Merge branch 'master' into STAR_limitBAMsortRAM

LICENSE

 MIT License
 
-Copyright (c) 2018 Peter van 't Hof
+Copyright (c) Sequencing Analysis Support Core - 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

bwa.wdl

@@ -3,6 +3,7 @@ task BwaMem {
     File inputR1
     File? inputR2
     String referenceFasta
+    Array[File] indexFiles # These indexFiles need to be added, otherwise cromwell will not find them.
     String outputPath
     String? readgroup
 
@@ -26,3 +27,39 @@ task BwaMem {
         memory: if defined(memory) then memory else 8
     }
 }
+
+task index {
+    File fasta
+    String? preCommand
+    String? constructionAlgorithm
+    Int? blockSize
+    String? outputDir
+    String fastaFilename = basename(fasta)
+
+    command {
+        set -e -o pipefail
+        ${"mkdir -p " + outputDir}
+        ${preCommand}
+        if [[ ! '${outputDir}' =  '' ]]
+        then
+            ln -sf ${fasta} ${outputDir + "/"}${fastaFilename}
+        fi
+        bwa index \
+        ${"-a " + constructionAlgorithm} \
+        ${"-b" + blockSize} \
+        ${outputDir + "/"}${fastaFilename}
+    }
+
+    output {
+        File indexBase = if (defined(outputDir)) then select_first([outputDir]) + "/" + fastaFilename else fastaFilename
+        File indexedFasta = indexBase
+        Array[File] indexFiles = [indexBase + ".bwt",indexBase + ".pac",indexBase + ".sa",indexBase + ".amb",indexBase + ".ann"]
+    }
+    parameter_meta {
+        fasta: "Fasta file to be indexed"
+        constructionAlgorithm: "-a STR    BWT construction algorithm: bwtsw, is or rb2 [auto]"
+        blockSize: "-b INT    block size for the bwtsw algorithm (effective with -a bwtsw) [10000000]"
+        outputDir: "index will be created in this output directory"
+    }
+}
+

centrifuge.wdl

@@ -24,10 +24,7 @@ task download {
     command {
         set -e -o pipefail
         ${preCommand}
-        ${'if [ ! -f ' + seqTaxMapPath +
-        ' ]; then mkdir -p ' + seqTaxMapPath +
-        '; rm -d ' + seqTaxMapPath +
-        '; fi' }
+        ${"mkdir -p $(dirname " + seqTaxMapPath + ")"}
         ${executable} \
         -o ${libraryPath} \
         ${true='-d ' false='' defined(domain)}${sep=','  domain} \
@@ -92,8 +89,7 @@ task build {
     command {
         set -e -o pipefail
         ${preCommand}
-        mkdir -p  ${centrifugeIndexBase}
-        rm -d ${centrifugeIndexBase}
+        ${"mkdir -p $(dirname " + centrifugeIndexBase + ")"}
         ${centrifugeBuildExecutable} \
         ${true='--large-index' false='' largeIndex} \
         ${true='--noauto' false='' noAuto} \

common.wdl

@@ -51,12 +51,13 @@ task concatenateTextFiles {
     Array[File] fileList
     String combinedFilePath
     Boolean? unzip=false
+    Boolean? zip=false
 
     command {
-        mkdir -p ${combinedFilePath}
-        rm -d ${combinedFilePath}
+        set -e -o pipefail
+        ${"mkdir -p $(dirname " + combinedFilePath + ")"}
         ${true='zcat' false= 'cat' unzip} ${sep=' ' fileList} \
-        > ${combinedFilePath}
+        ${true="| gzip -c" false="" zip} > ${combinedFilePath}
     }
 
     output {

cutadapt.wdl

@@ -6,13 +6,13 @@ task cutadapt {
     String? format
     String? preCommand
     Int? cores = 1
-    String? memory = "4G"
-    Array[String]? adapter
-    Array[String]? front
-    Array[String]? anywhere
-    Array[String]? adapterRead2
-    Array[String]? frontRead2
-    Array[String]? anywhereRead2
+    Int? memory = 4
+    Array[String]+? adapter
+    Array[String]+? front
+    Array[String]+? anywhere
+    Array[String]+? adapterRead2
+    Array[String]+? frontRead2
+    Array[String]+? anywhereRead2
     Boolean? interleaved
     String? pairFilter
     Float? errorRate
@@ -59,7 +59,9 @@ task cutadapt {
 
     command {
         set -e -o pipefail
-        mkdir -p $(dirname ${read1output})
+        ${"mkdir -p $(dirname " + read1output + ")"}
+        ${"mkdir -p $(dirname " + read2output + ")"}
+        ${"mkdir -p $(dirname " + reportPath + ")"}
         ${preCommand}
         cutadapt \
         ${"--cores=" + cores} \
@@ -120,4 +122,4 @@ task cutadapt {
         cpu: select_first([cores])
         memory: select_first([memory])
     }
-}
\ No newline at end of file
+}

fastqc.wdl

@@ -15,7 +15,11 @@ task fastqc {
     File? limits
     Int? kmers
     String? dir
-
+    # Chops of the .gz extension if present.
+    String name = sub(seqFile, "\\.gz$","")
+    # This regex chops of the extension and replaces it with _fastqc for the reportdir.
+    # Just as fastqc does it.
+    String reportDir = outdirPath + "/" + sub(basename(name), "\\.[^\\.]*$", "_fastqc")
     command {
     set -e -o pipefail
     ${preCommand}
@@ -40,10 +44,10 @@ task fastqc {
     }
 
     output {
-        File rawReport = select_first(glob(outdirPath + "/*/fastqc_data.txt"))
-        File htmlReport = select_first(glob(outdirPath + "/*/fastqc_report.html"))
-        File summary = select_first(glob(outdirPath + "/*/summary.txt"))
-        Array[File] images = glob(outdirPath + "/*/Images/*.png")
+        File rawReport = reportDir + "/fastqc_data.txt"
+        File htmlReport = reportDir + "/fastqc_report.html"
+        File summary = reportDir + "/summary.txt"
+        Array[File] images = glob(reportDir + "/Images/*.png")
     }
 
     runtime {
@@ -113,4 +117,4 @@ task getConfiguration {
     runtime {
         memory: 1
     }
-}
\ No newline at end of file
+}

samtools.wdl

@@ -65,3 +65,55 @@ task Flagstat {
         File flagstat = outputPath
     }
 }
+
+task fastq {
+    String? preCommand
+    File inputBam
+    String outputRead1
+    String? outputRead2
+    String? outputRead0
+    Int? includeFilter
+    Int? excludeFilter
+    Int? excludeSpecificFilter
+    Boolean? appendReadNumber
+    Boolean? outputQuality
+    Int? compressionLevel
+    Int? threads
+    Int? memory
+    Int totalThreads = select_first([threads, 1])
+
+    command {
+        ${preCommand}
+        samtools fastq \
+        ${true="-1" false="-s" defined(outputRead2)} ${outputRead1} \
+        ${"-2 " + outputRead2} \
+        ${"-0 " + outputRead0} \
+        ${"-f " + includeFilter} \
+        ${"-F " + excludeFilter} \
+        ${"-G " + excludeSpecificFilter} \
+        ${true="-N" false="-n" appendReadNumber} \
+        ${true="-O" false="" outputQuality} \
+        ${"-c " + compressionLevel} \
+        ${"--threads " + totalThreads} \
+        ${inputBam}
+    }
+    output {
+        File read1 = outputRead1
+        File? read2 = outputRead2
+        File? read0 = outputRead0
+    }
+    runtime {
+        cpu: totalThreads
+        memory: select_first([memory, 1])
+    }
+    parameter_meta {
+        preCommand: "A command that is run before the task. Can be used to activate environments"
+        inputBam: "The bam file to process."
+        outputRead1: "If only outputRead1 is given '-s' flag is assumed. Else '-1'."
+        includeFilter: "Include reads with ALL of these flags. Corresponds to '-f'"
+        excludeFilter: "Exclude reads with ONE OR MORE of these flags. Corresponds to '-F'"
+        excludeSpecificFilter: "Exclude reads with ALL of these flags. Corresponds to '-G'"
+        appendReadNumber: "Append /1 and /2 to the read name, or don't. Corresponds to '-n/N"
+
+    }
+}

seqtk.wdl

+task sample {
+    File sequenceFile
+    String? outFilePath = "subsampledReads.fq.gz"
+    String? preCommand
+    Int? seed
+    Boolean? twoPassMode
+    Float? fraction
+    Int? number
+    Boolean? zip = true
+
+    command {
+    set -e -o pipefail
+    ${'mkdir -p $(dirname ' + outFilePath + ')'}
+    ${preCommand}
+    seqtk sample \
+    ${"-s " + seed} \
+    ${true="-2 " false="" twoPassMode} \
+    ${sequenceFile} \
+    ${number} ${fraction} \
+    ${true="| gzip" false="" zip} \
+    ${"> " + outFilePath}
+    }
+    output {
+        File subsampledReads= select_first([outFilePath])
+    }
+}
\ No newline at end of file

spades.wdl

+task spades {
+    String outputDir
+    String? preCommand
+    File read1
+    File? read2
+    File? interlacedReads
+    File? sangerReads
+    File? pacbioReads
+    File? nanoporeReads
+    File? tslrContigs
+    File? trustedContigs
+    File? untrustedContigs
+    Boolean? singleCell
+    Boolean? metagenomic
+    Boolean? rna
+    Boolean? plasmid
+    Boolean? ionTorrent
+    Boolean? onlyErrorCorrection
+    Boolean? onlyAssembler
+    Boolean? careful
+    Boolean? disableGzipOutput
+    Boolean? disableRepeatResolution
+    File? dataset
+    Int? threads
+    Int? memoryGb
+    File? tmpDir
+    String? k
+    Float? covCutoff
+    Int? phredOffset
+    Int finalThreads = select_first([threads,1])
+    Int totalMemory = select_first([memoryGb, finalThreads * 16])
+    Int clusterMemory = totalMemory / finalThreads
+
+    command {
+        set -e -o pipefail
+        ${preCommand}
+        spades.py \
+        ${"-o " + outputDir} \
+        ${true="--sc" false="" singleCell} \
+        ${true="--meta" false="" metagenomic} \
+        ${true="--rna" false="" rna} \
+        ${true="--plasmid" false="" plasmid} \
+        ${true="--iontorrent" false="" ionTorrent} \
+        ${"--12 " + interlacedReads } \
+        ${true="-1" false="-s" defined(read2)} ${read1}  \
+        ${"-2 " + read2 } \
+        ${"--sanger " + sangerReads } \
+        ${"--pacbio " + pacbioReads } \
+        ${"--nanopore " + nanoporeReads } \
+        ${"--tslr " + tslrContigs } \
+        ${"--trusted-contigs " + trustedContigs } \
+        ${"--untrusted-contigs " + untrustedContigs } \
+        ${true="--only-error-correction" false="" onlyErrorCorrection } \
+        ${true="--only-assembler" false="" onlyAssembler } \
+        ${true="--careful" false="" careful } \
+        ${true="--disable-gzip-output" false="" disableGzipOutput} \
+        ${true="--disable-rr" false="" disableRepeatResolution } \
+        ${"--dataset " + dataset } \
+        ${"--threads " + finalThreads} \
+        ${"--memory " + totalMemory } \
+        ${"-k " + k } \
+        ${"--cov-cutoff " + covCutoff } \
+        ${"--phred-offset " + phredOffset }
+    }
+    output {
+        Array[File] correctedReads = glob(outputDir + "/corrected/*.fastq*")
+        File scaffolds = outputDir + "/scaffolds.fasta"
+        File contigs = outputDir + "/contigs.fasta"
+        File assemblyGraphWithScaffoldsGfa = outputDir + "/assembly_graph_with_scaffolds.gfa"
+        File assemblyGraphFastg = outputDir + "/assembly_graph.fastg"
+        File contigsPaths = outputDir + "/contigs.paths"
+        File scaffoldsPaths = outputDir + "/scaffolds.paths"
+        File params = outputDir + "/params.txt"
+        File log = outputDir + "/spades.log"
+    }
+    runtime {
+        cpu: finalThreads
+        memory: clusterMemory
+    }
+}
\ No newline at end of file

unicycler.wdl

+task unicycler {
+    String? preCommand
+    File? short1
+    File? short2
+    File? unpaired
+    File? long
+    String out
+    Int? verbosity
+    Int? minFastaLength
+    Int? keep
+    Boolean? vcf
+    Int? threads
+    Int? memory
+    Int finalThreads = select_first(threads, 1)
+    Int finalMemory = select_first(memory, 4)
+    String? mode
+    Float? minBridgeQual
+    Int? linearSeqs
+    File? spadesPath
+    Boolean? noCorrect
+    Float? minKmerFrac
+    Float? maxKmerFrac
+    Int? kmerCount
+    Float? depthFilter
+    Boolean? noMiniasm
+    File? raconPath
+    File? existingLongReadAssembly
+    Boolean? noRotate
+    File? startGenes
+    Float? startGeneId
+    Float? startGeneCov
+    String? makeblastdbPath
+    File? tblastnPath
+    Boolean? noPilon
+    File? bowtie2Path
+    File? bowtie2buildPath
+    File? samtoolsPath
+    File? pilonPath
+    File? javaPath
+    Int? minPolishSize
+    File? bcftoolsPath
+    Int? minComponentSize
+    Int? minDeadEndSize
+    File? contamination
+    String? scores
+    String? lowScore
+    command {
+        set -e -o pipefail
+        mkdir -p ${out}
+        ${preCommand}
+        unicycler \
+        ${"--short1 " + short1} \
+        ${"--short2 " + short2} \
+        ${"--unpaired " + unpaired} \
+        ${"--long " + long} \
+        --out ${out} \
+        ${"--min_fasta_length " + minFastaLength} \
+        ${"--keep " + keep } \
+        ${true="--vcf" false="" vcf } \
+        ${"--threads " + finalThreads } \
+        ${"--mode " + mode } \
+        ${"--min_bridge_qual " + minBridgeQual } \
+        ${"--linear_seqs " + linearSeqs } \
+        ${"--spades_path " + spadesPath } \
+        ${true="--no_correct" false="" noCorrect } \
+        ${"--min_kmer_frac " + minKmerFrac } \
+        ${"--max_kmer_frac " + maxKmerFrac } \
+        ${"--kmer_count " + kmerCount } \
+        ${"--depth_filter " + depthFilter } \
+        ${true="--no_miniasm" false="" noMiniasm } \
+        ${"--racon_path " + raconPath } \
+        ${"--existing_long_read_assembly " + existingLongReadAssembly } \
+        ${true="--no_rotate" false="" noRotate } \
+        ${"--start_genes " + startGenes } \
+        ${"--start_gene_id " + startGeneId } \
+        ${"--start_gene_cov " + startGeneCov } \
+        ${"--makeblastdb_path " + makeblastdbPath } \
+        ${"--tblastn_path " + tblastnPath } \
+        ${true="--no_pilon" false="" noPilon } \
+        ${"--bowtie2_path " + bowtie2Path } \
+        ${"--bowtie2_build_path " + bowtie2buildPath } \
+        ${"--samtools_path " + samtoolsPath } \
+        ${"--pilon_path " + pilonPath } \
+        ${"--java_path " + javaPath } \
+        ${"--min_polish_size " + minPolishSize } \
+        ${"--bcftools_path " + bcftoolsPath } \
+        ${"--min_component_size " + minComponentSize } \
+        ${"--min_dead_end_size " + minDeadEndSize } \
+        ${"--contamination " + contamination } \
+        ${"--scores " + scores } \
+        ${"--low_score " + lowScore }
+    }
+    output {
+        File assemblyFasta = out + "/assembly.fasta"
+        File assemblyGfa = out + "/assembly.gfa"
+        File log = out + "/unicycler.log"
+    }
+    runtime {
+        cpu: finalThreads
+        memory: finalMemory
+    }
+}
\ No newline at end of file