Merge pull request #116 from biowdl/add_sv_tasks

Add sv tasks

CHANGELOG.md

@@ -11,6 +11,13 @@ that users understand how the changes affect the new version.
 
 version 2.2.0-dev
 ---------------------------
++ Update WDL task Picard (Add task RenameSample)
++ Update WDL task Samtools (Add task FilterShortReadsBam)
++ Add WDL task for BCFtools (bcf to vcf)
++ Add WDL task for SURVIVOR (merge)
++ Update WDL task Manta (Add germline SV calling)
++ Add WDL task for Delly
++ Add WDL task for Clever (and Mate-Clever)
 + Add proper copyright headers to all WDL files. So the free software license
   is clear to end users who wish to adapt and modify.
 + Add pedigree input for HaplotypeCaller and GenotypeGVCFs.

CPAT.wdl

@@ -73,4 +73,4 @@ task CPAT {
 }
 
 # There is also make_hexamer_tab.py and make_logitModel.py
-# that can be added as tasks here.
\ No newline at end of file
+# that can be added as tasks here.

bcftools.wdl

+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task Bcf2Vcf {
+    input {
+        File bcf
+        String outputPath = "./bcftools/SV.vcf"
+        String dockerImage = "quay.io/biocontainers/bcftools:1.9--ha228f0b_3"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        bcftools view ~{bcf} -O v -o ~{outputPath}
+    }
+
+    output {
+        File outputVcf = outputPath
+    }
+
+    runtime {
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        bcf: {description: "The generated BCF from an SV caller", category: "required"}
+        outputPath: {description: "The location the output VCF file should be written.", 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"}
+    }
+}

clever.wdl

+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import "bwa.wdl"
+
+task Mateclever {
+    input {
+        File fiteredBam
+        File indexedFiteredBam
+        BwaIndex bwaIndex
+        File predictions
+        String outputPath = "./clever"
+        Int cleverMaxDelLength = 100000
+        Int maxLengthDiff= 30
+        Int maxOffset = 150
+
+        Int threads = 10
+        String memory = "15G"
+        String dockerImage = "quay.io/biocontainers/clever-toolkit:2.4--py36hcfe0e84_6"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        echo ~{outputPath} ~{fiteredBam} ~{predictions} none > predictions.list
+        mateclever \
+        -T ~{threads} \
+        -k \
+        -f \
+        -M ~{cleverMaxDelLength} \
+        -z ~{maxLengthDiff} \
+        -o ~{maxOffset} \
+        ~{bwaIndex.fastaFile} \
+        predictions.list \
+        ~{outputPath}
+    }
+
+    output {
+        File matecleverVcf = outputPath + "/deletions.vcf"
+    }
+
+    runtime {
+        cpu: threads
+        memory: memory
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        fiteredBam: {description: "The bam file where sequences less than 30bp were removed.", category: "required"}
+        indexedFiteredBam: {description: "The index of the filtered bam file.", category: "required"}
+        bwaIndex: {description: "The BWA index files.", category: "required"}
+        predictions: {description: "The predicted deletions (VCF) from clever.", category: "required"}
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        threads: {description: "The the number of threads required to run a program", category: "advanced"}
+        memory: {description: "The memory required to run the programs", category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+    }
+}
+
+task Prediction {
+    input {
+        File bamFile
+        File bamIndex
+        BwaIndex bwaIndex
+        String outputPath = "./clever"
+
+        Int threads = 10
+        String memory = "15G"
+        String dockerImage = "quay.io/biocontainers/clever-toolkit:2.4--py36hcfe0e84_6"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        clever \
+        -T ~{threads} \
+        --use_mapq \
+        --sorted \
+        -f \
+        ~{bamFile} \
+        ~{bwaIndex.fastaFile} \
+        ~{outputPath}
+    }
+
+    output {
+        File predictions = outputPath + "/predictions.vcf"
+    }
+
+    runtime {
+        cpu: threads
+        memory: memory
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        bamFile: {description: "The bam file to process.", category: "required"}
+        bamIndex: {description: "The index bam file.", category: "required"}
+        bwaIndex: {description: "The BWA index files.", category: "required"}
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        threads: {description: "The the number of threads required to run a program", category: "advanced"}
+        memory: {description: "The memory required to run the programs", 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"}
+
+        # outputs
+        predictions: {description: "The predicted deletions (VCF) from clever.", category: "advanced"}
+    }
+}

delly.wdl

+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task CallSV {
+    input {
+        File bamFile
+        File bamIndex
+        File referenceFasta
+        File referenceFastaFai
+        String outputPath = "./delly/delly.vcf"
+
+        String memory = "15G"
+        String dockerImage = "quay.io/biocontainers/delly:0.8.1--h4037b6b_1"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        delly call \
+        -o ~{outputPath} \
+        -g ~{referenceFasta} \
+        ~{bamFile}
+    }
+
+    output {
+        File dellyBcf = outputPath
+    }
+
+    runtime {
+        memory: memory
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        bamFile: {description: "The bam file to process.", category: "required"}
+        bamIndex: {description: "The index bam file.", category: "required"}
+        referenceFasta: {description: "The reference fasta file also used for mapping.", category: "required"}
+        referenceFastaFai: {description: "Fasta index (.fai) file of the reference", category: "required" }
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        memory: {description: "The memory required to run the programs", 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"}
+    }
+}

manta.wdl

@@ -20,7 +20,63 @@ version 1.0
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
-import "common.wdl"
+task Germline {
+    input {
+        File bamFile
+        File bamIndex
+        File referenceFasta
+        File referenceFastaFai
+        String runDir = "./manta_run"
+        File? callRegions
+        File? callRegionsIndex
+        Boolean exome = false
+
+        Int cores = 1
+        Int memoryGb = 4
+        String dockerImage = "quay.io/biocontainers/manta:1.4.0--py27_1"
+    }
+
+    command {
+        set -e
+        configManta.py \
+        ~{"--normalBam " + bamFile} \
+        --referenceFasta ~{referenceFasta} \
+        ~{"--callRegions " + callRegions} \
+        --runDir ~{runDir} \
+        ~{true="--exome" false="" exome}
+
+        ~{runDir}/runWorkflow.py \
+        -m local \
+        -j ~{cores} \
+        -g ~{memoryGb}
+    }
+
+    output {
+        File mantaVCF = runDir + "/results/variants/diploidSV.vcf.gz"
+        File mantaVCFindex = runDir + "/results/variants/diploidSV.vcf.gz.tbi"
+    }
+
+    runtime {
+        cpu: cores
+        memory: "~{memoryGb}G"
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        bamFile: {description: "The bam file to process.", category: "required"}
+        bamIndex: {description: "The index bam file.", category: "required"}
+        referenceFasta: {description: "The reference fasta file also used for mapping.", category: "required"}
+        referenceFastaFai: {description: "Fasta index (.fai) file of the reference", category: "required" }
+        runDir: {description: "The directory to use as run/output directory.", category: "common"}
+        callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
+        callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
+        exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
+        cores: {description: "The the number of cores required to run a program", category: "required"}
+        memoryGb: {description: "The memory required to run the manta", category: "required"}
+        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"}
+    }
+}
 
 task Somatic {
     input {
@@ -87,10 +143,8 @@ task Somatic {
         callRegions: {description: "The bed file which indicates the regions to operate on.", category: "common"}
         callRegionsIndex: {description: "The index of the bed file which indicates the regions to operate on.", category: "common"}
         exome: {description: "Whether or not the data is from exome sequencing.", category: "common"}
-
         cores: {description: "The number of cores to use.", category: "advanced"}
         memoryGb: {description: "The amount of memory this job will use in Gigabytes.", 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"}
+        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"}
     }
 }

picard.wdl

@@ -51,6 +51,7 @@ task BedToIntervalList {
     }
 
     parameter_meta {
+        # inputs
         bedFile: {description: "A bed file.", category: "required"}
         dict: {description: "A sequence dict file.", category: "required"}
         outputPath: {description: "The location the output interval list should be written to.",
@@ -156,6 +157,7 @@ task CollectMultipleMetrics {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The input BAM file for which metrics will be collected.",
                    category: "required"}
         inputBamIndex: {description: "The index of the input BAM file.", category: "required"}
@@ -227,6 +229,7 @@ task CollectRnaSeqMetrics {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The input BAM file for which metrics will be collected.",
                    category: "required"}
         inputBamIndex: {description: "The index of the input BAM file.", category: "required"}
@@ -286,6 +289,7 @@ task CollectTargetedPcrMetrics {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The input BAM file for which metrics will be collected.",
                    category: "required"}
         inputBamIndex: {description: "The index of the input BAM file.", category: "required"}
@@ -344,6 +348,7 @@ task GatherBamFiles {
     }
 
     parameter_meta {
+        # inputs
         inputBams: {description: "The BAM files to be merged together.", category: "required"}
         inputBamsIndex: {description: "The indexes of the input BAM files.", category: "required"}
         outputBamPath: {description: "The path where the merged BAM file will be written.", caregory: "required"}
@@ -386,6 +391,7 @@ task GatherVcfs {
     }
 
     parameter_meta {
+        # inputs
         inputVcfs: {description: "The VCF files to be merged together.", category: "required"}
         inputVcfIndexes: {description: "The indexes of the input VCF files.", category: "required"}
         outputVcfPath: {description: "The path where the merged VCF file will be written.", caregory: "required"}
@@ -452,6 +458,7 @@ task MarkDuplicates {
     }
 
     parameter_meta {
+        # inputs
         inputBams: {description: "The BAM files for which the duplicate reads should be marked.", category: "required"}
         inputBamIndexes: {description: "Th eindexes for the input BAM files.", category: "required"}
         outputBamPath: {description: "The location where the ouptut BAM file should be written.", category: "required"}
@@ -501,6 +508,7 @@ task MergeVCFs {
     }
 
     parameter_meta {
+        # inputs
         inputVCFs: {description: "The VCF files to be merged.", category: "required"}
         inputVCFsIndexes: {description: "The indexes of the VCF files.", category: "required"}
         outputVcfPath: {description: "The location the output VCF file should be written to.", category: "required"}
@@ -618,6 +626,7 @@ task SortVcf {
     }
 
     parameter_meta {
+        # inputs
         vcfFiles: {description: "The VCF files to merge and sort.", category: "required"}
         outputVcfPath: {description: "The location the sorted VCF files should be written to.", category: "required"}
         dict: {description: "A sequence dictionary matching the VCF files.", category: "advanced"}
@@ -628,4 +637,44 @@ task SortVcf {
         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"}
     }
-}
\ No newline at end of file
+}
+
+task RenameSample {
+    input {
+        File inputVcf
+        String outputPath = "./picard/renamed.vcf"
+        String newSampleName
+        String memory = "24G"
+        String javaXmx = "8G"
+        String dockerImage = "quay.io/biocontainers/picard:2.19.0--0"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        picard -Xmx~{javaXmx} \
+        RenameSampleInVcf \
+        I=~{inputVcf} \
+        O=~{outputPath} \
+        NEW_SAMPLE_NAME=~{newSampleName}
+    }
+
+    output {
+        File renamedVcf = outputPath
+    }
+
+    runtime {
+        docker: dockerImage
+        memory: memory
+    }
+
+    parameter_meta {
+        # inputs
+        inputVcf: {description: "The VCF file to process.", category: "required"}
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        newSampleName: {description: "A string to replace the old sample name.", category: "required"}
+        memory: {description: "The memory required to run the programs", category: "advanced"}
+        javaXmx: {description: "The max. memory allocated for JAVA", 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"}
+    }
+}

samtools.wdl

@@ -48,6 +48,7 @@ task BgzipAndIndex {
     }
 
     parameter_meta {
+        # inputs
         inputFile: {description: "The file to be compressed and indexed.", category: "required"}
         outputDir: {description: "The directory in which the output will be placed.", category: "required"}
         type: {description: "The type of file (eg. vcf or bed) to be compressed and indexed.", category: "common"}
@@ -90,6 +91,7 @@ task Index {
     }
 
     parameter_meta {
+        # inputs
         bamFile: {description: "The BAM file for which an index should be made.", category: "required"}
         outputBamPath: {description: "The location where the BAM file should be written to. The index will appear alongside this link to the BAM file.",
                         category: "common"}
@@ -125,6 +127,7 @@ task Merge {
     }
 
     parameter_meta {
+        # inputs
         bamFiles: {description: "The BAM files to merge.", category: "required"}
         outputBamPath: {description: "The location the merged BAM file should be written to.", category: "common"}
         force: {description: "Equivalent to samtools merge's `-f` flag.", category: "advanced"}
@@ -156,6 +159,7 @@ task SortByName {
     }
 
     parameter_meta {
+        # inputs
         bamFile: {description: "The BAM file to get sorted.", category: "required"}
         outputBamPath: {description: "The location the sorted BAM file should be written to.", 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.",
@@ -186,6 +190,7 @@ task Markdup {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The BAM file to be processed.", category: "required"}
         outputBamPath: {description: "The location of the output BAM file.", category: "required"}
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
@@ -216,6 +221,7 @@ task Flagstat {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The BAM file for which statistics should be retrieved.", category: "required"}
         outputPath: {description: "The location the ouput should be written to.", category: "required"}
         dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
@@ -232,8 +238,8 @@ task Fastq {
         Int? includeFilter
         Int? excludeFilter
         Int? excludeSpecificFilter
-        Boolean? appendReadNumber
-        Boolean? outputQuality
+        Boolean appendReadNumber = false
+        Boolean outputQuality = false
         Int? compressionLevel
 
         Int threads = 1
@@ -269,6 +275,7 @@ task Fastq {
     }
 
     parameter_meta {
+        # inputs
         inputBam: {description: "The bam file to process.", category: "required"}
         outputRead1: {description: "The location the reads (first reads for pairs, in case of paired-end sequencing) should be written to.", category: "required"}
         outputRead2: {description: "The location the second reads from pairs should be written to.", category: "common"}
@@ -313,6 +320,7 @@ task Tabix {
     }
 
     parameter_meta {
+        # inputs
         inputFile: {description: "The file to be indexed.", category: "required"}
         outputFilePath: {description: "The location where the file should be written to. The index will appear alongside this link to the file.",
                         category: "common"}
@@ -327,7 +335,9 @@ task View {
         File inFile
         File? referenceFasta
         String outputFileName = "view.bam"
-        Boolean? uncompressedBamOutput
+        Boolean includeHeader = false
+        Boolean outputBam = false
+        Boolean uncompressedBamOutput = false
         Int? includeFilter
         Int? excludeFilter
         Int? excludeSpecificFilter
@@ -346,6 +356,7 @@ task View {
         samtools view -b \
         ~{"-T " + referenceFasta} \
         ~{"-o " + outputFileName} \
+        ~{true="-b " false="" outputBam} \
         ~{true="-u " false="" uncompressedBamOutput} \
         ~{"-f " + includeFilter} \
         ~{"-F " + excludeFilter} \
@@ -357,7 +368,7 @@ task View {
     }
 
     output {
-        File outputBam = outputFileName
+        File outputBAM = outputFileName
         File outputBamIndex = outputIndexPath
     }
 
@@ -368,6 +379,7 @@ task View {
     }
 
     parameter_meta {
+        # inputs
         inFile: {description: "A BAM, SAM or CRAM file.", category: "required"}
         referenceFasta: {description: "The reference fasta file also used for mapping.", category: "advanced"}
         outputFileName: {description: "The location the output BAM file should be written.", category: "common"}
@@ -383,3 +395,37 @@ task View {
                       category: "advanced"}
     }
 }
+
+task FilterShortReadsBam {
+    input {
+        File bamFile
+        String outputPathBam
+        String dockerImage = "quay.io/biocontainers/samtools:1.8--h46bd0b3_5"
+    }
+    
+    String outputPathBamIndex = sub(outputPathBam, "\.bam$", ".bai")
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPathBam})"
+        samtools view -h ~{bamFile} | \
+        awk 'length($10) > 30 || $1 ~/^@/' | \
+        samtools view -bS -> ~{outputPathBam}
+        samtools index ~{outputPathBam} ~{outputPathBamIndex}
+    }
+
+    output {
+        File filteredBam = outputPathBam
+        File filteredBamIndex = outputPathBamIndex
+    }
+
+    runtime {
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        bamFile: {description: "The bam file to process.", category: "required"}
+        outputPathBam: {description: "The filtered bam 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"}
+    }
+}

survivor.wdl

+version 1.0
+
+# MIT License
+#
+# Copyright (c) 2018 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task Merge {
+    input{
+        Array[File] filePaths
+        Int breakpointDistance = 1000
+        Int suppVecs = 2
+        Int svType = 1
+        Int strandType = 1
+        Int distanceBySvSize = 0
+        Int minSize = 30
+        String outputPath = "./survivor/merged.vcf"
+        String memory = "24G"
+        String dockerImage = "quay.io/biocontainers/survivor:1.0.6--h6bb024c_0"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPath})"
+        echo '~{sep="\n" filePaths}' > fileList
+        SURVIVOR merge \
+        fileList \
+        ~{breakpointDistance} \
+        ~{suppVecs} \
+        ~{svType} \
+        ~{strandType} \
+        ~{distanceBySvSize} \
+        ~{minSize} \
+        ~{outputPath}
+    }
+
+    output {
+        File mergedVcf = outputPath
+    }
+
+    runtime {
+        memory: memory
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        filePaths: {description: "An array of VCF files (predictions) to be merged by SURVIVOR", category: "required"}
+        breakpointDistance: {description: "The distance between pairwise breakpoints between SVs", category: "advanced"}
+        suppVecs: {description: "The minimum number of SV callers to support the merging", category: "advanced"}
+        svType: {description: "A boolean to include the type SV to be merged", category: "advanced"}
+        strandType: {description: "A boolean to include strand type of an SV to be merged", category: "advanced"}
+        distanceBySvSize: {description: "A boolean to predict the pairwise distance between the SVs based on their size", category: "advanced"}
+        minSize: {description: "The mimimum size of SV to be merged", category: "advanced"}
+        outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+        memory: {description: "The memory required to run the programs", 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"}
+    }
+}