callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
cores: {description: "The number of cores to use.", category: "advanced"}
memoryGb: {description: "The amount of memory this job will use in Gigabytes.", 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"}
+ 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"}
}
}
@@ -95,11 +95,12 @@ task Somatic {
File tumorBamIndex
File referenceFasta
File referenceFastaFai
+ Boolean exome = false
+
File? callRegions
File? callRegionsIndex
File? indelCandidatesVcf
File? indelCandidatesVcfIndex
- Boolean exome = false
Int cores = 1
Int memoryGb = 4
@@ -133,13 +134,14 @@ task Somatic {
}
runtime {
- docker: dockerImage
cpu: cores
- time_minutes: timeMinutes
memory: "~{memoryGb}G"
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
+ # inputs
runDir: {description: "The directory to use as run/output directory.", category: "common"}
normalBam: {description: "The normal/control sample's BAM file.", category: "required"}
normalBamIndex: {description: "The index for the normal/control sample's BAM file.", category: "required"}
@@ -147,17 +149,15 @@ task Somatic {
tumorBamIndex: {description: "The index for the tumor/case sample's BAM file.", category: "required"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+ exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
indelCandidatesVcf: {description: "An indel candidates VCF file from manta.", category: "advanced"}
indelCandidatesVcfIndex: {description: "The index for the indel candidates VCF file.", category: "advanced"}
- exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
-
cores: {description: "The number of cores to use.", category: "advanced"}
memoryGb: {description: "The amount of memory this job will use in Gigabytes.", 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"}
+ 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"}
}
meta {
@@ -165,4 +165,4 @@ task Somatic {
exclude: ["doNotDefineThis"]
}
}
-}
\ No newline at end of file
+}
diff --git a/stringtie.wdl b/stringtie.wdl
index 5ed62de..fff4140 100644
--- a/stringtie.wdl
+++ b/stringtie.wdl
@@ -24,9 +24,10 @@ task Stringtie {
input {
File bam
File bamIndex
- File? referenceGtf
Boolean skipNovelTranscripts = false
String assembledTranscriptsFile
+
+ File? referenceGtf
Boolean? firstStranded
Boolean? secondStranded
String? geneAbundanceFile
@@ -64,19 +65,19 @@ task Stringtie {
}
parameter_meta {
+ # inputs
bam: {description: "The input BAM file.", category: "required"}
bamIndex: {description: "The input BAM file's index.", category: "required"}
- referenceGtf: {description: "A reference GTF file to be used as guide.", category: "common"}
skipNovelTranscripts: {description: "Whether new transcripts should be assembled or not.", category: "common"}
assembledTranscriptsFile: {description: "Where the output of the assembly should be written.", category: "required"}
+ referenceGtf: {description: "A reference GTF file to be used as guide.", category: "common"}
firstStranded: {description: "Equivalent to the --rf flag of stringtie.", category: "required"}
secondStranded: {description: "Equivalent to the --fr flag of stringtie.", category: "required"}
geneAbundanceFile: {description: "Where the abundance file should be written.", category: "common"}
threads: {description: "The number of threads to use.", category: "advanced"}
memory: {description: "The amount of memory needed for this task in GB.", 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"}
+ 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"}
}
}
@@ -84,13 +85,14 @@ task Merge {
input {
Array[File]+ gtfFiles
String outputGtfPath
+ Boolean keepMergedTranscriptsWithRetainedIntrons = false
+
File? guideGtf
Int? minimumLength
Float? minimumCoverage
Float? minimumFPKM
Float? minimumTPM
Float? minimumIsoformFraction
- Boolean keepMergedTranscriptsWithRetainedIntrons = false
String? label
String memory = "10G"
@@ -125,19 +127,19 @@ task Merge {
}
parameter_meta {
+ # inputs
gtfFiles: {description: "The GTF files produced by stringtie.", category: "required"}
outputGtfPath: {description: "Where the output should be written.", category: "required"}
+ keepMergedTranscriptsWithRetainedIntrons: {description: "Equivalent to the -i flag of 'stringtie --merge'.", category: "advanced"}
guideGtf: {description: "Equivalent to the -G option of 'stringtie --merge'.", category: "advanced"}
minimumLength: {description: "Equivalent to the -m option of 'stringtie --merge'.", category: "advanced"}
minimumCoverage: {description: "Equivalent to the -c option of 'stringtie --merge'.", category: "advanced"}
minimumFPKM: {description: "Equivalent to the -F option of 'stringtie --merge'.", category: "advanced"}
minimumTPM: {description: "Equivalent to the -T option of 'stringtie --merge'.", category: "advanced"}
minimumIsoformFraction: {description: "Equivalent to the -f option of 'stringtie --merge'.", category: "advanced"}
- keepMergedTranscriptsWithRetainedIntrons: {description: "Equivalent to the -i flag of 'stringtie --merge'.", category: "advanced"}
label: {description: "Equivalent to the -l option of 'stringtie --merge'.", category: "advanced"}
memory: {description: "The amount of memory needed for this task in GB.", 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"}
+ 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/survivor.wdl b/survivor.wdl
index b958300..c7b3105 100644
--- a/survivor.wdl
+++ b/survivor.wdl
@@ -1,7 +1,5 @@
version 1.0
-# MIT License
-#
# Copyright (c) 2018 Leiden University Medical Center
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
@@ -32,6 +30,7 @@ task Merge {
Boolean distanceBySvSize = false
Int minSize = 30
String outputPath = "./survivor/merged.vcf"
+
String memory = "24G"
Int timeMinutes = 60
String dockerImage = "quay.io/biocontainers/survivor:1.0.6--h6bb024c_0"
@@ -64,15 +63,15 @@ task Merge {
parameter_meta {
# inputs
- filePaths: {description: "An array of VCF files (predictions) to be merged by SURVIVOR", category: "required"}
- breakpointDistance: {description: "The distance between pairwise breakpoints between SVs", category: "advanced"}
- suppVecs: {description: "The minimum number of SV callers to support the merging", category: "advanced"}
- svType: {description: "A boolean to include the type SV to be merged", category: "advanced"}
- strandType: {description: "A boolean to include strand type of an SV to be merged", category: "advanced"}
- distanceBySvSize: {description: "A boolean to predict the pairwise distance between the SVs based on their size", category: "advanced"}
- minSize: {description: "The mimimum size of SV to be merged", category: "advanced"}
+ filePaths: {description: "An array of VCF files (predictions) to be merged by SURVIVOR.", category: "required"}
+ breakpointDistance: {description: "The distance between pairwise breakpoints between SVs.", category: "advanced"}
+ suppVecs: {description: "The minimum number of SV callers to support the merging.", category: "advanced"}
+ svType: {description: "A boolean to include the type SV to be merged.", category: "advanced"}
+ strandType: {description: "A boolean to include strand type of an SV to be merged.", category: "advanced"}
+ distanceBySvSize: {description: "A boolean to predict the pairwise distance between the SVs based on their size.", category: "advanced"}
+ minSize: {description: "The mimimum size of SV to be merged.", category: "advanced"}
outputPath: {description: "The location the output VCF file should be written.", category: "common"}
- memory: {description: "The memory required to run the programs", category: "advanced"}
+ memory: {description: "The memory required to run the programs.", 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/talon.wdl b/talon.wdl
index c11ab9e..61f5eb4 100644
--- a/talon.wdl
+++ b/talon.wdl
@@ -1,6 +1,6 @@
version 1.0
-# Copyright (c) 2019 Sequencing Analysis Support Core - Leiden University Medical Center
+# Copyright (c) 2019 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
@@ -8,10 +8,10 @@ version 1.0
# 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 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
diff --git a/transcriptclean.wdl b/transcriptclean.wdl
index 7966130..efdd95f 100644
--- a/transcriptclean.wdl
+++ b/transcriptclean.wdl
@@ -1,6 +1,6 @@
version 1.0
-# Copyright (c) 2019 Sequencing Analysis Support Core - Leiden University Medical Center
+# Copyright (c) 2019 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
@@ -8,10 +8,10 @@ version 1.0
# 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 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
@@ -54,10 +54,10 @@ task GetSJsFromGtf {
parameter_meta {
# inputs
- gtfFile: {description: "Input gtf file", category: "required"}
- genomeFile: {description: "Reference genome", category: "required"}
- minIntronSize: {description: "Minimum size of intron to consider a junction.", category: "advanced"}
+ gtfFile: {description: "Input gtf file.", category: "required"}
+ genomeFile: {description: "Reference genome.", category: "required"}
outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
+ minIntronSize: {description: "Minimum size of intron to consider a junction.", 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"}
@@ -97,7 +97,7 @@ task GetTranscriptCleanStats {
parameter_meta {
# inputs
- inputSam: {description: "Output sam file from transcriptclean", category: "required"}
+ inputSam: {description: "Output sam file from transcriptclean.", category: "required"}
outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
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"}
@@ -189,8 +189,7 @@ task TranscriptClean {
cores: {description: "The number of cores to be used.", 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"}
+ 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
fastaFile: {description: "Fasta file containing corrected reads."}
diff --git a/umi-tools.wdl b/umi-tools.wdl
index c5f3b14..7b0a399 100644
--- a/umi-tools.wdl
+++ b/umi-tools.wdl
@@ -1,6 +1,6 @@
version 1.0
-# Copyright (c) 2017 Sequencing Analysis Support Core - Leiden University Medical Center
+# Copyright (c) 2017 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
@@ -8,10 +8,10 @@ version 1.0
# 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 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
@@ -26,9 +26,10 @@ task Extract {
File? read2
String bcPattern
String? bcPattern2
- Boolean threePrime = false
String read1Output = "umi_extracted_R1.fastq.gz"
String? read2Output = "umi_extracted_R2.fastq.gz"
+ Boolean threePrime = false
+
Int timeMinutes = 1 + ceil(size([read1, read2], "G") * 2)
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:6089936aca6219b5bb5f54210ac5eb456c7503f2-0"
}
@@ -50,21 +51,21 @@ task Extract {
}
runtime {
- docker: dockerImage
time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
+ # inputs
read1: {description: "The first/single-end fastq file.", category: "required"}
read2: {description: "The second-end fastq file.", category: "common"}
bcPattern: {description: "The pattern to be used for UMI extraction. See the umi_tools docs for more information.", category: "required"}
bcPattern2: {description: "The pattern to be used for UMI extraction in the second-end reads. See the umi_tools docs for more information.", category: "advanced"}
- threePrime: {description: "Whether or not the UMI's are at the reads' 3' end. If false the UMIs are extracted from the 5' end.", category: "advanced"}
read1Output: {description: "The location to write the first/single-end output fastq file to.", category: "advanced"}
read2Output: {description: "The location to write the second-end output fastq file to.", category: "advanced"}
+ threePrime: {description: "Whether or not the UMI's are at the reads' 3' end. If false the UMIs are extracted from the 5' end.", 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"}
+ 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"}
}
}
@@ -72,15 +73,15 @@ task Dedup {
input {
File inputBam
File inputBamIndex
- String? umiSeparator
String outputBamPath
- String? statsPrefix
Boolean paired = true
+ String? umiSeparator
+ String? statsPrefix
+
String memory = "25G"
Int timeMinutes = 30 + ceil(size(inputBam, "G") * 30)
-
- # Use a multi-package-container which includes umi_tools (0.5.5) and samtools (1.9)
+ # Use a multi-package-container which includes umi_tools (0.5.5) and samtools (1.9).
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:6089936aca6219b5bb5f54210ac5eb456c7503f2-0"
}
@@ -107,21 +108,21 @@ task Dedup {
}
runtime {
- docker: dockerImage
- time_minutes: timeMinutes
memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
+ # inputs
inputBam: {description: "The input BAM file.", categrory: "required"}
inputBamIndex: {description: "The index for the ipnut BAM file.", cateogry: "required"}
outputBamPath: {description: "The location to write the output BAM file to.", category: "required"}
- statsPrefix: {description: "The prefix for the stats files.", category: "advanced"}
- umiSeparator: {description: "Seperator used for UMIs in the read names.", category: "advanced"}
paired: {description: "Whether or not the data is paired.", category: "common"}
+ umiSeparator: {description: "Seperator used for UMIs in the read names.", category: "advanced"}
+ statsPrefix: {description: "The prefix for the stats files.", category: "advanced"}
memory: {description: "The amount of memory required for the task.", 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"}
+ 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/unicycler.wdl b/unicycler.wdl
index fc39360..938d0c7 100644
--- a/unicycler.wdl
+++ b/unicycler.wdl
@@ -22,12 +22,13 @@ version 1.0
task Unicycler {
input {
+ String out
+
String? preCommand
File? short1
File? short2
File? unpaired
File? long
- String out
Int? verbosity
Int? minFastaLength
Int? keep
@@ -125,4 +126,4 @@ task Unicycler {
cpu: threads
memory: memory
}
-}
\ No newline at end of file
+}
diff --git a/vardict.wdl b/vardict.wdl
index 92beb32..fc37c9e 100644
--- a/vardict.wdl
+++ b/vardict.wdl
@@ -27,29 +27,28 @@ task VarDict {
String tumorSampleName
File tumorBam
File tumorBamIndex
- String? normalSampleName
- File? normalBam
- File? normalBamIndex
File referenceFasta
File referenceFastaFai
File bedFile
String outputVcf
-
- Int chromosomeColumn = 1
- Int startColumn = 2
- Int endColumn = 3
- Int geneColumn = 4
-
Boolean outputCandidateSomaticOnly = true
Boolean outputAllVariantsAtSamePosition = true
Float mappingQuality = 20
Int minimumTotalDepth = 8
Int minimumVariantDepth = 4
Float minimumAlleleFrequency = 0.02
+ Int chromosomeColumn = 1
+ Int startColumn = 2
+ Int endColumn = 3
+ Int geneColumn = 4
+
+ String? normalSampleName
+ File? normalBam
+ File? normalBamIndex
+ String javaXmx = "16G"
Int threads = 1
String memory = "18G"
- String javaXmx = "16G"
Int timeMinutes = 300
String dockerImage = "quay.io/biocontainers/vardict-java:1.5.8--1"
}
@@ -93,33 +92,31 @@ task VarDict {
}
parameter_meta {
+ # inputs
tumorSampleName: {description: "The name of the tumor/case sample.", category: "required"}
tumorBam: {description: "The tumor/case sample's BAM file.", category: "required"}
tumorBamIndex: {description: "The index for the tumor/case sample's BAM file.", category: "required"}
- normalSampleName: {description: "The name of the normal/control sample.", category: "common"}
- normalBam: {description: "The normal/control sample's BAM file.", category: "common"}
- normalBamIndex: {description: "The normal/control sample's BAM file.", category: "common"}
referenceFasta: {description: "The reference fasta file.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
bedFile: {description: "A bed file describing the regions to operate on. These regions must be below 1e6 bases in size.", category: "required"}
outputVcf: {description: "The location to write the output VCF file to.", category: "required"}
- chromosomeColumn: {description: "Equivalent to vardict-java's `-c` option.", category: "advanced"}
- startColumn: {description: "Equivalent to vardict-java's `-S` option.", category: "advanced"}
- endColumn: {description: "Equivalent to vardict-java's `-E` option.", category: "advanced"}
- geneColumn: {description: "Equivalent to vardict-java's `-g` option.", category: "advanced"}
outputCandidateSomaticOnly: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-M` flag.", category: "advanced"}
outputAllVariantsAtSamePosition: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-A` flag.", category: "advanced"}
mappingQuality: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-Q` option.", category: "advanced"}
minimumTotalDepth: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-d` option.", category: "advanced"}
minimumVariantDepth: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-v` option.", category: "advanced"}
minimumAlleleFrequency: {description: "Equivalent to var2vcf_paired.pl or var2vcf_valid.pl's `-f` option.", category: "advanced"}
-
+ chromosomeColumn: {description: "Equivalent to vardict-java's `-c` option.", category: "advanced"}
+ startColumn: {description: "Equivalent to vardict-java's `-S` option.", category: "advanced"}
+ endColumn: {description: "Equivalent to vardict-java's `-E` option.", category: "advanced"}
+ geneColumn: {description: "Equivalent to vardict-java's `-g` option.", category: "advanced"}
+ normalSampleName: {description: "The name of the normal/control sample.", category: "common"}
+ normalBam: {description: "The normal/control sample's BAM file.", category: "common"}
+ normalBamIndex: {description: "The normal/control sample's BAM file.", category: "common"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.", category: "advanced"}
threads: {description: "The number of threads to 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"}
+ 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/vt.wdl b/vt.wdl
index 99cc131..95585ff 100644
--- a/vt.wdl
+++ b/vt.wdl
@@ -1,6 +1,6 @@
version 1.0
-# Copyright (c) 2020 Sequencing Analysis Support Core - 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
@@ -8,10 +8,10 @@ version 1.0
# 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 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
@@ -28,9 +28,10 @@ task Normalize {
File referenceFastaFai
Boolean ignoreMaskedRef = false
String outputPath = "./vt/normalized_decomposed.vcf"
- String dockerImage = "quay.io/biocontainers/vt:0.57721--hdf88d34_2"
+
String memory = "4G"
Int timeMinutes = 30
+ String dockerImage = "quay.io/biocontainers/vt:0.57721--hdf88d34_2"
}
command {
@@ -56,13 +57,12 @@ task Normalize {
# inputs
inputVCF: {description: "The VCF file to process.", category: "required"}
inputVCFIndex: {description: "The index of the VCF file to be processed.", category: "required"}
- outputPath: {description: "The location the output VCF file should be written.", category: "common"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
- ignoreMaskedRef: {description: "Warns but does not exit when REF is inconsistent with masked reference sequence for non SNPs", category: "advanced"}
- memory: {description: "The memory required to run the programs", category: "advanced"}
+ ignoreMaskedRef: {description: "Warns but does not exit when REF is inconsistent with masked reference sequence for non SNPs.", category: "advanced"}
+ outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+ memory: {description: "The memory required to run the programs.", 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/whatshap.wdl b/whatshap.wdl
index 9362459..5c69400 100644
--- a/whatshap.wdl
+++ b/whatshap.wdl
@@ -20,10 +20,14 @@ version 1.0
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
-
task Phase {
input {
String outputVCF
+ File vcf
+ File vcfIndex
+ File phaseInput
+ File phaseInputIndex
+
File? reference
File? referenceIndex
String? tag
@@ -33,20 +37,15 @@ task Phase {
String? chromosome
String? threshold
String? ped
- File vcf
- File vcfIndex
- File phaseInput
- File phaseInputIndex
String memory = "4G"
Int timeMinutes = 120
- # Whatshap 1.0, tabix 0.2.5
+ # Whatshap 1.0, tabix 0.2.5.
String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
}
command {
set -e
-
whatshap phase \
~{vcf} \
~{phaseInput} \
@@ -69,24 +68,27 @@ task Phase {
}
runtime {
- docker: dockerImage
- time_minutes: timeMinutes
memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
+ # inputs
outputVCF: {description: "Output VCF file. Add .gz to the file name to get compressed output. If omitted, use standard output.", category: "common"}
- reference: {description: "Reference file. Provide this to detect alleles through re-alignment. If no index (.fai) exists, it will be created", category: "common"}
- tag: {description: "Store phasing information with PS tag (standardized) or HP tag (used by GATK ReadBackedPhasing) (default: {description: PS)", category: "common"}
- algorithm: {description: "Phasing algorithm to use (default: {description: whatshap)", category: "advanced"}
- indels: {description: "Also phase indels (default: {description: do not phase indels)", category: "common"}
+ vcf: {description: "VCF or BCF file with variants to be phased (can be gzip-compressed).", category: "required"}
+ vcfIndex: {description: "Index for the VCF or BCF file with variants to be phased.", category: "required"}
+ phaseInput: {description: "BAM, CRAM, VCF or BCF file(s) with phase information, either through sequencing reads (BAM, CRAM) or through phased blocks (VCF, BCF).", category: "required"}
+ phaseInputIndex: {description: "Index of BAM, CRAM, VCF or BCF file(s) with phase information.", category: "required"}
+ reference: {description: "Reference file. Provide this to detect alleles through re-alignment. If no index (.fai) exists, it will be created.", category: "common"}
+ referenceIndex: {description: "Index of reference file.", category: "common"}
+ tag: {description: "Store phasing information with PS tag (standardized) or HP tag (used by GATK ReadBackedPhasing) (default: {description: PS).", category: "common"}
+ algorithm: {description: "Phasing algorithm to use (default: {description: whatshap).", category: "advanced"}
+ indels: {description: "Also phase indels (default: {description: do not phase indels).", category: "common"}
sample: {description: "Name of a sample to phase. If not given, all samples in the input VCF are phased. Can be used multiple times.", category: "common"}
chromosome: {description: "Name of chromosome to phase. If not given, all chromosomes in the input VCF are phased. Can be used multiple times.", category: "common"}
threshold: {description: "The threshold of the ratio between the probabilities that a pair of reads come from the same haplotype and different haplotypes in the read merging model (default: {description: 1000000).", category: "advanced"}
ped: {description: "Use pedigree information in PED file to improve phasing (switches to PedMEC algorithm). Columns 2, 3, 4 must refer to child, mother, and father sample names as used in the VCF and BAM/CRAM. Other columns are ignored.", category: "advanced"}
- vcf: {description: "VCF or BCF file with variants to be phased (can be gzip-compressed)", category: "required"}
- vcfIndex: {description: "Index for the VCF or BCF file with variants to be phased", category: "required"}
- phaseInput: {description: "BAM, CRAM, VCF or BCF file(s) with phase information, either through sequencing reads (BAM, CRAM) or through phased blocks (VCF, BCF)", 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"}
@@ -95,16 +97,17 @@ task Phase {
task Stats {
input {
+ File vcf
+
String? gtf
String? sample
String? tsv
String? blockList
String? chromosome
- File vcf
String memory = "4G"
Int timeMinutes = 120
- # Whatshap 1.0, tabix 0.2.5
+ # Whatshap 1.0, tabix 0.2.5.
String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
}
@@ -125,18 +128,19 @@ task Stats {
}
runtime {
- docker: dockerImage
- time_minutes: timeMinutes
memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
- gtf: "Write phased blocks to GTF file."
- sample: "Name of the sample to process. If not given, use first sample found in VCF."
- tsv: "Filename to write statistics to (tab-separated)."
- blockList: "Filename to write list of all blocks to (one block per line)."
- chromosome: "Name of chromosome to process. If not given, all chromosomes in the input VCF are considered."
- vcf: "Phased VCF file"
+ # inputs
+ vcf: {description: "Phased VCF file.", category: "required"}
+ gtf: {description: "Write phased blocks to GTF file.", category: "common"}
+ sample: {description: "Name of the sample to process. If not given, use first sample found in VCF.", category: "common"}
+ tsv: {description: "Filename to write statistics to (tab-separated).", category: "common"}
+ blockList: {description: "Filename to write list of all blocks to (one block per line).", category: "advanced"}
+ chromosome: {description: "Name of chromosome to process. If not given, all chromosomes in the input VCF are considered.", 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"}
@@ -145,57 +149,58 @@ task Stats {
task Haplotag {
input {
+ File vcf
+ File vcfIndex
+ File alignments
+ File alignmentsIndex
String outputFile
+
File? reference
File? referenceFastaIndex
String? regions
String? sample
- File vcf
- File vcfIndex
- File alignments
- File alignmentsIndex
String memory = "4G"
Int timeMinutes = 120
- # Whatshap 1.0, tabix 0.2.5
+ # Whatshap 1.0, tabix 0.2.5.
String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
}
command {
set -e
-
whatshap haplotag \
- ~{vcf} \
- ~{alignments} \
- ~{if defined(outputFile) then ("--output " + '"' + outputFile+ '"') else ""} \
- ~{if defined(reference) then ("--reference " + '"' + reference + '"') else ""} \
- ~{if defined(regions) then ("--regions " + '"' + regions + '"') else ""} \
- ~{if defined(sample) then ("--sample " + '"' + sample + '"') else ""}
-
- python3 -c "import pysam; pysam.index('~{outputFile}')"
+ ~{vcf} \
+ ~{alignments} \
+ ~{if defined(outputFile) then ("--output " + '"' + outputFile+ '"') else ""} \
+ ~{if defined(reference) then ("--reference " + '"' + reference + '"') else ""} \
+ ~{if defined(regions) then ("--regions " + '"' + regions + '"') else ""} \
+ ~{if defined(sample) then ("--sample " + '"' + sample + '"') else ""}
+
+ python3 -c "import pysam; pysam.index('~{outputFile}')"
}
output {
- File bam = outputFile
- File bamIndex = outputFile + ".bai"
+ File bam = outputFile
+ File bamIndex = outputFile + ".bai"
}
runtime {
- docker: dockerImage
- time_minutes: timeMinutes
memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
}
parameter_meta {
- outputFile: "Output file. If omitted, use standard output."
- reference: "Reference file. Provide this to detect alleles through re-alignment. If no index (.fai) exists, it will be created."
- referenceFastaIndex: "Index for the reference file."
- regions: "Specify region(s) of interest to limit the tagging to reads/variants overlapping those regions. You can specify a space-separated list of regions in the form of chrom:start-end, chrom (consider entire chromosome), or chrom:start (consider region from this start to end of chromosome)."
- sample: "Name of a sample to phase. If not given, all samples in the input VCF are phased. Can be used multiple times."
- vcf: "VCF file with phased variants (must be gzip-compressed and indexed)."
- vcfIndex: "Index for the VCF or BCF file with variants to be phased."
- alignments: "File (BAM/CRAM) with read alignments to be tagged by haplotype."
- alignmentsIndex: "Index for the alignment file."
+ # inputs
+ vcf: {description: "VCF file with phased variants (must be gzip-compressed and indexed).", category: "required"}
+ vcfIndex: {description: "Index for the VCF or BCF file with variants to be phased.", category: "required"}
+ alignments: {description: "File (BAM/CRAM) with read alignments to be tagged by haplotype.", category: "required"}
+ alignmentsIndex: {description: "Index for the alignment file.", category: "required"}
+ outputFile: {description: "Output file. If omitted, use standard output.", category: "required"}
+ reference: {description: "Reference file. Provide this to detect alleles through re-alignment. If no index (.fai) exists, it will be created.", category: "common"}
+ referenceFastaIndex: {description: "Index for the reference file.", category: "common"}
+ regions: {description: "Specify region(s) of interest to limit the tagging to reads/variants overlapping those regions. You can specify a space-separated list of regions in the form of chrom:start-end, chrom (consider entire chromosome), or chrom:start (consider region from this start to end of chromosome).", category: "advanced"}
+ sample: {description: "Name of a sample to phase. If not given, all samples in the input VCF are phased. Can be used multiple times.", 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"}
diff --git a/wisestork.wdl b/wisestork.wdl
index 0fd812b..6be3216 100644
--- a/wisestork.wdl
+++ b/wisestork.wdl
@@ -22,13 +22,15 @@ version 1.0
task Count {
input {
- Int? binSize
- File reference
- File referenceIndex
- File? binFile
File inputBam
File inputBamIndex
+ File reference
+ File referenceIndex
String outputBed = "output.bed"
+
+ Int? binSize
+ File? binFile
+
String dockerImage = "quay.io/biocontainers/wisestork:0.1.2--pyh24bf2e0_0"
}
@@ -54,15 +56,17 @@ task Count {
task GcCorrect {
input {
- Int? binSize
File reference
File referenceIndex
- File? binFile
File inputBed
String outputBed = "output.bed"
+
+ Int? binSize
+ File? binFile
Float? fracN
Int? iter
Float? fracLowess
+
String dockerImage = "quay.io/biocontainers/wisestork:0.1.2--pyh24bf2e0_0"
}
@@ -91,13 +95,16 @@ task GcCorrect {
task Newref {
input {
- Int? binSize
File reference
File referenceIndex
- File? binFile
Array[File]+ inputBeds
String outputBed = "output.bed"
+
+ Int? binSize
+ File? binFile
Int? nBins
+
+ Int memory = 2 + ceil(length(inputBeds) * 0.15)
String dockerImage = "quay.io/biocontainers/wisestork:0.1.2--pyh24bf2e0_0"
}
@@ -106,36 +113,36 @@ task Newref {
mkdir -p $(dirname ~{outputBed})
wisestork newref \
~{"--binsize " + binSize} \
- --reference ~{reference} \
- ~{"--bin-file " + binFile} \
- --output ~{outputBed} \
- -I ~{sep=" -I " inputBeds} \
- ~{"--n-bins " + nBins}
+ --reference ~{reference} \
+ ~{"--bin-file " + binFile} \
+ --output ~{outputBed} \
+ -I ~{sep=" -I " inputBeds} \
+ ~{"--n-bins " + nBins}
}
output {
File bedFile = outputBed
}
- Int memory = 2 + ceil(length(inputBeds) * 0.15)
-
runtime {
- docker: dockerImage
memory: "~{memory}G"
+ docker: dockerImage
}
}
task Zscore {
input {
- Int? binSize
File reference
File referenceIndex
- File? binFile
File inputBed
File inputBedIndex
File dictionaryFile
File dictionaryFileIndex
String outputBed = "output.bed"
+
+ Int? binSize
+ File? binFile
+
String dockerImage = "quay.io/biocontainers/wisestork:0.1.2--pyh24bf2e0_0"
}
@@ -159,4 +166,3 @@ task Zscore {
docker: dockerImage
}
}
-
--
GitLab