From 93240a92ad1b5c171698b7fc00bb9ae0e4e54c14 Mon Sep 17 00:00:00 2001
From: DavyCats <davycats.dc@gmail.com>
Date: Tue, 3 Apr 2018 16:20:29 +0200
Subject: [PATCH] add runtime settings
---
biopet.wdl | 4 ++++
bwa.wdl | 10 +++++++++-
common.wdl | 48 ++++++++++++++++++++++++++++++++++++++++++------
fastqc.wdl | 6 ++++++
gatk.wdl | 32 ++++++++++++++++++++++++++++++++
htseq.wdl | 4 ++++
mergecounts.wdl | 4 ++++
picard.wdl | 20 ++++++++++++++++++++
star.wdl | 3 ++-
stringtie.wdl | 2 +-
10 files changed, 124 insertions(+), 9 deletions(-)
diff --git a/biopet.wdl b/biopet.wdl
index f2ca0a0..8bdf7fb 100644
--- a/biopet.wdl
+++ b/biopet.wdl
@@ -134,4 +134,8 @@ task BaseCounter {
File transcriptIntronicSense = outputDir + "/" + prefix + ".base.transcript.intronic.sense.counts"
File transcriptSense = outputDir + "/" + prefix + ".base.transcript.sense.counts"
}
+
+ runtime {
+ memory: 16
+ }
}
diff --git a/bwa.wdl b/bwa.wdl
index 6f316d2..774f932 100644
--- a/bwa.wdl
+++ b/bwa.wdl
@@ -6,15 +6,23 @@ task BwaMem {
String outputPath
String? readgroup
+ Int? threads
+ Int? memory
+
command {
set -e -o pipefail
mkdir -p $(dirname ${outputPath})
${preCommand}
- bwa mem ${"-R '" + readgroup + "'"} \
+ bwa mem ${"-t " + threads} \
+ ${"-R '" + readgroup + "'"} \
${referenceFasta} ${inputR1} ${inputR2} | samtools sort --output-fmt BAM - > ${outputPath}
}
output {
File bamFile = outputPath
}
+ runtime{
+ threads: select_first([threads])
+ memory: if defined(memory) then memory else 8
+ }
}
diff --git a/common.wdl b/common.wdl
index 97731d4..a780747 100644
--- a/common.wdl
+++ b/common.wdl
@@ -1,31 +1,49 @@
task objectMd5 {
Object the_object
+
command {
cat ${write_object(the_object)} | md5sum - | sed -e 's/ -//'
}
+
output {
String md5sum = read_string(stdout())
}
+
+ runtime {
+ memory: 1
+ }
}
task mapMd5 {
Map[String,String] map
+
command {
- cat ${write_map(map)} | md5sum - | sed -e 's/ -//'
+ cat ${write_map(map)} | md5sum - | sed -e 's/ -//'
}
+
output {
String md5sum = read_string(stdout())
}
+
+ runtime {
+ memory: 1
+ }
}
task stringArrayMd5 {
Array[String] stringArray
+
command {
- set -eu -o pipefail
- echo ${sep=',' stringArray} | md5sum - | sed -e 's/ -//'
+ set -eu -o pipefail
+ echo ${sep=',' stringArray} | md5sum - | sed -e 's/ -//'
}
+
output {
- String md5sum = read_string(stdout())
+ String md5sum = read_string(stdout())
+ }
+
+ runtime {
+ memory: 1
}
}
@@ -33,37 +51,55 @@ task concatenateTextFiles {
Array[File] fileList
String combinedFilePath
Boolean? unzip=false
+
command {
mkdir -p ${combinedFilePath}
rm -d ${combinedFilePath}
${true='zcat' false= 'cat' unzip} ${sep=' ' fileList} \
> ${combinedFilePath}
}
+
output {
File combinedFile = combinedFilePath
}
+
+ runtime {
+ memory: 1
+ }
}
# inspired by https://gatkforums.broadinstitute.org/wdl/discussion/9616/is-there-a-way-to-flatten-arrays
task flattenStringArray {
Array[Array[String]] arrayList
+
command {
- for line in $(echo ${sep=', ' arrayList}) ; \
- do echo $line | tr -d '"[],' ; done
+ for line in $(echo ${sep=', ' arrayList}) ; \
+ do echo $line | tr -d '"[],' ; done
}
+
output {
Array[String] flattenedArray = read_lines(stdout())
}
+
+ runtime {
+ memory: 1
+ }
}
task appendToStringArray {
Array[String] array
String string
+
command {
echo "${sep='\n' array}
${string}"
}
+
output {
Array[String] out_array = read_lines(stdout())
}
+
+ runtime {
+ memory: 1
+ }
}
\ No newline at end of file
diff --git a/fastqc.wdl b/fastqc.wdl
index cdbda5e..515e9a6 100644
--- a/fastqc.wdl
+++ b/fastqc.wdl
@@ -87,15 +87,21 @@ task extractAdapters {
task getConfiguration {
String? preCommand
String? fastqcDirFile = "fastqcDir.txt"
+
command {
set -e -o pipefail
${preCommand}
echo $(dirname $(readlink -f $(which fastqc))) > ${fastqcDirFile}
}
+
output {
String fastqcDir = read_string(fastqcDirFile)
File adapterList = fastqcDir + "/Configuration/adapter_list.txt"
File contaminantList = fastqcDir + "/Configuration/contaminant_list.txt"
File limits = fastqcDir + "/Configuration/limits.txt"
}
+
+ runtime {
+ memory: 1
+ }
}
\ No newline at end of file
diff --git a/gatk.wdl b/gatk.wdl
index 6a3d160..6edac93 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -24,9 +24,14 @@ task BaseRecalibrator {
--known-sites ${sep=" --known-sites " known_indels_sites_VCFs} \
-L ${sep=" -L " sequence_group_interval}
}
+
output {
File recalibration_report = "${recalibration_report_filename}"
}
+
+ runtime {
+ memory: 6
+ }
}
# Apply Base Quality Score Recalibration (BQSR) model
@@ -57,10 +62,15 @@ task ApplyBQSR {
--static-quantized-quals 10 --static-quantized-quals 20 --static-quantized-quals 30 \
-L ${sep=" -L " sequence_group_interval}
}
+
output {
File recalibrated_bam = "${output_bam_path}"
File recalibrated_bam_checksum = "${output_bam_path}.md5"
}
+
+ runtime {
+ memory: 6
+ }
}
# Combine multiple recalibration tables from scattered BaseRecalibrator runs
@@ -78,9 +88,14 @@ task GatherBqsrReports {
-I ${sep=' -I ' input_bqsr_reports} \
-O ${output_report_filepath}
}
+
output {
File output_bqsr_report = "${output_report_filepath}"
}
+
+ runtime {
+ memory: 4
+ }
}
# Call variants on a single sample with HaplotypeCaller to produce a GVCF
@@ -109,10 +124,15 @@ task HaplotypeCallerGvcf {
-contamination ${default=0 contamination} \
-ERC GVCF
}
+
output {
File output_gvcf = "${gvcf_basename}.vcf.gz"
File output_gvcf_index = "${gvcf_basename}.vcf.gz.tbi"
}
+
+ runtime {
+ memory: 6
+ }
}
task GenotypeGVCFs {
@@ -154,6 +174,10 @@ task GenotypeGVCFs {
File output_vcf = output_basename + ".vcf.gz"
File output_vcf_index = output_basename + ".vcf.gz.tbi"
}
+
+ runtime{
+ memory: 6
+ }
}
task CombineGVCFs {
@@ -193,6 +217,10 @@ task CombineGVCFs {
File output_gvcf = output_basename + ".vcf.gz"
File output_gvcf_index = output_basename + ".vcf.gz.tbi"
}
+
+ runtime {
+ memory: 6
+ }
}
task SplitNCigarReads {
@@ -221,4 +249,8 @@ task SplitNCigarReads {
File bam = output_bam
File bam_index = output_bam + ".bai"
}
+
+ runtime {
+ memory: 6
+ }
}
diff --git a/htseq.wdl b/htseq.wdl
index b740b4f..62091ff 100644
--- a/htseq.wdl
+++ b/htseq.wdl
@@ -22,4 +22,8 @@ task HTSeqCount {
output {
File counts = outputTable
}
+
+ runtime {
+ memory: 3
+ }
}
\ No newline at end of file
diff --git a/mergecounts.wdl b/mergecounts.wdl
index ed5d5e7..c2373f7 100644
--- a/mergecounts.wdl
+++ b/mergecounts.wdl
@@ -32,4 +32,8 @@ task MergeCounts {
output {
File mergedCounts = outputFile
}
+
+ runtime {
+ memory: 4 + (2*length(inputFiles))
+ }
}
\ No newline at end of file
diff --git a/picard.wdl b/picard.wdl
index 4c6e167..24e8a51 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -17,10 +17,15 @@ task ScatterIntervalList {
INPUT=${interval_list} \
OUTPUT=scatter_list
}
+
output {
Array[File] out = glob("scatter_list/*/*.interval_list")
Int interval_count = read_int(stdout())
}
+
+ runtime {
+ memory: 6
+ }
}
# Combine multiple recalibrated BAM files from scattered ApplyRecalibration runs
@@ -41,11 +46,16 @@ task GatherBamFiles {
CREATE_INDEX=true \
CREATE_MD5_FILE=true
}
+
output {
File output_bam = "${output_bam_path}"
File output_bam_index = sub(output_bam_path, ".bam$", ".bai")
File output_bam_md5 = "${output_bam_path}.md5"
}
+
+ runtime {
+ memory: 6
+ }
}
# Mark duplicate reads to avoid counting non-independent observations
@@ -81,11 +91,16 @@ task MarkDuplicates {
CREATE_INDEX=true \
ADD_PG_TAG_TO_READS=false
}
+
output {
File output_bam = output_bam_path
File output_bam_index = sub(output_bam_path, ".bam$", ".bai")
File duplicate_metrics = metrics_path
}
+
+ runtime {
+ memory: 6
+ }
}
# Combine multiple VCFs or GVCFs from scattered HaplotypeCaller runs
@@ -107,8 +122,13 @@ task MergeVCFs {
INPUT=${sep=' INPUT=' input_vcfs} \
OUTPUT=${output_vcf_path}
}
+
output {
File output_vcf = output_vcf_path
File output_vcf_index = output_vcf_path + ".tbi"
}
+
+ runtime {
+ memory: 6
+ }
}
\ No newline at end of file
diff --git a/star.wdl b/star.wdl
index a8e2453..1ba1545 100644
--- a/star.wdl
+++ b/star.wdl
@@ -37,6 +37,7 @@ task Star {
}
runtime {
- threads: runThreadN
+ threads: select_first([runThreadN])
+ memory: 10
}
}
\ No newline at end of file
diff --git a/stringtie.wdl b/stringtie.wdl
index 33118d3..2f20133 100644
--- a/stringtie.wdl
+++ b/stringtie.wdl
@@ -28,6 +28,6 @@ task Stringtie {
}
runtime {
- threads: threads
+ threads: select_first([threads])
}
}
\ No newline at end of file
--
GitLab