diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9646b5f037e85740143c84c0c6d577497cba4a11..b27addabdd83bfa695a7ebb0cd86da70dc175519 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,11 @@ that users understand how the changes affect the new version.
version 5.0.0-dev
---------------------------
++ deepvariant: Add task for DeepVariant.
++ gatk: Make intervals optional for GenotypeGVCFs.
++ isoseq3: Add required bam index input to isoseq3.
++ pbbam: Add task for indexing PacBio bam files.
++ picard: Add CollectHsMetrics and CollectVariantCallingMetrics.
+ Samtools: Add `threads` to parameter meta for Merge task.
+ bcftools: add tmpDir input to specify temporary directory when sorting.
+ bcftools: remove outputType and implement indexing based on output file extension.
diff --git a/bam2fastx.wdl b/bam2fastx.wdl
index 42240cd4da789985ca1d84ec86973f833f15672b..18434755f251ee91df8a10e36eac3990fbd51217 100644
--- a/bam2fastx.wdl
+++ b/bam2fastx.wdl
@@ -91,12 +91,25 @@ task Bam2Fastq {
command {
set -e
mkdir -p "$(dirname ~{outputPrefix})"
+
+ # Localise the bam and pbi files so they are next to each other in the
+ # current folder
+ bamfiles=""
+ for bamfile in ~{sep=" " bam};do
+ ln $bamfile .
+ bamfiles=$bamfiles" $(basename $bamfile)"
+ done
+
+ for bamindex in ~{sep=" " bamIndex}; do
+ ln $bamindex .
+ done
+
bam2fastq \
--output ~{outputPrefix} \
-c ~{compressionLevel} \
~{true="--split-barcodes" false="" splitByBarcode} \
~{"--seqid-prefix " + seqIdPrefix} \
- ~{sep=" " bam}
+ $bamfiles
}
output {
diff --git a/chunked-scatter.wdl b/chunked-scatter.wdl
index b54a7d2e909a20d43bbe194d9f28496b7753ce5d..115c5ca4eb8fb8407ef0f2d7c36c61c39c669d11 100644
--- a/chunked-scatter.wdl
+++ b/chunked-scatter.wdl
@@ -24,6 +24,7 @@ task ChunkedScatter {
input {
File inputFile
String prefix = "./scatter"
+ Boolean splitContigs = false
Int? chunkSize
Int? overlap
Int? minimumBasesPerFile
@@ -40,6 +41,7 @@ task ChunkedScatter {
~{"-c " + chunkSize} \
~{"-o " + overlap} \
~{"-m " + minimumBasesPerFile} \
+ ~{true="--split-contigs " false="" splitContigs} \
~{inputFile}
}
diff --git a/deepvariant.wdl b/deepvariant.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..88bdb35267732aaf096eb883539394bcf6fbb345
--- /dev/null
+++ b/deepvariant.wdl
@@ -0,0 +1,91 @@
+version 1.0
+
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task RunDeepVariant {
+ input {
+ File referenceFasta
+ File referenceFastaIndex
+ File inputBam
+ File inputBamIndex
+ String modelType
+ String outputVcf
+ File? customizedModel
+ Int? numShards
+ String? outputGVcf
+ File? regions
+ String? sampleName
+ Boolean? VCFStatsReport = true
+
+ String memory = "3G"
+ Int timeMinutes = 5000
+ String dockerImage = "google/deepvariant:1.0.0"
+ }
+
+ command {
+ set -e
+
+ /opt/deepvariant/bin/run_deepvariant \
+ --ref ~{referenceFasta} \
+ --reads ~{inputBam} \
+ --model_type ~{modelType} \
+ --output_vcf ~{outputVcf} \
+ ~{"--output_gvcf " + outputGVcf} \
+ ~{"--customized_model " + customizedModel} \
+ ~{"--num_shards " + numShards} \
+ ~{"--regions} " + regions} \
+ ~{"--sample_name " + sampleName} \
+ ~{true="--vcf_stats_report" false="--novcf_stats_report" VCFStatsReport}
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ output {
+ File outputVCF = outputVcf
+ File outputVCFIndex = outputVCF + ".tbi"
+ File? outputGVCF = outputGVcf
+ File? outputGVCFIndex = outputGVcf + ".tbi"
+ Array[File] outputVCFStatsReport = glob("*.visual_report.html")
+ }
+
+ parameter_meta {
+ referenceFasta: {description: "Genome reference to use", category: "required"}
+ referenceFastaIndex: {description: "Index for the genome reference file.", category: "required"}
+ inputBam: {description: "Aligned, sorted, indexed BAM file containing the reads we want to call.", category: "required"}
+ inputBamIndex: {description: "Index for the input bam file.", category: "required"}
+ modelType: {description: "<WGS|WES|PACBIO>. Type of model to use for variant calling. Each model_type has an associated default model, which can be overridden by the --customized_model flag", category: "required"}
+ outputVcf: {description: "Path where we should write VCF file.", category: "required"}
+ customizedModel: {description: "A path to a model checkpoint to load for the `call_variants` step. If not set, the default for each --model_type will be used", category: "advanced"}
+ numShards: {description: "Number of shards for make_examples step.", category: "common"}
+ outputGVcf: {description: "Path where we should write gVCF file.", category: "common"}
+ regions: {description: "List of regions we want to process, in BED/BEDPE format.", category: "advanced"}
+ sampleName: {description: "Sample name to use instead of the sample name from the input reads BAM (SM tag in the header).", category: "common"}
+ VCFStatsReport: {description: "Output a visual report (HTML) of statistics about the output VCF.", 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/gatk.wdl b/gatk.wdl
index e0209a0c4ef0f4b19fde26f3b47f0d0bd2b33fe0..12416dda147265aff574110d075f34f2897fdae7 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -820,7 +820,7 @@ task GenotypeGVCFs {
input {
File gvcfFile
File gvcfFileIndex
- Array[File]+ intervals
+ Array[File]? intervals
String outputPath
File referenceFasta
File referenceFastaDict
@@ -846,9 +846,9 @@ task GenotypeGVCFs {
~{"-D " + dbsnpVCF} \
~{"--pedigree " + pedigree} \
~{true="-G" false="" length(annotationGroups) > 0} ~{sep=" -G " annotationGroups} \
- --only-output-calls-starting-in-intervals \
-V ~{gvcfFile} \
- -L ~{sep=' -L ' intervals}
+ ~{true="--only-output-calls-starting-in-intervals" false="" defined(intervals)} \
+ ~{true="-L" false="" defined(intervals)} ~{sep=' -L ' intervals}
}
output {
@@ -866,7 +866,7 @@ task GenotypeGVCFs {
parameter_meta {
gvcfFile: {description: "The GVCF file to be genotyped.", category: "required"}
gvcfFileIndex: {description: "The index of the input GVCF file.", category: "required"}
- intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "required"}
+ intervals: {description: "Bed files or interval lists describing the regions to operate on.", category: "optional"}
outputPath: {description: "The location to write the output VCF file to.", category: "required"}
referenceFasta: {description: "The reference fasta file which was also used for mapping.",
category: "required"}
diff --git a/isoseq3.wdl b/isoseq3.wdl
index 604a71d50fa673b5d248b7edfc943ccc66150c82..5060f0e7ca5a216bd409f5d19605ac0f65d855dc 100644
--- a/isoseq3.wdl
+++ b/isoseq3.wdl
@@ -26,6 +26,7 @@ task Refine {
Boolean requirePolyA = false
String logLevel = "WARN"
File inputBamFile
+ File inputBamIndex
File primerFile
String outputDir
String outputNamePrefix
@@ -72,6 +73,7 @@ task Refine {
requirePolyA: {description: "Require fl reads to have a poly(A) tail and remove it.", category: "common"}
logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"}
inputBamFile: {description: "Bam input file.", category: "required"}
+ inputBamIndex: {description: "Index for the Bam input file.", category: "required"}
primerFile: {description: "Barcode/primer fasta file.", category: "required"}
outputDir: {description: "Output directory path.", category: "required"}
outputNamePrefix: {description: "Basename of the output files.", category: "required"}
diff --git a/lima.wdl b/lima.wdl
index 1a40b1c8174c8df6aefa360fe199e2a1d8ccea8d..7ef9d4abfe8e88a26bad13d407895813f1da2227 100644
--- a/lima.wdl
+++ b/lima.wdl
@@ -83,32 +83,30 @@ task Lima {
~{true="--peek-guess" false="" peekGuess} \
--log-level ~{logLevel} \
--num-threads ~{cores} \
- ~{"--log-file " + outputPrefix + ".fl.stderr.log"} \
+ ~{"--log-file " + outputPrefix + ".stderr.log"} \
~{inputBamFile} \
~{barcodeFile} \
- ~{basename(outputPrefix) + ".fl.bam"}
+ ~{outputPrefix + ".bam"}
- # copy commands below are needed because glob command does not find
- # multiple bam/bam.pbi/subreadset.xml files when not located in working
- # directory.
- cp "~{basename(outputPrefix)}.fl.json" "~{outputPrefix}.fl.json"
- cp "~{basename(outputPrefix)}.fl.lima.counts" "~{outputPrefix}.fl.lima.counts"
- cp "~{basename(outputPrefix)}.fl.lima.report" "~{outputPrefix}.fl.lima.report"
- cp "~{basename(outputPrefix)}.fl.lima.summary" "~{outputPrefix}.fl.lima.summary"
- find . -path "*.bam" > bamFiles.txt
- find . -path "*.bam.pbi" > bamIndexes.txt
- find . -path "*.subreadset.xml" > subreadsets.txt
+ # copy the files with the default filename to the folder specified in
+ # outputPrefix.
+ if [ "~{basename(outputPrefix)}.json" != "~{outputPrefix}.json" ]; then
+ cp "~{basename(outputPrefix)}.json" "~{outputPrefix}.json"
+ cp "~{basename(outputPrefix)}.lima.counts" "~{outputPrefix}.lima.counts"
+ cp "~{basename(outputPrefix)}.lima.report" "~{outputPrefix}.lima.report"
+ cp "~{basename(outputPrefix)}.lima.summary" "~{outputPrefix}.lima.summary"
+ fi
}
output {
- Array[File] limaBam = read_lines("bamFiles.txt")
- Array[File] limaBamIndex = read_lines("bamIndexes.txt")
- Array[File] limaXml = read_lines("subreadsets.txt")
- File limaStderr = outputPrefix + ".fl.stderr.log"
- File limaJson = outputPrefix + ".fl.json"
- File limaCounts = outputPrefix + ".fl.lima.counts"
- File limaReport = outputPrefix + ".fl.lima.report"
- File limaSummary = outputPrefix + ".fl.lima.summary"
+ Array[File] limaBam = glob("*.bam")
+ Array[File] limaBamIndex = glob("*.bam.pbi")
+ Array[File] limaXml = glob("*.subreadset.xml")
+ File limaStderr = outputPrefix + ".stderr.log"
+ File limaJson = outputPrefix + ".json"
+ File limaCounts = outputPrefix + ".lima.counts"
+ File limaReport = outputPrefix + ".lima.report"
+ File limaSummary = outputPrefix + ".lima.summary"
}
runtime {
diff --git a/pbbam.wdl b/pbbam.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..52737a008625e559b76905b673f0c18260b8c582
--- /dev/null
+++ b/pbbam.wdl
@@ -0,0 +1,70 @@
+version 1.0
+
+# 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
+# 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
+
+task Index {
+ input {
+ File bamFile
+ String? outputBamPath
+
+ String memory = "2G"
+ Int timeMinutes = 1 + ceil(size(bamFile, "G") * 4)
+ String dockerImage = "quay.io/biocontainers/pbbam:1.6.0--h5b7e6e0_0"
+ }
+
+ # Select_first is needed, otherwise womtool validate fails.
+ String outputPath = select_first([outputBamPath, basename(bamFile)])
+ String bamIndexPath = outputPath + ".pbi"
+
+ command {
+ bash -c '
+ set -e
+ # Make sure outputBamPath does not exist.
+ if [ ! -f ~{outputPath} ]
+ then
+ mkdir -p "$(dirname ~{outputPath})"
+ ln ~{bamFile} ~{outputPath}
+ fi
+ pbindex ~{outputPath} ~{bamIndexPath}
+ '
+ }
+
+ output {
+ File indexedBam = outputPath
+ File index = bamIndexPath
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ # inputs
+ bamFile: {description: "The BAM file for which an index should be made.", category: "required"}
+ outputBamPath: {description: "The location where the BAM file should be written to. The index will appear alongside this link to the BAM file.",
+ 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"}
+ }
+}
diff --git a/pbmm2.wdl b/pbmm2.wdl
index 84fbd2d08e32c9b9676e5b24f6d6c0843bb95dce..31d4c667e37f2444df413085d78870208504761a 100644
--- a/pbmm2.wdl
+++ b/pbmm2.wdl
@@ -30,7 +30,7 @@ task Mapping {
Int cores = 4
String memory = "30G"
- Int timeMinutes = 1 + ceil(size(queryFile, "G") * 200 / cores)
+ Int timeMinutes = 1 + ceil(size(queryFile, "G") * 2000 / cores)
String dockerImage = "quay.io/biocontainers/pbmm2:1.3.0--h56fc30b_1"
}
@@ -41,6 +41,7 @@ task Mapping {
-j ~{cores} \
~{referenceMMI} \
~{queryFile} \
+ --sample ~{sample} \
~{sample}.align.bam
}
diff --git a/picard.wdl b/picard.wdl
index 1afa5ea7272155e09064c07725e729121061bf83..49db8b8b44eccb793f8eba46bc5b8aae7b297582 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -66,6 +66,71 @@ task BedToIntervalList {
}
}
+task CollectHsMetrics {
+ input {
+ File inputBam
+ File inputBamIndex
+ File referenceFasta
+ File referenceFastaDict
+ File referenceFastaFai
+ File targets
+ File? baits
+ String basename
+
+ # Use the targets file as baits as a fallback, since often the baits
+ # for a certain capture kit are not available.
+ File baitsFile = select_first([baits, targets])
+ File targetsFile = targets
+
+ Int memoryMb = javaXmxMb + 512
+ Int javaXmxMb = 3072
+ # Additional * 2 because picard multiple metrics reads the reference fasta twice.
+ Int timeMinutes = 1 + ceil(size(referenceFasta, "G") * 3 * 2) + ceil(size(inputBam, "G") * 6)
+ String dockerImage = "quay.io/biocontainers/picard:2.23.2--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{basename})"
+ picard -Xmx~{javaXmxMb}M -XX:ParallelGCThreads=1 \
+ CollectHsMetrics \
+ I=~{inputBam} \
+ R=~{referenceFasta} \
+ BAIT_INTERVALS=~{baitsFile} \
+ TARGET_INTERVALS=~{targetsFile} \
+ O="~{basename}.hs_metrics.txt"
+ }
+
+ output {
+ File HsMetrics = basename + ".hs_metrics.txt"
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: "~{memoryMb}M"
+ }
+
+ 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"}
+ targets: {description: "Picard interval file of the capture targets.", category: "required"}
+ baits: {description: "Picard interval file of the capture bait set.", category: "advanced"}
+ basename: {description: "The basename/prefix of the output files (may include directories).", category: "required"}
+ memoryMb: {description: "The amount of memory this job will use in megabytes.", category: "advanced"}
+ javaXmxMb: {description: "The maximum memory available to the program in megabytes. Should be lower than `memoryMb` 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 CollectMultipleMetrics {
input {
File inputBam
@@ -315,6 +380,57 @@ task CollectTargetedPcrMetrics {
}
}
+task CollectVariantCallingMetrics {
+ input {
+ File dbsnp
+ File dbsnpIndex
+ File inputVCF
+ File inputVCFIndex
+ String basename
+
+ String memory = "9G"
+ String javaXmx = "8G"
+ Int timeMinutes = 1440
+ String dockerImage = "quay.io/biocontainers/picard:2.23.2--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{basename})"
+ picard -Xmx~{javaXmx} \
+ CollectVariantCallingMetrics -XX:ParallelGCThreads=1 \
+ DBSNP=~{dbsnp} \
+ INPUT=~{inputVCF} \
+ OUTPUT=~{basename}
+ }
+
+ output {
+ File details = basename + ".variant_calling_detail_metrics"
+ File summary = basename + ".variant_calling_summary_metrics"
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ parameter_meta {
+ # inputs
+ dbsnp: {description: "DBSNP vcf file to use with CollectVariantCallingMetrics.", category: "required"}
+ dbsnpIndex: {description: "Index file for the DBSNP VCF.", category: "required"}
+ inputVCF: {description: "Input VCF file", category: "required"}
+ inputVCFIndex: {description: "Index file for the input VCF.", category: "required"}
+ basename: {description: "The basename/prefix of the output files (may include directories).", 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 CreateSequenceDictionary {
input {
File inputFile
diff --git a/samtools.wdl b/samtools.wdl
index 24d95aa4b4b17a8e2d5eeb6a26c19cebeeeac312..ad94338a37d7e0b526aa1623780c350819241ec3 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -332,6 +332,7 @@ task Merge {
Int threads = 1
Int timeMinutes = 1 + ceil(size(bamFiles, "G") * 2)
+ String memory = "4G"
String dockerImage = "quay.io/biocontainers/samtools:1.10--h9402c20_2"
}
String indexPath = sub(outputBamPath, "\.bam$",".bai")
@@ -355,6 +356,7 @@ task Merge {
runtime {
cpu: threads
docker: dockerImage
+ memory: memory
time_minutes: timeMinutes
}
@@ -362,7 +364,7 @@ task Merge {
# inputs
bamFiles: {description: "The BAM files to merge.", category: "required"}
outputBamPath: {description: "The location the merged BAM file should be written to.", category: "common"}
- threads: {description: "Number of threads to use.", category: "advanced"}
+ threads: {description: "Number of threads to use.", category: "common"}
force: {description: "Equivalent to samtools merge's `-f` flag.", 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.",
diff --git a/whatshap.wdl b/whatshap.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..2ee90f5024ca3fec7051a091ecaa2944f61de874
--- /dev/null
+++ b/whatshap.wdl
@@ -0,0 +1,197 @@
+version 1.0
+
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+
+task Phase {
+ input {
+ String outputVCF
+ File? reference
+ File? referenceIndex
+ String? tag
+ String? algorithm
+ Boolean? indels
+ String? sample
+ 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
+ String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
+ }
+
+ command {
+ whatshap phase \
+ ~{vcf} \
+ ~{phaseInput} \
+ ~{if defined(outputVCF) then ("--output " + '"' + outputVCF + '"') else ""} \
+ ~{if defined(reference) then ("--reference " + '"' + reference + '"') else ""} \
+ ~{if defined(tag) then ("--tag " + '"' + tag + '"') else ""} \
+ ~{if defined(algorithm) then ("--algorithm " + '"' + algorithm + '"') else ""} \
+ ~{true="--indels" false="" indels} \
+ ~{if defined(sample) then ("--sample " + '"' + sample + '"') else ""} \
+ ~{if defined(chromosome) then ("--chromosome " + '"' + chromosome + '"') else ""} \
+ ~{if defined(threshold) then ("--threshold " + '"' + threshold + '"') else ""} \
+ ~{if defined(ped) then ("--ped " + '"' + ped + '"') else ""} \
+ tabix -p vcf ~{outputVCF}
+ }
+
+ output {
+ File phasedVCF = outputVCF
+ File phasedVCFIndex = outputVCF + ".tbi"
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ parameter_meta {
+ 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"}
+ 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"}
+ }
+}
+
+task Stats {
+ input {
+ 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
+ String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
+ }
+
+ command {
+ whatshap stats \
+ ~{vcf} \
+ ~{if defined(gtf) then ("--gtf " + '"' + gtf + '"') else ""} \
+ ~{if defined(sample) then ("--sample " + '"' + sample + '"') else ""} \
+ ~{if defined(tsv) then ("--tsv " + '"' + tsv + '"') else ""} \
+ ~{if defined(blockList) then ("--block-list " + '"' + blockList + '"') else ""} \
+ ~{if defined(chromosome) then ("--chromosome " + '"' + chromosome + '"') else ""}
+ }
+
+ output {
+ File? phasedGTF = gtf
+ File? phasedTSV = tsv
+ File? phasedBlockList = blockList
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ 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"
+ 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 Haplotag {
+ input {
+ 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
+ String dockerImage = "quay.io/biocontainers/mulled-v2-5c61fe1d8c284dd05d26238ce877aa323205bf82:89b4005d04552bdd268e8af323df83357e968d83-0"
+ }
+
+ command {
+ 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}')"
+ }
+
+ output {
+ File bam = outputFile
+ File bamIndex = outputFile + ".bai"
+ }
+
+ runtime {
+ docker: dockerImage
+ time_minutes: timeMinutes
+ memory: memory
+ }
+
+ 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."
+ 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"}
+ }
+}