Merge branch 'develop' into BIOWDL-499

CHANGELOG.md

@@ -12,6 +12,10 @@ that users understand how the changes affect the new version.
 version 5.0.0-dev
 ---------------------------
 + Add NanoPlot and NanoQC tasks.
++ collect-columns: updated docker image to version 1.0.0 and added the
+  `sumOnDuplicateId` input (defaults to false).
++ survivor: replace integer boolean type to logical true or false value.
++ vt: Add option to ignore masked reference.
 + bcftools: add sorting and annotation
 + Bam2fastx: Input bam and index are now arrays.
 + Lima: Remove globs from outputs.

collect-columns.wdl

@@ -29,13 +29,14 @@ task CollectColumns {
         Int? separator
         Array[String]? sampleNames
         Boolean header = false
+        Boolean sumOnDuplicateId = false
         Array[String]? additionalAttributes
         File? referenceGtf
         String? featureAttribute
 
         Int memoryGb = 4 + ceil(0.5 * length(inputTables))
         Int timeMinutes = 10
-        String dockerImage = "quay.io/biocontainers/collect-columns:0.2.0--py_1"
+        String dockerImage = "quay.io/biocontainers/collect-columns:1.0.0--py_0"
     }
 
     command {
@@ -49,6 +50,7 @@ task CollectColumns {
         ~{"-s " + separator} \
         ~{true="-n" false="" defined(sampleNames)} ~{sep=" " sampleNames} \
         ~{true="-H" false="" header} \
+        ~{true="-S" false="" sumOnDuplicateId} \
         ~{true="-a" false="" defined(additionalAttributes)} ~{sep=" " additionalAttributes} \
         ~{"-g " + referenceGtf} \
         ~{"-F " + featureAttribute}
@@ -72,6 +74,7 @@ task CollectColumns {
         separator: {description: "Equivalent to the -s option of collect-columns.", category: "advanced"}
         sampleNames: {description: "Equivalent to the -n option of collect-columns.", category: "advanced"}
         header: {description: "Equivalent to the -H flag of collect-columns.", category: "advanced"}
+        sumOnDuplicateId: {description: "Equivalent to the -S flag of collect-columns.", category: "advanced"}
         additionalAttributes: {description: "Equivalent to the -a option of collect-columns.", category: "advanced"}
         referenceGtf: {description: "Equivalent to the -g option of collect-columns.", category: "advanced"}
         featureAttribute: {description: "Equivalent to the -F option of collect-columns.", category: "advanced"}

survivor.wdl

@@ -27,9 +27,9 @@ task Merge {
         Array[File] filePaths
         Int breakpointDistance = 1000
         Int suppVecs = 2
-        Int svType = 1
-        Int strandType = 1
-        Int distanceBySvSize = 0
+        Boolean svType = true
+        Boolean strandType = true
+        Boolean distanceBySvSize = false
         Int minSize = 30
         String outputPath = "./survivor/merged.vcf"
         String memory = "24G"
@@ -45,9 +45,9 @@ task Merge {
         fileList \
         ~{breakpointDistance} \
         ~{suppVecs} \
-        ~{svType} \
-        ~{strandType} \
-        ~{distanceBySvSize} \
+        ~{true=1 false=0 svType} \
+        ~{true=1 false=0 strandType} \
+        ~{true=1 false=0 distanceBySvSize} \
         ~{minSize} \
         ~{outputPath}
     }

vt.wdl

@@ -26,6 +26,7 @@ task Normalize {
         File inputVCFIndex
         File referenceFasta
         File referenceFastaFai
+        Boolean ignoreMaskedRef = false
         String outputPath = "./vt/normalized_decomposed.vcf"
         String dockerImage = "quay.io/biocontainers/vt:0.57721--hdf88d34_2"
         String memory = "4G"
@@ -33,9 +34,12 @@ task Normalize {
     }
 
     command {
-        set -e
+        set -eo pipefail
         mkdir -p "$(dirname ~{outputPath})"
-        vt normalize ~{inputVCF} -r ~{referenceFasta} | vt decompose -s - -o ~{outputPath}
+        vt normalize ~{inputVCF} \
+        -r ~{referenceFasta} \
+        ~{true="-m " false="" ignoreMaskedRef} \
+        | vt decompose -s - -o ~{outputPath}
     }
 
     output {
@@ -55,6 +59,7 @@ task Normalize {
         outputPath: {description: "The location the output VCF file should be written.", category: "common"}
         referenceFasta: {description: "The reference fasta file which was also used for mapping.", category: "required"}
         referenceFastaFai: {description: "The index for the reference fasta file.", category: "required"}
+        ignoreMaskedRef: {description: "Warns but does not exit when REF is inconsistent with masked reference sequence for non SNPs", category: "advanced"}
         memory: {description: "The memory required to run the programs", 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"}