annotate manta.xml @ 4:d09254e37c68 draft

"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/manta commit 61062db986142ec4ba86757a724bcb9b94d9f838"

<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( $bam_input.bam_input_selector ) == "not_tumor_bam":
    ln -s '$bam_input.normal_bam_file' normal.bam &&
    ln -s '$bam_input.normal_bam_file.metadata.bam_index' normal.bai &&
    #else if str( $bam_input.bam_input_selector ) == "tumor_bam":
    ln -s '$bam_input.normal_bam_file' normal.bam &&
    ln -s '$bam_input.normal_bam_file.metadata.bam_index' normal.bai &&
    ln -s '$bam_input.tumor_bam_file' tumor.bam &&
    ln -s '$bam_input.tumor_bam_file.metadata.bam_index' tumor.bai &&
    #end if

    #if str( $set_configuration.set_configuration_switch ) == "Customized":
        sed -i 's/minCandidateVariantSize = 8/minCandidateVariantSize = $set_configuration.minCandidateVariantSize/' ./configManta.py.ini &&
        sed -i 's/rnaMinCandidateVariantSize = 1000/rnaMinCandidateVariantSize = $set_configuration.rnaMinCandidateVariantSize/' ./configManta.py.ini &&
        sed -i 's/minEdgeObservations = 3/minEdgeObservations = $set_configuration.minEdgeObservations/' ./configManta.py.ini &&
        sed -i 's/graphNodeMaxEdgeCount = 10/graphNodeMaxEdgeCount = $set_configuration.graphNodeMaxEdgeCount/' ./configManta.py.ini &&
        sed -i 's/minCandidateSpanningCount = 3/minCandidateSpanningCount = $set_configuration.minCandidateSpanningCount/' ./configManta.py.ini &&
        sed -i 's/minScoredVariantSize = 50/minScoredVariantSize = $set_configuration.minScoredVariantSize/' ./configManta.py.ini &&
        sed -i 's/minDiploidVariantScore = 10/minDiploidVariantScore = $set_configuration.minDiploidVariantScore/' ./configManta.py.ini &&
        sed -i 's/minPassDiploidVariantScore = 20/minPassDiploidVariantScore = $set_configuration.minPassDiploidVariantScore/' ./configManta.py.ini &&
        sed -i 's/minPassDiploidGTScore = 15/minPassDiploidGTScore = $set_configuration.minPassDiploidGTScore/' ./configManta.py.ini &&
        sed -i 's/minSomaticScore = 10/minSomaticScore = $set_configuration.minSomaticScore/' ./configManta.py.ini &&
        sed -i 's/minPassSomaticScore = 30/minPassSomaticScore = $set_configuration.minPassSomaticScore/' ./configManta.py.ini &&
        sed -i 's/enableRemoteReadRetrievalForInsertionsInGermlineCallingModes = 1/enableRemoteReadRetrievalForInsertionsInGermlineCallingModes = $set_configuration.enableRemoteReadRetrievalForInsertionsInGermlineCallingModes/' ./configManta.py.ini &&
        sed -i 's/enableRemoteReadRetrievalForInsertionsInCancerCallingModes = 0/enableRemoteReadRetrievalForInsertionsInCancerCallingModes = $set_configuration.enableRemoteReadRetrievalForInsertionsInCancerCallingModes/' ./configManta.py.ini &&
        sed -i 's/useOverlapPairEvidence = 0/useOverlapPairEvidence = $set_configuration.useOverlapPairEvidence/' ./configManta.py.ini &&
    #end if

    #if str( $set_configuration.set_configuration_switch ) == "Custom_config_file":
        cp '$set_configuration.CustomConfigFile' ./configManta.py.ini &&
    #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} &&

    ln -s -f '${run_dir}/runWorkflow.py' '${run_manta_workflow}' &&
    ln -s -f './configManta.py.ini' '${set_conf_file}' &&
    python2 '${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="Just 'normal' BAM file or 'normal' + 'tumor' BAM files" help="Select between a single normal BAM file or a pair of normal / tumor BAM files">
                <option value="not_tumor_bam">Normal</option>
                <option value="tumor_bam">Normal + Tumor</option>
            </param>

            <when value="not_tumor_bam">
                <param name="normal_bam_file" type="data" format="bam" label="select normal BAM" help="Select the files you wish to send to Manta (normal sample, it must be in BAM format)." />
            </when>

            <when value='tumor_bam'>
                <param name="normal_bam_file" type="data" format="bam" label="select normal BAM" help="Select the files you wish to send to Manta (normal sample, it must be in BAM format)." />
                <param name="tumor_bam_file" type="data" format="bam" label="select tumor BAM" help="Select the files you wish to send to Manta (tumor sample, it must be in BAM format)." />
            </when>
        </conditional>

        <param name="additional_param" type="select" multiple="true" display="checkboxes" label="Additional parameters" >
            <option value="exome">Set options for WES input: turn off depth filters</option>
            <option value="rna">Set options for RNA-Seq input. Must specify exactly one bam input file</option>
            <option value="unstrandedRNA">Set if RNA-Seq input is unstranded: Allows splice-junctions on either strand</option>
        </param>

        <section name="advanced" title="Advanced options" expanded="false">

            <param name="callMemMb" type="integer" value="8000" label="Set default task memory requirements" help="The maximum memory size to assign to tasks" />
            <param name="scanSizeMb" type="integer" value="12" label="Set maximum sequence region size" help="The maximum sequence region size (in megabases) scanned by each task during SV Locus graph generation. (default: 12)" />
            <!-- <param name="generateEvidenceBam" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Generate a bam of supporting reads for all SVs" help="Click yes for generating a BAM of supporting reads for all SVs."/> -->

        </section>

        <!-- <expand macro="manta_configuration"/> -->

        <conditional name="set_configuration">
            <param name="set_configuration_switch" type="select" label="Do you want to change default configuration settings?">
                <option value="Default_config_file">Default Manta Configuration File</option>    
                <option value="Custom_config_file">Upload your Own Configuration File</option>
                <option value="Customized">Customize a Configuration File using this Galaxy Form</option>
            </param>
            <when value="Default_config_file">
            </when>
            <when value="Custom_config_file">
                <param format="ini" name="CustomConfigFile" type="data" label="config file"/>
            </when>
            <when value="Customized">
                <param name="minCandidateVariantSize" type="integer" value="8" label="minCandidateVariantSize" help="Run discovery and candidate reporting for all SVs/indels at or above this size."/>
                <param name="rnaMinCandidateVariantSize" type="integer" value="1000" label="rnaMinCandidateVariantSize" help="Separate option (to provide different default) used for runs in RNA-mode."/>
                <param name="minEdgeObservations" type="integer" value="3" label="minEdgeObservations" help="Remove all edges from the graph unless they're supported by this many 'observations'."/>
                <param name="graphNodeMaxEdgeCount" type="integer" value="10" label="graphNodeMaxEdgeCount" help="If both nodes of an edge have an edge count higher than this, then skip evaluation of the edge."/>
                <param name="minCandidateSpanningCount" type="integer" value="3" label="minCandidateSpanningCount" help="Run discovery and candidate reporting for all SVs/indels with at least this many spanning support observations."/>
                <param name="minScoredVariantSize" type="integer" value="50" label="minScoredVariantSize" help="After candidate identification, only score and report SVs/indels at or above this size."/>
                <param name="minDiploidVariantScore" type="integer" value="10" label="minDiploidVariantScore" help="Minimum VCF 'QUAL' score for a variant to be included in the diploid vcf."/>
                <param name="minPassDiploidVariantScore" type="integer" value="20" label="minPassDiploidVariantScore" help="VCF 'QUAL' score below which a variant is marked as filtered in the diploid vcf."/>
                <param name="minPassDiploidGTScore" type="integer" value="15" label="minPassDiploidGTScore" help="Minimum genotype quality score below which single samples are filtered for a variant in the diploid vcf."/>
                <param name="minSomaticScore" type="integer" value="10" label="minSomaticScore" help="Somatic quality scores below this level are not included in the somatic vcf."/>
                <param name="minPassSomaticScore" type="integer" value="30" label="minPassSomaticScore" help="Somatic quality scores below this level are filtered in the somatic vcf."/>
                <param name="enableRemoteReadRetrievalForInsertionsInGermlineCallingModes" type="integer" value="1" label="enableRemoteReadRetrievalForInsertionsInGermlineCallingModes" help="Remote read retrieval is used ot improve the assembly of putative insertions by retrieving any mate reads in remote locations with poor mapping quality. This feature can be enabled/disabled separately for germline and cancer calling below."/>
                <param name="enableRemoteReadRetrievalForInsertionsInCancerCallingModes" type="integer" value="0" label="enableRemoteReadRetrievalForInsertionsInCancerCallingModes" help="Here 'CancerCallingModes' includes tumor-normal subtraction and tumor-only calling. 'GermlineCallingModes' includes all other calling modes."/>
                <param name="useOverlapPairEvidence" type="integer" value="0" label="useOverlapPairEvidence" help="Set if an overlapping read pair will be considered as evidence. Set this value &lt;= 0 to skip overlapping read pairs."/>
            </when>
        </conditional>

        <param name="runworkflow_file_check" type="boolean" label="output manta run_workflow file" checked="False" help="Show run_workflow file on history"/>
        <param name="config_file_check" type="boolean" label="output conf file" checked="False" help="Show configuration file on history"/>
        <param name="candidateSV_check" type="boolean" label="Unscored candidate SV and indels" checked="False"
               help="Show unfiltered structural variants"/>
        <param name="candidateSmallIndels_check" type="boolean" label="all snvs" checked="False"
               help="Subset of the Unscored candidate SV and indels, containing only simple insertion and deletion variants"/>
        <param name="diploidSV_check" type="boolean" label="filtered variants in diploid model" checked="False"
               help="Show filtered variants in a diploid (only normal) model. In the case of a tumor/normal subtraction, the scores in this file *do not*
                     reflect any information from the tumor sample" />
        <param name="somaticSV_check" type="boolean" label="SVs and indels scored under a somatic variant model" checked="False"
               help="This file will only be produced if a tumor sample alignment file is supplied during configuration"/>
    </inputs>

    <outputs>
        <data format="txt" name="run_manta_workflow" label="Parameters for running Manta">
            <filter>runworkflow_file_check == True</filter>
        </data>

        <data format="tabular" name="set_conf_file" label="conf_file.ini">
            <filter>config_file_check == True</filter>
        </data>
        <data format="vcf_bgzip" name="candidateSV" label="Manta unfiltered SVs" from_work_dir="MantaWorkflow/results/variants/candidateSV.vcf.gz">
            <filter>candidateSV_check == True</filter>
        </data>
        <data format="vcf_bgzip" name="candidateSmallIndels" label="Manta unfiltered Small Indels" from_work_dir="MantaWorkflow/results/variants/candidateSmallIndels.vcf.gz">
            <filter>candidateSmallIndels_check == True</filter>
        </data>
        <data format="vcf_bgzip" name="diploidSV" label="Manta SVs (diploid model)" from_work_dir="MantaWorkflow/results/variants/diploidSV.vcf.gz">
            <filter>diploidSV_check == True</filter>
        </data>
        <data format="vcf_bgzip" name="somaticSV" label="Manta SVs (somatic model)" from_work_dir="MantaWorkflow/results/variants/somaticSV.vcf.gz">
            <filter>somaticSV_check == True</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"/>
                <param name="somaticSV_check" value="True"/>
                <output name="candidateSmallIndels" file="candidateSmallIndels.vcf.gz" decompress="true" lines_diff="4"/>
                <output name="somaticSV" file="somaticSV.vcf.gz" decompress="true" lines_diff="4"/>
        </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="4"/>
        </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"/>
                <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="candidateSV_check" value="True"/>
                <output name="candidateSV" file="candidateSV.vcf.gz" decompress="true" lines_diff="4"/>
        </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"/>
                <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="4"/>
        </test>
 </tests>

    <help><![CDATA[
**Outputs**
  The primary Manta outputs are a set of VCF 4.1 files. Currently there are 3 VCF files
  created for a germline analysis, and an additional somatic VCF is produced for a
  tumor/normal subtraction. These files are:
  
  - diploidSV.vcf.gz
      SVs and indels scored and genotyped under a diploid model for the set of samples in a
      joint diploid sample analysis or for the normal sample in a tumor/normal subtraction
      analysis. **In the case of a tumor/normal subtraction, the scores in this file do not
      reflect any information from the tumor sample.**
  
  - somaticSV.vcf.gz
      SVs and indels scored under a somatic variant model. This file will only be produced
      if a tumor sample alignment file is supplied during configuration
  
  - candidateSV.vcf.gz
      Unscored SV and indel candidates. Only a minimal amount of supporting evidence is
      required for an SV to be entered as a candidate in this file. An SV or indel must be a
      candidate to be considered for scoring, therefore an SV cannot appear in the other VCF
      outputs if it is not present in this file. Note that by default this file includes
      indels of size 8 and larger. The smallest indels in this set are intended to be passed
      on to a small variant caller without scoring by manta itself (by default manta scoring
      starts at size 50).
  
  - candidateSmallIndels.vcf.gz
      Subset of the candidateSV.vcf.gz file containing only simple insertion and deletion
      variants less than the minimum scored variant size (50 by default). Passing this file
      to a small variant caller will provide continuous coverage over all indel sizes when
      the small variant caller and manta outputs are evaluated together. Alternate small
      indel candidate sets can be parsed out of the candidateSV.vcf.gz file if this
      candidate set is not appropriate.
  
  For tumor-only analysis, Manta will produce an additional VCF:

  - tumorSV.vcf.gz
      Subset of the candidateSV.vcf.gz file after removing redundant candidates and small
      indels less than the minimum scored variant size (50 by default). The SVs are not
      scored, but include additional details: (1) paired and split read supporting evidence
      counts for each allele (2) a subset of the filters from the scored tumor-normal model
      are applied to the single tumor case to improve precision.

**Manta helps**
  This script configures the Manta SV analysis pipeline.
  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>

</tool>