view svtyper.xml @ 0:00cab3d2e98b draft

planemo upload

<tool id="svtyper"
      name="svtyper"
      version="0.1.0">

    <description>Compute variant genotypes</description>

    <requirements>
        <requirement type="package" version="0.6.1">svtyper</requirement>
        <requirement type="package" version="1.9">samtools</requirement>
    </requirements>

    <version_command>
        svtyper -h | grep version | cut -d 'v' -f 3
    </version_command>

    <command detect_errors="aggressive">
      <![CDATA[
          #set refln = "ref.fasta"
          #if $ref
              samtools faidx '$ref' &&
              ln -s -f '$ref' '$refln' &&
              ln -s -f '${ref}.fai' '${refln}.fai' &&
          #end if

          #set agnostic_files = []
          #for $i, $aln in enumerate( $alignment_files ):
              #if $aln
                  #if $aln.is_of_type("bam"):
                      ln -s -f '${aln}' '${i}.bam' &&
                      ln -s -f '${aln.metadata.bam_index}' '${i}.bam.bai' &&
                      $agnostic_files.append(str($i) + ".bam")
                  #else:
                      ln -s -f '${aln}' '${i}.cram' &&
                      ln -s -f '${aln.metadata.cram_index}' '${i}.cram.crai' &&
                      $agnostic_files.append(str($i) + ".cram")
                  #end if
              #end if
          #end for

          svtyper
          -i '$vcf'
          -B ${",".join(map(str, $agnostic_files))}
          -o '$vcfout'

          #if $ref
              -T $refln
          #end if

          #if $libin
              -l $libin
          #elif $outputlib
              -l $libout
          #end if

          -m '$minaln'
          -n '$samplesize'

          #if int($maxreads) > 0
              --max_reads '$maxreads'
          #end if

          --split_weight '$splitweight'
          --disc_weight '$discweight'

          #if $outputbam
              -w '$bamout'
          #end if

          > '$vcfout'
      ]]>
    </command>

    <inputs>
        <param name="vcf"
               label="vcf file"
               argument="--input_vcf"

               type="data"
               format="vcf"

               help="VCF input (default: stdin)"/>

        <param name="alignment_files"
               label="bam/cram file"
               argument="--bam"

               type="data"
               format="bam,cram"
               multiple="true"

               help="BAM or CRAM file(s), comma-separated if genotyping multiple samples" />

        <param name="ref"
               label="Reference"
               argument="--ref_fasta"

               type="data"
               format="fasta"
               optional="true"

               help="Indexed reference FASTA file (recommended for reading CRAM files)" />

        <param name="libin"
               label="Library json file"
               argument="--lib_info"

               type="data"
               format="json"

               help="read JSON file of library information" />

        <param name="minaln"
               label="Min aligned bases"
               argument="--min_aligned"

               type="integer"
               value="20"

               help="minimum number of aligned bases to consider read as evidence [20]" />

        <param name="samplesize"
               label="Sampling size for insert size determination"
               argument="-n"

               type="integer"
               value="1000000"

               help="number of reads to sample from BAM file for building insert size distribution [1000000]" />

        <param name="sumquals"
               label="Add genotyping quality"
               argument="--sum_quals"

               type="boolean"
               truevalue="-q"
               falsevalue=""
               checked="no"
               value="false"

               help="add genotyping quality to existing QUAL (default: overwrite QUAL field)" />

        <param name="maxreads"
               label="Max reads to consider per variant"
               argument="--max_reads"

               type="integer"
               value="0"

               help="maximum number of reads to assess at any variant (reduces processing time in high-depth regions, default: 0 = unlimited)" />

        <param name="splitweight"
               label="Split read weight"
               argument="--split_weight"

               type="float"
               value="1"

               help="weight for split reads [1]" />

        <param name="discweight"
               label="Discordant read weight"
               argument="--disc_weight"

               type="float"
               value="1"

               help="weight for discordant paired-end reads [1]" />

        <param name="outputlib"
               label="Create an output library json file"

               type="boolean"
               checked="no"

               help="if an input library json file (--lib_info) is not provided, create an output library json file" />

        <param name="outputbam"
               label="Create an output bam file"

               type="boolean"
               checked="no"

               help="generate an output bam file containing the reads supporting the structural variants" />
    </inputs>

    <outputs>
        <data format="vcf" name="vcfout" />
        <data format="json" name="libout">
            <filter>outputlib</filter>
        </data>
        <data format="bam" name="bamout">
            <filter>outputbam</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="vcf" value="test1.vcf"/>
            <param name="alignment_files" value="test1.bam"/>
            <param name="libin" value="test1.bam.json"/>
            <output name="vcfout" file="test1.out.vcf"
                    compare="diff" lines_diff="2" />
        </test>
    </tests>
    <help>
        <![CDATA[

            usage: svtyper [-h] [-i FILE] [-o FILE] -B FILE [-T FILE] [-l FILE] [-m INT]
                           [-n INT] [-q] [--max_reads INT] [--split_weight FLOAT]
                           [--disc_weight FLOAT] [-w FILE] [--verbose]

            svtyper
            author: Colby Chiang ([e-mail])
            version: v0.6.0
            description: Compute genotype of structural variants based on breakpoint depth

            optional arguments:
              -h, --help            show this help message and exit
              -i FILE, --input_vcf FILE
                                    VCF input (default: stdin)
              -o FILE, --output_vcf FILE
                                    output VCF to write (default: stdout)
              -B FILE, --bam FILE   BAM or CRAM file(s), comma-separated if genotyping multiple samples
              -T FILE, --ref_fasta FILE
                                    Indexed reference FASTA file (recommended for reading CRAM files)
              -l FILE, --lib_info FILE
                                    create/read JSON file of library information
              -m INT, --min_aligned INT
                                    minimum number of aligned bases to consider read as evidence [20]
              -n INT                number of reads to sample from BAM file for building insert size distribution [1000000]
              -q, --sum_quals       add genotyping quality to existing QUAL (default: overwrite QUAL field)
              --max_reads INT       maximum number of reads to assess at any variant (reduces processing time in high-depth regions, default: unlimited)
              --split_weight FLOAT  weight for split reads [1]
              --disc_weight FLOAT   weight for discordant paired-end reads [1]
              -w FILE, --write_alignment FILE
                                    write relevant reads to BAM file
              --verbose             Report status updates

        ]]>
    </help>

    <citations>
        <citation type="doi">10.1038/nmeth.3505</citation>
    </citations>

  </tool>