depth_of_coverage.xml

<tool id="depth_of_coverage" name="DepthOfCoverage" version="3.7.0" >
    <description>Assess sequence coverage by a wide array of metrics, partitioned by sample, read group, or library</description>
    <macros>
        <import>macros.xml</import>
    </macros>

    <command detect_errors="exit_code"><![CDATA[
    #include source=$bam_index#
    #include source=$pre_gatk_ints_chth#
    java8 -jar \${GATK_JAR_PATH} -T DepthOfCoverage

    #include source=$gatk_bam_input#
    #include source=$ref_opts#
    #include source=$gatk_ints_chth#

    #if str( $input_calculate_coverage_over_genes ) != "None":
        --calculateCoverageOverGenes "${input_calculate_coverage_over_genes}"
    #end if
    #if str( $partition_type ) != "None":
        #for $pt in str( $partition_type ).split( ',' ):
            --partitionType "${pt}"
        #end for
    #end if
    --out "${output_per_locus_coverage}"

    #for $ct_group in $summary_coverage_threshold_group:
        --summaryCoverageThreshold "${ct_group.summary_coverage_threshold}"
    #end for
    --outputFormat "${output_format}"
    ]]></command>

    <inputs>
        <param name="partition_type" type="select" label="Partition type for depth of coverage" multiple="True" display="checkboxes" help="-pt,--partitionType &amp;lt;partitionType&amp;gt;">
            <option value="sample" selected="True">sample</option>
            <option value="readgroup">readgroup</option>
            <option value="library">library</option>
        </param>

        <repeat name="summary_coverage_threshold_group" title="Summary coverage threshold" help="-ct,--summaryCoverageThreshold &amp;lt;summaryCoverageThreshold&amp;gt;">
            <param name="summary_coverage_threshold" type="integer" value="15" label="for summary file outputs, report the % of bases covered to &gt;= this number" />
        </repeat>
        <param name="output_format" type="select" label="Output format" help="--outputFormat &amp;lt;outputFormat&amp;gt;" >
            <option value="csv">csv</option>
            <option value="table">table</option>
            <option value="rtable" selected="True">rtable</option>
        </param>
        <param name="ignore_deletion_sites" type="boolean" truevalue="--ignoreDeletionSites" falsevalue="" checked="False" label="Ignore sites consisting only of deletions" help="--ignoreDeletionSites" />
        <param name="include_deletions" type="boolean" truevalue="--includeDeletions" falsevalue="" checked="False" label="Include information on deletions" help="-dels,--includeDeletions" />
        <param name="max_base_quality" type="integer" value="127" label="Maximum quality of bases to count towards depth" help="--maxBaseQuality &amp;lt;maxBaseQuality&amp;gt;" />
        <param name="min_base_quality" type="integer" value="-1" label="Minimum quality of bases to count towards depth" help="-mbq,--minBaseQuality &amp;lt;minBaseQuality&amp;gt;" />
        <param name="max_mapping_quality" type="integer" value="2147483647" label="Maximum mapping quality of reads to count towards depth." help="--maxMappingQuality &amp;lt;maxMappingQuality&amp;gt;" />
        <param name="min_mapping_quality" type="integer" value="127" label="Minimum mapping quality of reads to count towards depth" help="-mmq,--minMappingQuality &amp;lt;minMappingQuality&amp;gt;" />
        <param name="n_bins" type="integer" value="499" label="Number of bins to use for granular binning" help="--nBins &amp;lt;nBins&amp;gt;" />
        <param name="omit_depth_output_at_each_base" type="boolean" truevalue="--omitDepthOutputAtEachBase" falsevalue="" checked="False" label="Omit the output of the depth of coverage at each base" help="-omitBaseOutput,--omitDepthOutputAtEachBase" />
        <param name="omit_interval_statistics" type="boolean" truevalue="--omitIntervalStatistics" falsevalue="" checked="False" label="Omit the per-interval statistics section" help="-omitIntervals,--omitIntervalStatistics" />
        <param name="omit_locus_table" type="boolean" truevalue="--omitLocusTable" falsevalue="" checked="False" label="Do not calculate the per-sample per-depth counts of loci" help="-omitLocusTable,--omitLocusTable" />
        <param name="omit_per_sample_stats" type="boolean" truevalue="--omitPerSampleStats" falsevalue="" checked="False" label="Omit the summary files per-sample." help="-omitSampleSummary,--omitPerSampleStats" />
        <param name="print_base_counts" type="boolean" truevalue="--printBaseCounts" falsevalue="" checked="False" label="Add base counts to per-locus output" help="-baseCounts,--printBaseCounts" />
        <param name="include_ref_n_sites" type="boolean" truevalue="--includeRefNSites" falsevalue="" checked="False" label="Include sites where the reference is N" help="--includeRefNSites" />
        <param name="print_bin_endpoints_and_exit" type="boolean" truevalue="--printBinEndpointsAndExit" falsevalue="" checked="False" label="Print the bin values and exits immediately" help="--printBinEndpointsAndExit" />
        <param name="start" type="integer" value="1" label="Starting (left endpoint) for granular binning" help="--start &amp;lt;start&amp;gt;" />
        <param name="stop" type="integer" value="500" label="Ending (right endpoint) for granular binning" help="--stop &amp;lt;stop&amp;gt;" />
        <param name="count_type" type="select" label="Partition type for depth of coverage" help="How should overlapping reads from the same fragment be handled? --countType&amp;lt;countType&amp;gt;">
            <option value="COUNT_READS" selected="True">COUNT_READS</option>
            <option value="COUNT_FRAGMENTS">COUNT_FRAGMENTS</option>
            <option value="COUNT_FRAGMENTS_REQUIRE_SAME_BASE">COUNT_FRAGMENTS_REQUIRE_SAME_BASE</option>
        </param>
    </inputs>


    <outputs>
        <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string}: INDEL VCF" help="Output VCF with indel calls." from_work_dir="./outdir/variants.indel.vcf">
            <filter>analysis['analysis_mode'] == 'single'</filter>
        </data>
        <data format="vcf" name="output_vcf_filt" label="${tool.name} on ${on_string}: FILTERED INDEL VCF" help="Output VCF with filtered indel calls." >
            <filter>analysis['analysis_mode'] == 'single'</filter>
            <filter>analysis['scalpel_export_single']['filt_single'] == 'filt_yes'</filter>
        </data>
        <data format="vcf" name="tumor_vcf" label="${tool.name} on ${on_string}: SOMATIC INDEL VCF" help="Somatic VCF with indel calls." from_work_dir="./outdir/main/somatic.indel.vcf">
            <filter>analysis['analysis_mode'] == 'somatic'</filter>
        </data>
        <data format="vcf" name="tumor_vcf_filt" label="${tool.name} on ${on_string}: FILTERED SOMATIC INDEL VCF" help="Somatic VCF with filtered indel calls.">
            <filter>analysis['analysis_mode'] == 'somatic'</filter>
            <filter>analysis['scalpel_export_somatic']['filt_somatic'] == 'filt_yes'</filter>
        </data>
        <data format="vcf" name="normal_vcf" label="${tool.name} on ${on_string}: COMMON INDEL VCF" help="Common VCF with indel calls." from_work_dir="./outdir/main/common.indel.vcf">
            <filter>analysis['analysis_mode'] == 'somatic'</filter>
        </data>
    </outputs>

    <tests></tests>

    <help><![CDATA[
    As the second most common type of variation in the human genome, insertions and deletions (indels) have been linked
    to many diseases, but the discovery of indels of more than a few bases in size from short-read sequencing data remains
    challenging. Scalpel (http://scalpel.sourceforge.net) is an open-source software for reliable indel detection based
    on the microassembly technique. It has been successfully used to discover mutations in novel candidate genes for
    autism, and it is extensively used in other large-scale studies of human diseases. This protocol gives an overview
    of the algorithm and describes how to use Scalpel to perform highly accurate indel calling from whole-genome and
    whole-exome sequencing data. We provide detailed instructions for an exemplary family-based de novo study, but we
    also characterize the other two supported modes of operation: single-sample and somatic analysis. Indel normalization,
    visualization and annotation of the mutations are also illustrated. Using a standard server, indel discovery and
    characterization in the exonic regions of the example sequencing data can be completed in ~5 h after read mapping.
    ]]></help>

    <citations>
        <citation type="doi">10.1038/nprot.2016.150</citation>
    </citations>

</tool>