diff --git a/biopet.wdl b/biopet.wdl
index b110defd1e3167397f3d4d8022f9b697acae92af..feb963fc2745f7d523025a3258a4a9f27a0280f7 100644
--- a/biopet.wdl
+++ b/biopet.wdl
@@ -409,6 +409,8 @@ task ValidateFastq {
output {
File stderr = stderr()
+ File validatedFastq1 = fastq1
+ File? validatedFastq2 = fastq2
}
runtime {
diff --git a/biopet/seqstat.wdl b/biopet/seqstat.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..c1e83a2f86919ad181dfaa4498c0d94b96752e15
--- /dev/null
+++ b/biopet/seqstat.wdl
@@ -0,0 +1,44 @@
+version 1.0
+
+# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 2018
+
+task Generate {
+ input {
+ String? preCommand
+ File? toolJar
+ File fastqR1
+ File? fastqR2
+ String outputFile
+ String sample
+ String library
+ String readgroup
+
+ Int memory = 4
+ Float memoryMultiplier = 2.0
+ }
+
+ String toolCommand = if defined(toolJar)
+ then "java -Xmx" + memory + "G -jar " + toolJar
+ else "biopet-seqstat -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ ~{preCommand}
+ mkdir -p $(dirname ~{outputFile})
+ ~{toolCommand} Generate \
+ --fastqR1 ~{fastqR1} \
+ ~{"--fastqR2 " + fastqR2} \
+ --output ~{outputFile} \
+ ~{"--sample " + sample} \
+ ~{"--library " + library } \
+ ~{"--readgroup " + readgroup }
+ }
+
+ output {
+ File json = outputFile
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
\ No newline at end of file
diff --git a/bwa.wdl b/bwa.wdl
index ba0023a3194c58e85b534d06371d6ab5a5e51184..d8ce3e3239a202f93de5ce25fbacd3e75bde6371 100644
--- a/bwa.wdl
+++ b/bwa.wdl
@@ -1,5 +1,7 @@
version 1.0
+import "common.wdl" as common
+
task Mem {
input {
String? preCommand
@@ -9,29 +11,59 @@ task Mem {
String outputPath
String? readgroup
+ String? picardJar
+
Int threads = 1
Int memory = 8
+ Int picardMemory = 4
}
+ String picardPrefix = if defined(picardJar)
+ then "java -Xmx" + picardMemory + "G -jar " + picardJar
+ else "picard -Xmx" + picardMemory + "G"
+
+ # Post alt script from bwa
+ String altCommand = if (defined(bwaIndex.altIndex)) then "| bwa-postalt " + bwaIndex.altIndex else ""
+
+ # setNmMdAndUqTags is only required if alt sequences are added
+ String setNmMdAndUqTagsCommand = picardPrefix + " SetNmMdAndUqTags " +
+ " INPUT=/dev/stdin OUTPUT=" + outputPath +
+ " CREATE_INDEX=true" +
+ " R=" + bwaIndex.fastaFile
+
+ String sortSamCommand = picardPrefix + " SortSam " +
+ " INPUT=/dev/stdin SORT_ORDER=coordinate " +
+ if(defined(bwaIndex.altIndex)) then " OUTPUT=/dev/stdout "
+ else " OUTPUT=" + outputPath + " CREATE_INDEX=true "
+
+ String picardCommand = if (defined(bwaIndex.altIndex)) then sortSamCommand + " | " + setNmMdAndUqTagsCommand
+ else sortSamCommand
+
+ String readgroupArg = if (defined(readgroup)) then "-R '" + readgroup + "'" else ""
+
command {
set -e -o pipefail
mkdir -p $(dirname ~{outputPath})
~{preCommand}
bwa mem ~{"-t " + threads} \
- ~{"-R '" + readgroup + "'"} \
+ ~{readgroupArg} \
~{bwaIndex.fastaFile} \
~{inputR1} \
~{inputR2} \
- | samtools sort --output-fmt BAM - > ~{outputPath}
+ ~{altCommand} \
+ | ~{picardCommand}
}
output {
- File bamFile = outputPath
+ IndexedBamFile bamFile = object {
+ file: outputPath,
+ index: sub(outputPath, ".bam$", ".bai")
+ }
}
runtime{
cpu: threads
- memory: memory
+ memory: memory + picardMemory + picardMemory
}
}
@@ -62,8 +94,10 @@ task Index {
}
output {
- File indexedFasta = outputFile
- Array[File] indexFiles = [outputFile + ".bwt",outputFile + ".pac",outputFile + ".sa",outputFile + ".amb",outputFile + ".ann"]
+ BwaIndex outputIndex = object {
+ fastaFile: outputFile,
+ indexFiles: [outputFile + ".bwt",outputFile + ".pac",outputFile + ".sa",outputFile + ".amb",outputFile + ".ann"]
+ }
}
parameter_meta {
@@ -77,4 +111,5 @@ task Index {
struct BwaIndex {
File fastaFile
Array[File] indexFiles
+ File? altIndex
}
diff --git a/centrifuge.wdl b/centrifuge.wdl
index 4b128c33627eb4eec4facb184c4e49a321d4b4a7..6ed05eb6e55b366a78de3f6e234538ba795bf99d 100644
--- a/centrifuge.wdl
+++ b/centrifuge.wdl
@@ -101,7 +101,7 @@ task Classify {
~{true="-k" false="" defined(assignments)} ~{assignments} \
~{true="-1" false="-U" defined(read2)} ~{sep=',' read1} \
~{true="-2" false="" defined(read2)} ~{sep=',' read2} \
- ~{true="-U" false="" defined(unpairedReads)} ~{sep=',' unpairedReads} \
+ ~{true="-U" false="" length(select_first([unpairedReads])) > 0} ~{sep=',' unpairedReads} \
~{"--report-file " + reportFilePath} \
~{"--min-hitlen " + minHitLen} \
~{"--min-totallen " + minTotalLen} \
@@ -197,7 +197,7 @@ task Kreport {
String suffix = "kreport"
String prefix = "centrifuge"
String indexPrefix
- Boolean? onlyUnique
+ Boolean? onlyUnique ## removed in 1.0.4
Boolean? showZeros
Boolean? isCountTable
Int? minScore
diff --git a/common.wdl b/common.wdl
index d2198aff445a33f8e9a91deca5e67afb1f26ee3f..7bd1da697e678744c521a0432337a4e86714af7e 100644
--- a/common.wdl
+++ b/common.wdl
@@ -42,11 +42,14 @@ task ConcatenateTextFiles {
Boolean zip = false
}
+ # When input and output is both compressed decompression is not needed
+ String cmdPrefix = if (unzip && !zip) then "zcat " else "cat "
+ String cmdSuffix = if (!unzip && zip) then " | gzip -c " else ""
+
command {
set -e -o pipefail
~{"mkdir -p $(dirname " + combinedFilePath + ")"}
- ~{true='zcat' false= 'cat' unzip} ~{sep=' ' fileList} \
- ~{true="| gzip -c" false="" zip} > ~{combinedFilePath}
+ ~{cmdPrefix} ~{sep=' ' fileList} ~{cmdSuffix} > ~{combinedFilePath}
}
output {
@@ -150,3 +153,10 @@ struct IndexedBamFile {
File file
File index
}
+
+struct FastqPair {
+ File R1
+ String? R1_md5
+ File? R2
+ String? R2_md5
+}
diff --git a/gatk.wdl b/gatk.wdl
index 265d28478133b8877bc69cc29c9811f41a8463f6..5123050ab2fdbcd051739b50837d4fe8307473e8 100644
--- a/gatk.wdl
+++ b/gatk.wdl
@@ -12,7 +12,6 @@ task ApplyBQSR {
File recalibrationReport
Array[File]+ sequenceGroupInterval
Reference reference
- Int? compressionLevel
Int memory = 4
Float memoryMultiplier = 3.0
@@ -112,7 +111,6 @@ task CombineGVCFs {
Reference reference
- Int? compressionLevel #TODO This isn't being used?
Int memory = 4
Float memoryMultiplier = 3.0
}
@@ -198,7 +196,6 @@ task GenotypeGVCFs {
IndexedVcfFile? dbsnpVCF
- Int? compressionLevel
Int memory = 4
Float memoryMultiplier =3.0
}
@@ -243,7 +240,6 @@ task HaplotypeCallerGvcf {
String gvcfPath
Reference reference
Float contamination = 0.0
- Int? compressionLevel
String? gatkJar
IndexedVcfFile? dbsnpVCF
diff --git a/picard.wdl b/picard.wdl
index 9dc3709d163dc0e822b0d8fd737c4a653d58ee09..f0175ac9839dae4d22b957e2e29312d131ffaccd 100644
--- a/picard.wdl
+++ b/picard.wdl
@@ -1,5 +1,42 @@
version 1.0
+task BedToIntervalList {
+ input {
+ String? preCommand
+ File? picardJar
+
+ File bedFile
+ File dict
+ String outputPath
+
+ Int memory = 4
+ Float memoryMultiplier = 3.0
+ }
+
+ String toolCommand = if defined(picardJar)
+ then "java -Xmx" + memory + "G -jar " + picardJar
+ else "picard -Xmx" + memory + "G"
+
+ command {
+ set -e -o pipefail
+ mkdir -p $(dirname "~{outputPath}")
+ ~{preCommand}
+ ~{toolCommand} \
+ BedToIntervalList \
+ I=~{bedFile} \
+ O=~{outputPath} \
+ SD=~{dict}
+ }
+
+ output {
+ File intervalList = outputPath
+ }
+
+ runtime {
+ memory: ceil(memory * memoryMultiplier)
+ }
+}
+
task CollectMultipleMetrics {
input {
String? preCommand
diff --git a/seqtk.wdl b/seqtk.wdl
index 64c604a5ecfe0beba399605dcabb1bb3de0ee59a..662d7e29321372161308eccbe430680315ee7445 100644
--- a/seqtk.wdl
+++ b/seqtk.wdl
@@ -6,9 +6,8 @@ task Sample {
String outFilePath = "subsampledReads.fq.gz"
String? preCommand
Int? seed
- Boolean twoPassMode
- Float? fraction
- Int? number
+ Boolean twoPassMode = false
+ Float fractionOrNumber # when above 1.0 is the number of reads, otherwise it's a fraction
Boolean zip = true
}
@@ -20,8 +19,7 @@ task Sample {
~{"-s " + seed} \
~{true="-2 " false="" twoPassMode} \
~{sequenceFile} \
- ~{number} \
- ~{fraction} \
+ ~{fractionOrNumber} \
~{true="| gzip" false="" zip} \
> ~{outFilePath}
}
diff --git a/spades.wdl b/spades.wdl
index 47195f196967b8b1863b908d9c483ed49df9f978..09f4bb0af05d38d066149c4947e2d69cdf680fc6 100644
--- a/spades.wdl
+++ b/spades.wdl
@@ -32,7 +32,8 @@ task Spades {
Int? phredOffset
}
- Int clusterMemory = ceil(memoryGb / threads)
+ Int clusterMemory = ceil(memoryGb / threads * 1.2)
+ Int memoryArg = ceil(memoryGb)
command {
set -e -o pipefail
@@ -60,7 +61,7 @@ task Spades {
~{true="--disable-rr" false="" disableRepeatResolution} \
~{"--dataset " + dataset} \
~{"--threads " + threads} \
- ~{"--memory " + memoryGb} \
+ ~{"--memory " + memoryArg} \
~{"-k " + k} \
~{"--cov-cutoff " + covCutoff} \
~{"--phred-offset " + phredOffset}
diff --git a/star.wdl b/star.wdl
index e03f6301052b648f2b86cd126e5ecfd9bdd27aed..3a795c746c5177c8f1705da3b5e44ceb463dc892 100644
--- a/star.wdl
+++ b/star.wdl
@@ -20,7 +20,7 @@ task Star {
Int memory = 10
}
- #TODO needs to be extended for all possible output extensions
+ # Needs to be extended for all possible output extensions
Map[String, String] samOutputNames = {"BAM SortedByCoordinate": "sortedByCoord.out.bam"}
command {