comparison manta.xml @ 9:7068cff5215f draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/manta commit 01bc6749826f5ef4a22540a9aa6a5ffd93786d4c

8:63d41dc49a7d

<tool id="manta" name="Manta" version="@WRAPPER_VERSION@">

    <description>Manta calls structural variants (SVs) and indels from mapped paired-end sequencing reads.</description>

    <macros>
        <import>manta_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>

    <command detect_errors="exit_code"><![CDATA[
    @VERSION@
    @pipefail@
    @set_reference_fasta_filename@
    #set run_dir = './MantaWorkflow'
    cp $__tool_directory__/configManta.py.ini configManta.py.ini &&
    #if str( $bam_input.bam_input_selector ) == "not_tumor_bam":

    #if str( $set_configuration.set_configuration_switch ) == "Custom_config_file":
        cp '$set_configuration.CustomConfigFile' ./configManta.py.ini &&
    #end if
    #if str( $set_configuration.set_configuration_switch ) == "Customized":
        rm ./configManta.py.ini &&
        python $__tool_directory__/customConfigManta.py
        --minCandidateVariantSize '$set_configuration.minCandidateVariantSize'
        --rnaMinCandidateVariantSize '$set_configuration.rnaMinCandidateVariantSize'
        --minEdgeObservations '$set_configuration.minEdgeObservations'
        --graphNodeMaxEdgeCount '$set_configuration.graphNodeMaxEdgeCount'
        --minCandidateSpanningCount '$set_configuration.minCandidateSpanningCount'

        --enableRemoteReadRetrievalForInsertionsInGermlineCallingModes '$set_configuration.enableRemoteReadRetrievalForInsertionsInGermlineCallingModes'
        --enableRemoteReadRetrievalForInsertionsInCancerCallingModes '$set_configuration.enableRemoteReadRetrievalForInsertionsInCancerCallingModes'
        --useOverlapPairEvidence '$set_configuration.useOverlapPairEvidence' &&
    #end if
    
    configManta.py --referenceFasta='${reference_fasta_filename}'
                   --config='./configManta.py.ini'
                   #if str( $bam_input.bam_input_selector ) == "not_tumor_bam":
                       --bam='normal.bam'
                   #else if str( $bam_input.bam_input_selector ) == "tumor_bam":
                       --bam='normal.bam'
                       --tumorBam='tumor.bam'
                   #end if
                      --runDir='${run_dir}'
                      --scanSizeMb=${advanced.scanSizeMb}
                      --callMemMb=${advanced.callMemMb} &&

    python2 '${run_dir}/runWorkflow.py' -m local -j \${GALAXY_SLOTS:-4}

    ]]></command>

    <inputs>
        <expand macro="reference_source_conditional" />
        <conditional name="bam_input">
            <param name="bam_input_selector" type="select" label="Single 'normal' or 'normal vs tumor' analysis" help="Select between a single normal BAM file or a pair of normal/tumor BAM files">
                <option value="not_tumor_bam">Normal</option>

            <filter>bam_input['bam_input_selector'] == 'tumor_bam'</filter>
        </data>
    </outputs>
    <tests>
        <test>
                <param name="reference_source_selector" value="cached"/>
                <param name="index" value="hg19"/>
                <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
                <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>

                <param name="callMemMb" value="1000"/>
                <param name="candidateSmallIndels_check" value="True"/>
                <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
                <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
         <test>
                <param name="reference_source_selector" value="cached"/>
                <param name="index" value="hg19"/>
                <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
                <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>
                <param name="set_configuration_switch" value="Customized"/>
                <param name="callMemMb" value="1000"/>
                <param name="candidateSmallIndels_check" value="True"/>
                <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
                <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
       <test>
                <param name="reference_source_selector" value="cached"/>
                <param name="index" value="hg19"/>
                <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
                <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>
                <param name="set_configuration_switch" value="Default_config_file"/>
                <param name="callMemMb" value="1000"/>
                <param name="candidateSmallIndels_check" value="True"/>
                <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
                <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
        <test>
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" ftype="fasta" value="hg19_region.fa"/>
                <param name="bam_input_selector" value="tumor_bam"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>

  You must specify a BAM or CRAM file for at least one sample.
  Configuration will produce a workflow run script which
  can execute the workflow on a single node or through
  sge and resume any interrupted execution.

**Options**
  --version             show program's version number and exit
  -h, --help            show this help message and exit
  --config=FILE         provide a configuration file to override defaults in
                        global config file (/home/lpanunzi/Desktop/Hackaton_GC
                        C2019/manta_sv/manta/bin/configManta.py.ini)
  --allHelp             show all extended/hidden options
**Workflow options**
    --bam=FILE, --normalBam=FILE
                        Normal sample BAM or CRAM file. May be specified more
                        than once, multiple inputs will be treated as each BAM
                        file representing a different sample. [optional] (no
                        default)
    --tumorBam=FILE, --tumourBam=FILE
                        Tumor sample BAM or CRAM file. Only up to one tumor
                        bam file accepted. [optional] (no default)
    --exome             Set options for WES input: turn off depth filters
    --rna               Set options for RNA-Seq input. Must specify exactly
                        one bam input file
    --unstrandedRNA     Set if RNA-Seq input is unstranded: Allows splice-
                        junctions on either strand
    --referenceFasta=FILE
                        samtools-indexed reference fasta file [required]
    --runDir=DIR        Name of directory to be created where all workflow
                        scripts and output will be written. Each analysis
                        requires a separate directory. (default:
                        MantaWorkflow)
    --callRegions=FILE  Optionally provide a bgzip-compressed/tabix-indexed
                        BED file containing the set of regions to call. No VCF
                        output will be provided outside of these regions. The
                        full genome will still be used to estimate statistics
                        from the input (such as expected fragment size
                        distribution). Only one BED file may be specified.
                        (default: call the entire genome)
**Extended options**
    These options are either unlikely to be reset after initial site
    configuration or only of interest for workflow development/debugging.
    They will not be printed here if a default exists unless --allHelp is
    specified
    
    --existingAlignStatsFile=FILE
                        Pre-calculated alignment statistics file. Skips
                        alignment stats calculation.
    --useExistingChromDepths
                        Use pre-calculated chromosome depths.
    --candidateBins=candidateBins
                        Provide the total number of tasks which candidate
                        generation  will be sub-divided into. (default: 256)
    --retainTempFiles   Keep all temporary files (for workflow debugging)
    --generateEvidenceBam
                        Generate a bam of supporting reads for all SVs
    --outputContig      Output assembled contig sequences in VCF file
    --scanSizeMb=INT    Maximum sequence region size (in megabases) scanned by
                        each task during SV Locus graph generation. (default:
                        12)
    --region=REGION     Limit the analysis to a region of the genome for
                        debugging purposes. If this argument is provided
                        multiple times all specified regions will be analyzed
                        together. All regions must be non-overlapping to get a
                        meaningful result. Examples: '--region chr20' (whole
                        chromosome), '--region chr2:100-2000 --region
                        chr3:2500-3000' (two regions)'. If this option is
                        specified (one or more times) together with the
                        --callRegions BED file, then all region arguments will
                        be intersected with the callRegions BED track.
    --callMemMb=INT     Set default task memory requirement (in megabytes) for
                        common tasks. This may benefit an analysis of unusual
                        depth, chimera rate, etc.. 'Common' tasks refers to
                        most compute intensive scatter-phase tasks of graph
                        creation and candidate generation.

    For further info see: https://github.com/Illumina/manta

  ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv710</citation>
    </citations>

9:7068cff5215f

<tool id="manta" name="Manta" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
    <description>Manta calls structural variants (SVs) and indels from mapped paired-end sequencing reads.</description>
    <macros>
        <import>manta_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>

    <command detect_errors="exit_code"><![CDATA[
    @pipefail@
    @set_reference_fasta_filename@
    #set run_dir = './MantaWorkflow'
    cp $__tool_directory__/configManta.py.ini configManta.py.ini &&
    #if str( $bam_input.bam_input_selector ) == "not_tumor_bam":

    #if str( $set_configuration.set_configuration_switch ) == "Custom_config_file":
        cp '$set_configuration.CustomConfigFile' ./configManta.py.ini &&
    #end if
    #if str( $set_configuration.set_configuration_switch ) == "Customized":
        rm ./configManta.py.ini &&
        python '$__tool_directory__/customConfigManta.py'
        --minCandidateVariantSize '$set_configuration.minCandidateVariantSize'
        --rnaMinCandidateVariantSize '$set_configuration.rnaMinCandidateVariantSize'
        --minEdgeObservations '$set_configuration.minEdgeObservations'
        --graphNodeMaxEdgeCount '$set_configuration.graphNodeMaxEdgeCount'
        --minCandidateSpanningCount '$set_configuration.minCandidateSpanningCount'

        --enableRemoteReadRetrievalForInsertionsInGermlineCallingModes '$set_configuration.enableRemoteReadRetrievalForInsertionsInGermlineCallingModes'
        --enableRemoteReadRetrievalForInsertionsInCancerCallingModes '$set_configuration.enableRemoteReadRetrievalForInsertionsInCancerCallingModes'
        --useOverlapPairEvidence '$set_configuration.useOverlapPairEvidence' &&
    #end if
    
    configManta.py
        --referenceFasta='${reference_fasta_filename}'
        --config='./configManta.py.ini'
        #if str( $bam_input.bam_input_selector ) == "not_tumor_bam":
            --bam='normal.bam'
        #else if str( $bam_input.bam_input_selector ) == "tumor_bam":
            --bam='normal.bam'
            --tumorBam='tumor.bam'
        #end if
        --runDir='${run_dir}'
        --scanSizeMb=${advanced.scanSizeMb}
        --callMemMb=${advanced.callMemMb} &&

    python2 '${run_dir}/runWorkflow.py' -m local -j \${GALAXY_SLOTS:-4}

    ]]></command>
    <inputs>
        <expand macro="reference_source_conditional" />
        <conditional name="bam_input">
            <param name="bam_input_selector" type="select" label="Single 'normal' or 'normal vs tumor' analysis" help="Select between a single normal BAM file or a pair of normal/tumor BAM files">
                <option value="not_tumor_bam">Normal</option>

            <filter>bam_input['bam_input_selector'] == 'tumor_bam'</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reference_source_selector" value="cached"/>
            <param name="index" value="hg19"/>
            <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
            <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
            <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>
            <param name="set_configuration_switch" value="Default_config_file"/>
            <param name="callMemMb" value="1000"/>
            <param name="candidateSmallIndels_check" value="True"/>
            <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
            <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
        <test>
            <param name="reference_source_selector" value="cached"/>
            <param name="index" value="hg19"/>
            <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
            <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
            <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>
            <param name="set_configuration_switch" value="Customized"/>
            <param name="callMemMb" value="1000"/>
            <param name="candidateSmallIndels_check" value="True"/>
            <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
            <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
        <test>
                <param name="reference_source_selector" value="cached"/>
                <param name="index" value="hg19"/>
                <param name="bam_input_selector" value="tumor_bam" dbkey="hg19"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>
                <param name="tumor_bam_file" ftype="bam" value="HCC1954_tumor.bam"/>

                <param name="callMemMb" value="1000"/>
                <param name="candidateSmallIndels_check" value="True"/>
                <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="6"/>
                <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="6"/>
        </test>
        <test>
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" ftype="fasta" value="hg19_region.fa"/>
                <param name="bam_input_selector" value="tumor_bam"/>
                <param name="normal_bam_file" ftype="bam" value="HCC1954_normal.bam"/>

  You must specify a BAM or CRAM file for at least one sample.
  Configuration will produce a workflow run script which
  can execute the workflow on a single node or through
  sge and resume any interrupted execution.


For further info see: https://github.com/Illumina/manta

  ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv710</citation>
    </citations>