From 325811625e2466362d2a292c4c143f93c6180682 Mon Sep 17 00:00:00 2001
From: ffinfo <pjrvanthof@gmail.com>
Date: Wed, 22 Aug 2018 13:33:14 +0200
Subject: [PATCH] Switch to structs
---
gatk.wdl | 141 +++++++++++++++++++++++++------------------------------
1 file changed, 64 insertions(+), 77 deletions(-)
diff --git a/gatk.wdl b/gatk.wdl
index 1f76099..265d284 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -1,18 +1,17 @@
version 1.0
+import "common.wdl"
+
# Apply Base Quality Score Recalibration (BQSR) model
task ApplyBQSR {
input {
String? preCommand
File? gatkJar
- File inputBam
- File inputBamIndex
+ IndexedBamFile inputBam
String outputBamPath
File recalibrationReport
Array[File]+ sequenceGroupInterval
- File refDict
- File refFasta
- File refFastaIndex
+ Reference reference
Int? compressionLevel
Int memory = 4
@@ -30,8 +29,8 @@ task ApplyBQSR {
ApplyBQSR \
--create-output-bam-md5 \
--add-output-sam-program-record \
- -R ~{refFasta} \
- -I ~{inputBam} \
+ -R ~{reference.fasta} \
+ -I ~{inputBam.file} \
--use-original-qualities \
-O ~{outputBamPath} \
-bqsr ~{recalibrationReport} \
@@ -42,7 +41,11 @@ task ApplyBQSR {
}
output {
- File recalibrated_bam = outputBamPath
+ IndexedBamFile recalibrated_bam = {
+ "file": outputBamPath,
+ "index": sub(outputBamPath, "\.bam$", ".bai")
+ }
+
File recalibrated_bam_checksum = outputBamPath + ".md5"
}
@@ -56,28 +59,19 @@ task BaseRecalibrator {
input {
String? preCommand
File? gatkJar
- File inputBam
- File inputBamIndex
+ IndexedBamFile inputBam
String recalibrationReportPath
Array[File]+ sequenceGroupInterval
- Array[File]? knownIndelsSitesVCFs
- Array[File]? knownIndelsSitesIndices
- File? dbsnpVCF
- File? dbsnpVCFindex
- File refDict
- File refFasta
- File refFastaIndex
+ Array[IndexedVcfFile]? knownIndelsSitesVCFs
+ IndexedVcfFile? dbsnpVCF
+ Reference reference
Int memory = 4
Float memoryMultiplier = 3.0
}
Array[File]+ knownIndelsSitesVCFsArg = flatten([
- select_first([knownIndelsSitesVCFs, []]),
- select_all([dbsnpVCF])
- ])
- Array[File]+ knownIndelsSitesIndicesArg = flatten([
- select_first([knownIndelsSitesIndices, []]),
- select_all([dbsnpVCFindex])
+ select_first([knownIndelsSitesVCFs.file, []]),
+ select_all([dbsnpVCF.file])
])
String toolCommand = if defined(gatkJar)
@@ -89,8 +83,8 @@ task BaseRecalibrator {
~{preCommand}
~{toolCommand} \
BaseRecalibrator \
- -R ~{refFasta} \
- -I ~{inputBam} \
+ -R ~{reference.fasta} \
+ -I ~{inputBam.file} \
--use-original-qualities \
-O ~{recalibrationReportPath} \
--known-sites ~{sep=" --known-sites " knownIndelsSitesVCFsArg} \
@@ -109,17 +103,14 @@ task BaseRecalibrator {
task CombineGVCFs {
input {
String? preCommand
- Array[File]+ gvcfFiles
- Array[File]+ gvcfFileIndexes
+ Array[IndexedVcfFile]+ gvcfFiles
Array[File]+ intervals
String outputPath
String? gatkJar
- File refFasta
- File refFastaIndex
- File refDict
+ Reference reference
Int? compressionLevel #TODO This isn't being used?
Int memory = 4
@@ -137,19 +128,21 @@ task CombineGVCFs {
if [ ~{length(gvcfFiles)} -gt 1 ]; then
~{toolCommand} \
CombineGVCFs \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{outputPath} \
-V ~{sep=' -V ' gvcfFiles} \
-L ~{sep=' -L ' intervals}
else # TODO this should be handeled in wdl
- ln -sf ~{gvcfFiles[0]} ~{outputPath}
- ln -sf ~{gvcfFileIndexes[0]} ~{outputPath}.tbi
+ ln -sf ~{gvcfFiles[0].file} ~{outputPath}
+ ln -sf ~{gvcfFiles[0].index} ~{outputPath}.tbi
fi
}
output {
- File outputGVCF = outputPath
- File outputGVCFindex = outputPath + ".tbi"
+ IndexedVcfFile outputVCF = {
+ "file": outputPath,
+ "index": outputPath + ".tbi"
+ }
}
runtime {
@@ -194,20 +187,16 @@ task GatherBqsrReports {
task GenotypeGVCFs {
input {
String? preCommand
- File gvcfFiles
- File gvcfFileIndexes
+ Array[IndexedVcfFile] gvcfFiles
Array[File]+ intervals
String outputPath
String? gatkJar
- File refFasta
- File refFastaIndex
- File refDict
+ Reference reference
- File? dbsnpVCF
- File? dbsnpVCFindex
+ IndexedVcfFile? dbsnpVCF
Int? compressionLevel
Int memory = 4
@@ -223,19 +212,21 @@ task GenotypeGVCFs {
~{preCommand}
~{toolCommand} \
GenotypeGVCFs \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{outputPath} \
- ~{"-D " + dbsnpVCF} \
+ ~{"-D " + dbsnpVCF.file} \
-G StandardAnnotation \
--only-output-calls-starting-in-intervals \
-new-qual \
- -V ~{gvcfFiles} \
+ -V ~{sep=' -V ' gvcfFiles.file} \
-L ~{sep=' -L ' intervals}
}
output {
- File outputVCF = outputPath
- File outputVCFindex = outputPath + ".tbi"
+ IndexedVcfFile outputVCF = {
+ "file": outputPath,
+ "index": outputPath + ".tbi"
+ }
}
runtime{
@@ -247,19 +238,15 @@ task GenotypeGVCFs {
task HaplotypeCallerGvcf {
input {
String? preCommand
- Array[File]+ inputBams
- Array[File]+ inputBamsIndex
+ Array[IndexedBamFile]+ inputBams
Array[File]+ intervalList
String gvcfPath
- File refDict
- File refFasta
- File refFastaIndex
+ Reference reference
Float contamination = 0.0
Int? compressionLevel
String? gatkJar
- File? dbsnpVCF
- File? dbsnpVCFindex
+ IndexedVcfFile? dbsnpVCF
Int memory = 4
Float memoryMultiplier = 3
@@ -274,18 +261,20 @@ task HaplotypeCallerGvcf {
~{preCommand}
~{toolCommand} \
HaplotypeCaller \
- -R ~{refFasta} \
+ -R ~{reference.fasta} \
-O ~{gvcfPath} \
- -I ~{sep=" -I " inputBams} \
+ -I ~{sep=" -I " inputBams.file} \
-L ~{sep=' -L ' intervalList} \
- ~{"-D " + dbsnpVCF} \
+ ~{"-D " + dbsnpVCF.file} \
-contamination ~{contamination} \
-ERC GVCF
}
output {
- File outputGVCF = gvcfPath
- File outputGVCFindex = gvcfPath + ".tbi"
+ IndexedVcfFile outputGVCF = {
+ "file": gvcfPath,
+ "index": gvcfPath + ".tbi"
+ }
}
runtime {
@@ -297,11 +286,8 @@ task MuTect2 {
input {
String? preCommand
- Array[File]+ inputBams
- Array[File]+ inputBamIndex
- File refFasta
- File refFastaIndex
- File refDict
+ Array[IndexedBamFile]+ inputBams
+ Reference reference
String outputVcf
String tumorSample
String? normalSample
@@ -321,8 +307,8 @@ task MuTect2 {
~{preCommand}
~{toolCommand} \
Mutect2 \
- -R ~{refFasta} \
- -I ~{sep=" -I " inputBams} \
+ -R ~{reference.fasta} \
+ -I ~{sep=" -I " inputBams.file} \
-tumor ~{tumorSample} \
~{"-normal " + normalSample} \
-O ~{outputVcf} \
@@ -330,8 +316,10 @@ task MuTect2 {
}
output {
- File vcfFile = outputVcf
- File vcfIndex = outputVcf + ".tbi"
+ IndexedVcfFile vcfFile = {
+ "file": outputVcf,
+ "index": outputVcf + ".tbi"
+ }
}
runtime {
@@ -343,11 +331,8 @@ task SplitNCigarReads {
input {
String? preCommand
- File inputBam
- File inputBamIndex
- File refFasta
- File refFastaIndex
- File refDict
+ IndexedBamFile inputBam
+ Reference reference
String outputBam
String? gatkJar
Array[File]+ intervals
@@ -365,15 +350,17 @@ task SplitNCigarReads {
~{preCommand}
~{toolCommand} \
SplitNCigarReads \
- -I ~{inputBam} \
- -R ~{refFasta} \
+ -I ~{inputBam.file} \
+ -R ~{reference.fasta} \
-O ~{outputBam} \
-L ~{sep=' -L ' intervals}
}
output {
- File bam = outputBam
- File bamIndex = sub(outputBam, "\.bam$", ".bai")
+ IndexedBamFile bam = {
+ "file": outputBam,
+ "index": sub(outputBam, "\.bam$", ".bai")
+ }
}
runtime {
--
GitLab