Merge remote-tracking branch 'origin/develop' into update_CPAT

8c7f9978 · Cats · 47c89884 · c1a647aa · 8c7f9978 · 8c7f9978
Commit 8c7f9978 authored 3 years ago by Cats
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,14 +12,27 @@ version 5.0.0-dev
 ---------------------------
 + Update CPAT to version 3.0.4.
  + Changed the `outFilePath` input to `outputPrefix`.
+ Survivor: Change integer to string literal in boolean parameters.
+ Samtools: Add mkdir line to `Fastq` task.
+ Add new parameters from CCS version 6.0.0 and add two new outputs:
+  `ccs_report.txt` & `zmw_metrics.json.gz`.
+ Change CutAdapt memory to `5G`.
+ Increase multiqc base time from 5 to 10.
+ Update biowdl-input-converter to version 0.3.
+ Update minimap2 to version 2.20.
+ Update lima to version 2.2.0.
+ Update ccs to version 6.0.0.
+ Update bam2fastx to version 1.3.1.
+ Add memory values to GffCompare, GffRead and CPAT.
 + GffCompare: Make the `referenceAnnotation` input optional.
 + Stringtie: Add the `minimumCoverage` input.
-+ UMI-tools: update default dockerImage to use umitools v1.1.1 with correct samtools version (1.10)
-+ UMI-tools: re-introduce samtools indexing
-+ UMI-tools: update default dockerImage to use umitools v1.1.1
-+ UMI-tools dedup: Add tempdir
-+ Update BCFTOOLS view: add options for filtering (include, exclude, excludeUncalled).
-+ Duphold: add duphold.wdl.
+ UMI-tools: Update default dockerImage to use umitools v1.1.1 with correct
+             samtools version (1.10).
+ UMI-tools: Re-introduce samtools indexing.
+ UMI-tools: Update default dockerImage to use umitools v1.1.1.
+ UMI-tools dedup: Add tempdir.
+ Bcftools view: Add options for filtering (include, exclude, excludeUncalled).
+ Duphold: Add `duphold.wdl`.
 + Add new wdl file prepareShiny.wdl for creating input files for shiny app.
 + mergePacBio: Rename `mergedReport` to `outputPathMergedReport`.
 + Lima: Fix copy commands.

--- a/CPAT.wdl
+++ b/CPAT.wdl
@@ -34,6 +34,7 @@ task CPAT {
        Array[String]? startCodons
        Array[String]? stopCodons

+        String memory = "4G"
        Int timeMinutes = 10 + ceil(size(gene, "G") * 30)
        String dockerImage = "biocontainers/cpat:3.0.4--py39hcbe4a3b_0"
    }
@@ -64,8 +65,9 @@ task CPAT {
    }

    runtime {
-        docker: dockerImage
+        memory: memory
        time_minutes: timeMinutes
+        docker: dockerImage
    }

    parameter_meta {
@@ -78,6 +80,7 @@ task CPAT {
        referenceGenomeIndex: {description: "The index of the reference. Should be added as input if CPAT should not index the reference genome.", category: "advanced"}
        startCodons: {description: "Equivalent to CPAT's `--start` option.", category: "advanced"}
        stopCodons: {description: "Equivalent to CPAT's `--stop` option.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", 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"}
    }

--- a/bam2fastx.wdl
+++ b/bam2fastx.wdl
@@ -32,7 +32,7 @@ task Bam2Fasta {

        String memory = "2G"
        Int timeMinutes = 15
-        String dockerImage = "quay.io/biocontainers/bam2fastx:1.3.0--he1c1bb9_8"
+        String dockerImage = "quay.io/biocontainers/bam2fastx:1.3.1--hf05d43a_1"
    }

    command {
@@ -100,7 +100,7 @@ task Bam2Fastq {

        String memory = "2G"
        Int timeMinutes = 15
-        String dockerImage = "quay.io/biocontainers/bam2fastx:1.3.0--he1c1bb9_8"
+        String dockerImage = "quay.io/biocontainers/bam2fastx:1.3.1--hf05d43a_1"
    }

    command {

--- a/biowdl.wdl
+++ b/biowdl.wdl
@@ -34,7 +34,7 @@ task InputConverter {

        String memory = "128M"
        Int timeMinutes = 1
-        String dockerImage = "quay.io/biocontainers/biowdl-input-converter:0.2.1--py_0"
+        String dockerImage = "quay.io/biocontainers/biowdl-input-converter:0.3.0--pyhdfd78af_0"
    }

    command <<<

--- a/ccs.wdl
+++ b/ccs.wdl
@@ -24,12 +24,19 @@ task CCS {
    input {
        File subreadsFile
        String outputPrefix
+        String logLevel = "WARN"
        Int minPasses = 3
+        Int topPasses = 60
        Int minLength = 10
        Int maxLength = 50000
        Boolean byStrand = false
+        Boolean skipPolish = false
+        Boolean all = false
+        Boolean subreadFallback = false
+        Boolean allKinetics = false
+        Boolean hifiKinetics = false
+        Float minSnr = 2.5
        Float minReadQuality = 0.99
-        String logLevel = "WARN"

        File? subreadsIndexFile
        String? chunkString
@@ -37,7 +44,7 @@ task CCS {
        Int threads = 2
        String memory = "4G"
        Int timeMinutes = 1440
-        String dockerImage = "quay.io/biocontainers/pbccs:5.0.0--0"
+        String dockerImage = "quay.io/biocontainers/pbccs:6.0.0--h9ee0642_2"
    }

    command {
@@ -45,15 +52,24 @@ task CCS {
        mkdir -p "$(dirname ~{outputPrefix})"
        ccs \
        --min-passes ~{minPasses} \
+        --min-snr ~{minSnr} \
+        --top-passes ~{topPasses} \
        --min-length ~{minLength} \
        --max-length ~{maxLength} \
        ~{true="--by-strand" false="" byStrand} \
+        ~{true="--skip-polish" false="" skipPolish} \
+        ~{true="--all" false="" all} \
+        ~{true="--subread-fallback" false="" subreadFallback} \
+        ~{true="--all-kinetics" false="" allKinetics} \
+        ~{true="--hifi-kinetics" false="" hifiKinetics} \
        --min-rq ~{minReadQuality} \
        --log-level ~{logLevel} \
        --num-threads ~{threads} \
        ~{"--chunk " + chunkString} \
+        ~{"--report-file " + outputPrefix + ".ccs_report.txt"} \
        ~{"--report-json " + outputPrefix + ".ccs.report.json"} \
        ~{"--log-file " + outputPrefix + ".ccs.stderr.log"} \
+        ~{"--metrics-json " + outputPrefix + ".zmw_metrics.json.gz"} \
        ~{subreadsFile} \
        ~{outputPrefix + ".ccs.bam"}
    }
@@ -61,8 +77,10 @@ task CCS {
    output {
        File ccsBam = outputPrefix + ".ccs.bam"
        File ccsBamIndex = outputPrefix + ".ccs.bam.pbi"
-        File ccsReport = outputPrefix + ".ccs.report.json"
+        File ccsReport = outputPrefix + ".ccs_report.txt"
+        File ccsJsonReport = outputPrefix + ".ccs.report.json"
        File ccsStderr = outputPrefix + ".ccs.stderr.log"
+        File zmwMetrics = outputPrefix + ".zmw_metrics.json.gz"
    }

    runtime {
@@ -76,12 +94,19 @@ task CCS {
        # inputs
        subreadsFile: {description: "Subreads input file.", category: "required"}
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
+        logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"}
        minPasses: {description: "Minimum number of full-length subreads required to generate ccs for a ZMW.", category: "advanced"}
+        topPasses: {description: "Pick at maximum the top N passes for each ZMW.", category: "advanced"}
        minLength: {description: "Minimum draft length before polishing.", category: "advanced"}
        maxLength: {description: "Maximum draft length before polishing.", category: "advanced"}
        byStrand: {description: "Generate a consensus for each strand.", category: "advanced"}
+        skipPolish: {description: "Only output the initial draft template (faster, less accurate).", category: "advanced"}
+        all: {description: "Emit all ZMWs.", category: "advanced"}
+        subreadFallback: {description: "Emit a representative subread, instead of the draft consensus, if polishing failed.", category: "advanced"}
+        allKinetics: {description: "Calculate mean pulse widths (PW) and interpulse durations (IPD) for every ZMW.", category: "advanced"}
+        hifiKinetics: {description: "Calculate mean pulse widths (PW) and interpulse durations (IPD) for every HiFi read.", category: "advanced"}
+        minSnr: {description: "Minimum SNR of subreads to use for generating CCS.", category: "advanced"}
        minReadQuality: {description: "Minimum predicted accuracy in [0, 1].", category: "common"}
-        logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"}
        subreadsIndexFile: {description: "Index for the subreads input file, required when using chunkString.", category: "advanced"}
        chunkString: {descpription: "Chunk string (e.g. 1/4, 5/5) for CCS.", category: "advanced"}
        threads: {description: "The number of threads to be used.", category: "advanced"}
@@ -92,7 +117,9 @@ task CCS {
        # outputs
        ccsBam: {description: "Consensus reads output file."}
        ccsBamIndex: {description: "Index of consensus reads output file."}
-        ccsReport: {description: "Ccs results report file."}
+        ccsReport: {description: "Ccs report file."}
+        ccsJsonReport: {description: "Ccs results json report file."}
        ccsStderr: {description: "Ccs STDERR log file."}
+        zmwMetrics: {description: "ZMW metrics json file."}
    }
 }
--- a/common.wdl
+++ b/common.wdl
@@ -221,7 +221,7 @@ task YamlToJson {
        String  memory = "128M"
        Int timeMinutes = 1
        # biowdl-input-converter has python and pyyaml.
-        String dockerImage = "quay.io/biocontainers/biowdl-input-converter:0.2.1--py_0"
+        String dockerImage = "quay.io/biocontainers/biowdl-input-converter:0.3.0--pyhdfd78af_0"
    }

    command {

--- a/cutadapt.wdl
+++ b/cutadapt.wdl
@@ -83,7 +83,7 @@ task Cutadapt {
        Boolean? noZeroCap

        Int cores = 4
-        String memory = "~{300 + 100 * cores}M"
+        String memory = "5G"
        Int timeMinutes = 1 + ceil(size([read1, read2], "G")  * 12.0 / cores)
        String dockerImage = "quay.io/biocontainers/cutadapt:2.10--py37hf01694f_1"
    }

--- a/gffcompare.wdl
+++ b/gffcompare.wdl
@@ -46,6 +46,7 @@ task GffCompare {
        Int? maxDistanceGroupingTranscriptStartSites
        String? namePrefix

+        String memory = "4G"
        Int timeMinutes = 1 + ceil(size(inputGtfFiles, "G") * 30)
        String dockerImage = "quay.io/biocontainers/gffcompare:0.10.6--h2d50403_0"

@@ -114,6 +115,7 @@ task GffCompare {
    }

    runtime {
+        memory: memory
       time_minutes: timeMinutes
       docker: dockerImage
    }
@@ -140,6 +142,7 @@ task GffCompare {
        maxDistanceFreeEndsTerminalExons: {description: "Equivalent to gffcompare's `-e` option.", category: "advanced"}
        maxDistanceGroupingTranscriptStartSites: {description: "Equivalent to gffcompare's `-d` option.", category: "advanced"}
        namePrefix: {description: "Equivalent to gffcompare's `-p` option.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", 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"}


--- a/gffread.wdl
+++ b/gffread.wdl
@@ -32,6 +32,7 @@ task GffRead {
        String? proteinFastaPath
        String? filteredGffPath

+        String memory = "4G"
        Int timeMinutes = 1 + ceil(size(inputGff, "G") * 10)
        String dockerImage = "quay.io/biocontainers/gffread:0.9.12--0"
    }
@@ -64,6 +65,7 @@ task GffRead {
    }

    runtime {
+        memory: memory
        time_minutes: timeMinutes
        docker: dockerImage
    }
@@ -78,6 +80,7 @@ task GffRead {
        CDSFastaPath: {description: "The location the CDS fasta should be written to.", category: "advanced"}
        proteinFastaPath: {description: "The location the protein fasta should be written to.", category: "advanced"}
        filteredGffPath: {description: "The location the filtered GFF should be written to.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", 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"}


--- a/lima.wdl
+++ b/lima.wdl
@@ -51,7 +51,7 @@ task Lima {
        Int threads = 2
        String memory = "2G"
        Int timeMinutes = 30
-        String dockerImage = "quay.io/biocontainers/lima:2.0.0--0"
+        String dockerImage = "quay.io/biocontainers/lima:2.2.0--h9ee0642_0"
    }

    Map[String, String] libraryDesignOptions = {"same": "--same", "different": "--different", "neighbors": "--neighbors"}
@@ -91,13 +91,13 @@ task Lima {
        dirName="$(dirname ~{outputPrefix})"
        find "$(cd ${dirName}; pwd)" -name "*.bam" > bamFiles.txt
        find "$(cd ${dirName}; pwd)" -name "*.bam.pbi" > bamIndexes.txt
-        find "$(cd ${dirName}; pwd)" -name "*.subreadset.xml" > subreadsets.txt
+        find "$(cd ${dirName}; pwd)" -name "*.consensusreadset.xml" > consensusreadset.txt
    >>>

    output {
        Array[File] limaBam = read_lines("bamFiles.txt")
        Array[File] limaBamIndex = read_lines("bamIndexes.txt")
-        Array[File] limaXml = read_lines("subreadsets.txt")
+        Array[File] limaXml = read_lines("consensusreadset.txt")
        File limaStderr = outputPrefix + ".lima.stderr.log"
        File limaJson = outputPrefix + ".json"
        File limaCounts = outputPrefix + ".lima.counts"

--- a/minimap2.wdl
+++ b/minimap2.wdl
@@ -33,7 +33,7 @@ task Indexing {
        Int cores = 1
        String memory = "4G"
        Int timeMinutes = 10
-        String dockerImage = "quay.io/biocontainers/minimap2:2.17--hed695b0_3"
+        String dockerImage = "quay.io/biocontainers/minimap2:2.20--h5bf99c6_0"
    }

    command {
@@ -100,7 +100,7 @@ task Mapping {
        Int cores = 4
        String memory = "30G"
        Int timeMinutes = 1 + ceil(size(queryFile, "G") * 200 / cores)
-        String dockerImage = "quay.io/biocontainers/minimap2:2.17--hed695b0_3"
+        String dockerImage = "quay.io/biocontainers/minimap2:2.20--h5bf99c6_0"
    }

    command {

--- a/multiqc.wdl
+++ b/multiqc.wdl
@@ -57,7 +57,7 @@ task MultiQC {
        String? clConfig

        String? memory
-        Int timeMinutes = 2 + ceil(size(reports, "G") * 8)
+        Int timeMinutes = 10 + ceil(size(reports, "G") * 8)
        String dockerImage = "quay.io/biocontainers/multiqc:1.9--py_1"
    }


--- a/nanopack.wdl
+++ b/nanopack.wdl
@@ -42,7 +42,7 @@ task NanoPlot {
        Int threads = 2
        String memory = "2G"
        Int timeMinutes = 15
-        String dockerImage = "quay.io/biocontainers/nanoplot:1.32.1--py_0"
+        String dockerImage = "quay.io/biocontainers/nanoplot:1.38.0--pyhdfd78af_0"
    }

    Map[String, String] fileTypeOptions = {"fastq": "--fastq ", "fasta": "--fasta ", "fastq_rich": "--fastq_rich ", "fastq_minimal": "--fastq_minimal ", "summary": "--summary ", "bam": "--bam ", "ubam": "--ubam ", "cram": "--cram ", "pickle": "--pickle ", "feather": "--feather "}

--- a/pacbio.wdl
+++ b/pacbio.wdl
@@ -26,7 +26,7 @@ task mergePacBio {
        String outputPathMergedReport

        String memory = "4G"
-        String dockerImage = "lumc/pacbio-merge:0.2"
+        String dockerImage = "quay.io/redmar_van_den_berg/pacbio-merge:0.2"
    }

    command {

--- a/samtools.wdl
+++ b/samtools.wdl
@@ -122,6 +122,8 @@ task Fastq {
    }

    command {
+        set -e
+        mkdir -p "$(dirname ~{outputRead1})"
        samtools fastq \
        ~{true="-1" false="-s" defined(outputRead2)} ~{outputRead1} \
        ~{"-2 " + outputRead2} \

--- a/scripts @ c31670d3
+++ b/scripts @ c31670d3
-Subproject commit 85e2ec542b65be5f2a25c22db05c28700fbe6db5
+Subproject commit c31670d3a9222a2feafc649cbc118c95afbc7189
--- a/survivor.wdl
+++ b/survivor.wdl
@@ -44,9 +44,9 @@ task Merge {
        fileList \
        ~{breakpointDistance} \
        ~{suppVecs} \
-        ~{true=1 false=0 svType} \
-        ~{true=1 false=0 strandType} \
-        ~{true=1 false=0 distanceBySvSize} \
+        ~{true='1' false='0' svType} \
+        ~{true='1' false='0' strandType} \
+        ~{true='1' false='0' distanceBySvSize} \
        ~{minSize} \
        ~{outputPath}
    }