diff --git a/CHANGELOG.md b/CHANGELOG.md
index 21019ef229a0951320ad07cb7b492b68649c41a7..33f85337a40d19520b36117a57720916ddbd3288 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,9 +8,24 @@ Newest changes should be on top.
This document is user facing. Please word the changes in such a way
that users understand how the changes affect the new version.
-->
-version 3.2.0
+
+version 3.2.0-develop
---------------------------
+ Added STAR GenomeGenerate task.
++ GATK.HaplotypeCaller: Add `--dont-use-soft-clipped-bases` and
+ `--standard-min-confidence-threshold-for-calling` options. These are
+ required for RNA seq variant calling according to GATK best practices.
++ Samtools: Fix quotations in sort command.
++ Samtools SortByName is now called Sort.
++ Generalize sort task to now also sort by position, instead of just read name.
++ Add CreateSequenceDictionary task to picard.
++ Add faidx task to samtools.
++ Isoseq3: Remove dirname command from output folder creation step.
++ Isoseq3: Requires more memory by default, is now 2G.
++ Isoseq3: Remove cp commands and other bash magic, file naming is now solved by pipeline.
++ Lima: Replace mv command with cp.
++ Add WDL task for smoove (lumpy) sv-caller.
+
version 3.1.0
---------------------------
diff --git a/ccs.wdl b/ccs.wdl
index 39bb0a19578e353a596c471e7490556de89896a9..3a8f887947faab7bc3ee898cf06fcd6ca28586d8 100644
--- a/ccs.wdl
+++ b/ccs.wdl
@@ -31,8 +31,8 @@ task CCS {
File subreadsFile
String outputPrefix
- Int cores = 4
- String memory = "10G"
+ Int cores = 2
+ String memory = "2G"
String dockerImage = "quay.io/biocontainers/pbccs:4.2.0--0"
}
diff --git a/gatk.wdl b/gatk.wdl
index b730cbee75fd470f8d6eb4d446d7bba06742c6e5..586c25d09edfde9cb6efa6387c445fb8b37753e9 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -910,6 +910,8 @@ task HaplotypeCaller {
String? outputMode
Boolean gvcf = false
String emitRefConfidence = if gvcf then "GVCF" else "NONE"
+ Boolean dontUseSoftClippedBases = false
+ Float? standardMinConfidenceThresholdForCalling
String memory = "12G"
String javaXmx = "4G"
@@ -931,7 +933,9 @@ task HaplotypeCaller {
~{"--pedigree " + pedigree} \
~{"--contamination-fraction-per-sample-file " + contamination} \
~{"--output-mode " + outputMode} \
- --emit-ref-confidence ~{emitRefConfidence}
+ --emit-ref-confidence ~{emitRefConfidence} \
+ ~{true="--dont-use-soft-clipped-bases" false="" dontUseSoftClippedBases} \
+ ~{"--standard-min-confidence-threshold-for-calling " + standardMinConfidenceThresholdForCalling}
}
output {
@@ -962,6 +966,8 @@ task HaplotypeCaller {
category: "advanced"}
emitRefConfidence: {description: "Whether to include reference calls. Three modes: 'NONE', 'BP_RESOLUTION' and 'GVCF'",
category: "advanced"}
+ dontUseSoftClippedBases: {description: "Do not use soft-clipped bases. Should be 'true' for RNA variant calling.", category: "common"}
+ standardMinConfidenceThresholdForCalling: {description: "Confidence threshold used for calling variants.", category: "advanced"}
dbsnpVCF: {description: "A dbSNP VCF.", category: "common"}
dbsnpVCFIndex: {description: "The index for the dbSNP VCF.", category: "common"}
pedigree: {description: "Pedigree file for determining the population \"founders\"", category: "common"}
diff --git a/isoseq3.wdl b/isoseq3.wdl
index 8cc0db8fe0456f5626ee4eebb8bb586846a370d1..10d87bbc2264ac1aad7661f8ab8786249503684a 100644
--- a/isoseq3.wdl
+++ b/isoseq3.wdl
@@ -27,50 +27,35 @@ task Refine {
String logLevel = "WARN"
File inputBamFile
File primerFile
- String outputPrefix
+ String outputDir
+ String outputNamePrefix
- Int cores = 4
- String memory = "10G"
+ Int cores = 2
+ String memory = "2G"
String dockerImage = "quay.io/biocontainers/isoseq3:3.3.0--0"
}
- command <<<
+ command {
set -e
- mkdir -p "$(dirname ~{outputPrefix})"
-
- # Create a unique output name base on the input bam file.
- bamBasename="$(basename ~{inputBamFile})"
- bamNewName="${bamBasename/fl/flnc}"
- folderDirname="$(dirname ~{outputPrefix})"
- combinedOutput="${folderDirname}/${bamNewName}"
-
+ mkdir -p "~{outputDir}"
isoseq3 refine \
--min-polya-length ~{minPolyAlength} \
~{true="--require-polya" false="" requirePolyA} \
--log-level ~{logLevel} \
--num-threads ~{cores} \
- --log-file "${bamNewName}.stderr.log" \
+ --log-file "~{outputDir}/~{outputNamePrefix}.stderr.log" \
~{inputBamFile} \
~{primerFile} \
- ${bamNewName}
-
- # Copy commands below are needed because naming schema for Refine output
- # can not be correctly handled in the WDL output section.
- cp "${bamNewName}" "${combinedOutput}"
- cp "${bamNewName}.pbi" "${combinedOutput}.pbi"
- cp "${bamNewName/bam/consensusreadset}.xml" "${combinedOutput/bam/consensusreadset}.xml"
- cp "${bamNewName/bam/filter_summary}.json" "${combinedOutput/bam/filter_summary}.json"
- cp "${bamNewName/bam/report}.csv" "${combinedOutput/bam/report}.csv"
- cp "${bamNewName}.stderr.log" "${combinedOutput}.stderr.log"
- >>>
+ "~{outputDir}/~{outputNamePrefix}.bam"
+ }
output {
- Array[File] outputFLNCfile = glob("*.bam")
- Array[File] outputFLNCindexFile = glob("*.bam.pbi")
- Array[File] outputConsensusReadsetFile = glob("*.consensusreadset.xml")
- Array[File] outputFilterSummaryFile = glob("*.filter_summary.json")
- Array[File] outputReportFile = glob("*.report.csv")
- Array[File] outputSTDERRfile = glob("*.stderr.log")
+ File outputFLNCfile = outputDir + "/" + outputNamePrefix + ".bam"
+ File outputFLNCindexFile = outputDir + "/" + outputNamePrefix + ".bam.pbi"
+ File outputConsensusReadsetFile = outputDir + "/" + outputNamePrefix + ".consensusreadset.xml"
+ File outputFilterSummaryFile = outputDir + "/" + outputNamePrefix + ".filter_summary.json"
+ File outputReportFile = outputDir + "/" + outputNamePrefix + ".report.csv"
+ File outputSTDERRfile = outputDir + "/" + outputNamePrefix + ".stderr.log"
}
runtime {
@@ -86,7 +71,8 @@ task Refine {
logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"}
inputBamFile: {description: "BAM input file.", category: "required"}
primerFile: {description: "Barcode/primer fasta file.", category: "required"}
- outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
+ outputDir: {description: "Output directory path.", category: "required"}
+ outputNamePrefix: {description: "Basename of the output files.", category: "required"}
cores: {description: "The number of cores to be used.", category: "advanced"}
memory: {description: "The amount of memory available to the job.", category: "advanced"}
dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
diff --git a/lima.wdl b/lima.wdl
index 747959a1eb9b1695ae891e178b36725d95204bed..ba8a5407fa1be7757beaff0b5bdb404016793352 100644
--- a/lima.wdl
+++ b/lima.wdl
@@ -48,8 +48,8 @@ task Lima {
File barcodeFile
String outputPrefix
- Int cores = 4
- String memory = "10G"
+ Int cores = 2
+ String memory = "2G"
String dockerImage = "quay.io/biocontainers/lima:1.11.0--0"
}
@@ -87,13 +87,13 @@ task Lima {
~{barcodeFile} \
~{basename(outputPrefix) + ".fl.bam"}
- # Move commands below are needed because glob command does not find
+ # copy commands below are needed because glob command does not find
# multiple bam/bam.pbi/subreadset.xml files when not located in working
# directory.
- mv "~{basename(outputPrefix)}.fl.json" "~{outputPrefix}.fl.json"
- mv "~{basename(outputPrefix)}.fl.lima.counts" "~{outputPrefix}.fl.lima.counts"
- mv "~{basename(outputPrefix)}.fl.lima.report" "~{outputPrefix}.fl.lima.report"
- mv "~{basename(outputPrefix)}.fl.lima.summary" "~{outputPrefix}.fl.lima.summary"
+ 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"
}
output {
diff --git a/picard.wdl b/picard.wdl
index 7df96aa93e758566419a73f7a98f01669cb7d3d6..5393cd3a30487f4cda0a40b4744717a9ad6ad505 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -313,6 +313,48 @@ task CollectTargetedPcrMetrics {
}
}
+task CreateSequenceDictionary {
+ input {
+ File inputFile
+ String outputDir
+
+ String memory = "3G"
+ String javaXmx = "2G"
+ String dockerImage = "quay.io/biocontainers/picard:2.22.3--0"
+ }
+
+ command {
+ set -e
+ mkdir -p "~{outputDir}"
+ picard -Xmx~{javaXmx} \
+ -XX:ParallelGCThreads=1 \
+ CreateSequenceDictionary \
+ REFERENCE=~{inputFile} \
+ OUTPUT="~{outputDir}/$(basename ~{inputFile}).dict"
+ }
+
+ output {
+ File outputDict = outputDir + "/" + basename(inputFile) + ".dict"
+ }
+
+ runtime {
+ memory: memory
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ # inputs
+ inputFile: {description: "The input fasta file.", category: "required"}
+ outputDir: {description: "Output directory path.", category: "required"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ javaXmx: {description: "The maximum memory available to the program. Should be lower than `memory` to accommodate JVM overhead.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+ # outputs
+ outputDict: {description: "Dictionary of the input fasta file."}
+ }
+}
+
# Combine multiple recalibrated BAM files from scattered ApplyRecalibration runs
task GatherBamFiles {
input {
diff --git a/samtools.wdl b/samtools.wdl
index a4a893a1ee34b8ce81a9b07f9cf976cd5bdc1292..5521c6aaa5f93badddc571acf400f52afa98de1f 100644
--- a/samtools.wdl
+++ b/samtools.wdl
@@ -57,6 +57,44 @@ task BgzipAndIndex {
}
}
+task Faidx {
+ input {
+ File inputFile
+ String outputDir
+
+ String memory = "2G"
+ String dockerImage = "quay.io/biocontainers/samtools:1.10--h9402c20_2"
+ }
+
+ command {
+ set -e
+ mkdir -p "~{outputDir}"
+ ln -s ~{inputFile} "~{outputDir}/$(basename ~{inputFile})"
+ samtools faidx \
+ "~{outputDir}/$(basename ~{inputFile})"
+ }
+
+ output {
+ File outputIndex = outputDir + "/" + basename(inputFile) + ".fai"
+ }
+
+ runtime {
+ memory: memory
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ # inputs
+ inputFile: {description: "The input fasta file.", category: "required"}
+ outputDir: {description: "Output directory path.", category: "required"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+ # outputs
+ outputIndex: {description: "Index of the input fasta file."}
+ }
+}
+
task Index {
input {
File bamFile
@@ -136,34 +174,52 @@ task Merge {
}
}
-task SortByName {
+task Sort {
input {
- File bamFile
- String outputBamPath = "namesorted.bam"
+ File inputBam
+ String outputPath
+ Boolean sortByName = false
+ Int compressionLevel = 1
- String dockerImage = "quay.io/biocontainers/samtools:1.8--h46bd0b3_5"
+ String memory = "2G"
+ String dockerImage = "quay.io/biocontainers/samtools:1.10--h9402c20_2"
+
+ Int? threads
}
command {
set -e
- mkdir -p "$(dirname ~{outputBamPath})"
- samtools sort -n ~{bamFile} -o ~{outputBamPath}
+ mkdir -p "$(dirname ~{outputPath})"
+ samtools sort \
+ -l ~{compressionLevel} \
+ ~{true="-n" false="" sortByName} \
+ ~{"--threads " + threads} \
+ -o ~{outputPath} \
+ ~{inputBam}
}
output {
- File outputBam = outputBamPath
+ File outputSortedBam = outputPath
}
runtime {
+ cpu: 1 + select_first([threads, 0])
+ memory: memory
docker: dockerImage
}
parameter_meta {
# inputs
- bamFile: {description: "The BAM file to get sorted.", category: "required"}
- outputBamPath: {description: "The location the sorted BAM file should be written to.", category: "common"}
- dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
- category: "advanced"}
+ inputBam: {description: "The input SAM file.", category: "required"}
+ outputPath: {description: "Output directory path + output file.", category: "required"}
+ sortByName: {description: "Sort the inputBam by read name instead of position.", category: "advanced"}
+ compressionLevel: {description: "Compression level from 0 (uncompressed) to 9 (best).", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+ threads: {description: "The number of additional threads that will be used for this task.", category: "advanced"}
+
+ # outputs
+ outputSortedBam: {description: "Sorted BAM file."}
}
}
diff --git a/scripts b/scripts
index dfef7cb2555667126dc1751add414527240d71bc..b83da72b9b43b956a3062b78fb08044eb9fae464 160000
--- a/scripts
+++ b/scripts
@@ -1 +1 @@
-Subproject commit dfef7cb2555667126dc1751add414527240d71bc
+Subproject commit b83da72b9b43b956a3062b78fb08044eb9fae464
diff --git a/smoove.wdl b/smoove.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..e8846f72b48ea5e0702af49c0954e6d27e20812c
--- /dev/null
+++ b/smoove.wdl
@@ -0,0 +1,72 @@
+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2020 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task Call {
+ input {
+ File bamFile
+ File bamIndex
+ File referenceFasta
+ File referenceFastaFai
+ String sample
+ String outputDir = "./smoove"
+
+ String memory = "15G"
+ String dockerImage = "quay.io/biocontainers/smoove:0.2.5--0"
+ Int timeMinutes = 1440
+ }
+
+ command {
+ set -e
+ mkdir -p ~{outputDir}
+ smoove call \
+ --outdir ~{outputDir} \
+ --name ~{sample} \
+ --fasta ~{referenceFasta} \
+ ~{bamFile}
+ }
+
+ output {
+ File smooveVcf = outputDir + "/" + sample + "-smoove.vcf.gz"
+ }
+
+ runtime {
+ memory: memory
+ docker: dockerImage
+ time_minutes: timeMinutes
+
+ }
+
+ parameter_meta {
+ # inputs
+ bamFile: {description: "The bam file to process.", category: "required"}
+ 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"}
+ 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"}
+ }
+}