Merge pull request #173 from biowdl/BIOWDL-387

Add bedtools intersect and text to file task.

CHANGELOG.md

@@ -11,6 +11,10 @@ that users understand how the changes affect the new version.
 
 version 2.2.0-dev
 ---------------------------
++ Add common.TextToFile task.
++ Add bedtools.Intersect.
++ Add `-o pipefail` to bedtools.MergeBedFiles to prevent errors in BED files 
+  from going unnoticed.
 + Centrifuge: Fix -1/-U options for single end data.
 + Add bedtools.Complement, bedtools.Merge, and add a task to combine multiple
   bed files called bedtools.MergeBedFiles. This task combines bedtools merge 

bedtools.wdl

@@ -102,6 +102,7 @@ task MergeBedFiles {
 
     # A sorted bed is needed for bedtools merge
     command {
+        set -e -o pipefail
         cat ~{sep=" " bedFiles} | bedtools sort | bedtools merge > ~{outputBed}
     }
 
@@ -163,3 +164,49 @@ task Sort {
         docker: dockerImage
     }
 }
+
+task Intersect {
+    input {
+        File regionsA
+        File regionsB
+        # Giving a faidx file will set the sorted option.
+        File? faidx
+        String outputBed = "intersect.bed"
+        String dockerImage = "quay.io/biocontainers/bedtools:2.23.0--hdbcaa40_3"
+    }
+    Boolean sorted = defined(faidx)
+
+    command {
+        set -e
+        ~{"cut -f1,2 " + faidx} ~{true="> sorted.genome" false ="" sorted}
+        bedtools intersect \
+        -a ~{regionsA} \
+        -b ~{regionsB} \
+        ~{true="-sorted" false="" sorted} \
+        ~{true="-g sorted.genome" false="" sorted} \
+        > ~{outputBed}
+    }
+
+    output {
+        File intersectedBed = outputBed
+    }
+
+    runtime {
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        faidx: {description: "The fasta index (.fai) file that is used to create the genome file required for sorted output. Implies sorted option.",
+                category: "common"}
+        regionsA: {description: "Region file a to intersect",
+                   category: "required"}
+        regionsB: {description: "Region file b to intersect",
+                   category: "required"}
+        outputBed: {description: "The path to write the output to",
+                    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"
+        }
+    }
+}

common.wdl

@@ -158,6 +158,34 @@ task StringArrayMd5 {
     }
 }
 
+task TextToFile {
+
+    input {
+        String text
+        String outputFile = "out.txt"
+        String dockerImage = "debian@sha256:f05c05a218b7a4a5fe979045b1c8e2a9ec3524e5611ebfdd0ef5b8040f9008fa"
+    }
+
+    command <<<
+        echo $'~{text}' > ~{outputFile}
+    >>>
+
+    output {
+        File out = outputFile
+    }
+
+    parameter_meta {
+        text: {description: "The text to print", category: "required"}
+        outputFile: {description: "The name of the output file", 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"}
+    }
+    runtime {
+        memory: "1G"
+        docker: dockerImage
+    }
+}
+
 task YamlToJson {
     input {
         File yaml

gatk.wdl

@@ -342,8 +342,10 @@ task HaplotypeCallerGvcf {
     parameter_meta {
         inputBams: {description: "The BAM files on which to perform variant calling.", category: "required"}
         inputBamsIndex: {description: "The indexes for the input BAM files.", category: "required"}
-        intervalList: {description: "Bed files or interval lists describing the regions to operate on.", category: "required"}
+        intervalList: {description: "Bed files or interval lists describing the regions to operate on.", category: "common"}
+        excludeIntervalList: {description: "Bed files or interval lists describing the regions to NOT operate on.", category: "common"}
         gvcfPath: {description: "The location to write the output GVCF to.", category: "required"}
+        ploidy: {description: "The ploidy with which the variants should be called.", category: "common"}
         referenceFasta: {description: "The reference fasta file which was also used for mapping.",
                          category: "required"}
         referenceFastaDict: {description: "The sequence dictionary associated with the reference fasta file.",