view pindel.xml @ 0:dd513c72ea56 draft

planemo upload for repository https://github.com/portiahollyoak/Tools commit 1f1c277219ca756c9baa453592b455597fd593d8-dirty
author portiahollyoak
date Tue, 17 May 2016 04:47:23 -0400
parents
children
line wrap: on
line source

<tool id ="pindel" name="Pindel" version="0.2.5b8">
    <description></description>
    <requirements>
        <requirement type="package" version="0.2.5b8">pindel</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
        ln -f -s "$input_file.metadata.bam_index" alignment.sorted.bam.bai &&
        ln -f -s "$input_file" alignment.sorted.bam &&
        ln -f -s "$reference" ref.fa &&
        samtools faidx ref.fa &&
       python $__tool_directory__/create_config_file.py
        --input_file alignment.sorted.bam
        --insert_size "$insert_size"
        --sample_label "$input_file.element_identifier"
        --output_config_file output_config_file &&
        pindel
        -f ref.fa
        -i output_config_file
        -c "$chromosome"
        -o prefix &&
        mv prefix_D $Deletions &&
        mv prefix_SI $Short_Insertions &&
        mv prefix_LI $Long_Insertions &&
        mv prefix_INV $Inversions &&
        mv prefix_TD $Tandem_Duplications &&
        mv prefix_RP $Read_Pair &&
        mv prefix_INT_final $INT_final &&
        mv prefix_CloseEndMapped $Close_End_Mapped
    ]]></command>
    <inputs>
        <param format="bam" name="input_file" type="data" label="One or more BAM alignment files produced by BWA"/>
        <param name="insert_size" type="integer" value="" label="Expected Insert size" />
        <param format="fasta" name="reference" type="data" label="Reference genome in fasta format"/>
        <param name="chromosome" type="text" value="ALL" help="Select a chromsome. ALL will use all chromosomes"
               label="Which chromosome to operate on"/>
    </inputs>
    <outputs>
        <data format="txt" name="Deletions" type="data" label="${input_file.element_identifier} Deletions"/>
        <data format="txt" name="Short_Insertions" type="data" label="${input_file.element_identifier} Short Insertions"/>
        <data format="txt" name="Long_Insertions" type="data" label="${input_file.element_identifier} Long Insertions"/>
        <data format="txt" name="Inversions" type="data" label="${input_file.element_identifier} Inversions"/>
        <data format="txt" name="Tandem_Duplications" type="data" label="${input_file.element_identifier} Tandom Duplications"/>
        <data format="txt" name="Breakpoints" type="data" label="${input_file.element_identifier} Breakpoints"/>
        <data format="txt" name="Read_Pair" type="data" label="${input_file.element_identifier} Read Pair Evidence"/>
        <data format="txt" name="INT_final" type="data" label="${input_file.element_identifier} INT_final"/>
        <data format="txt" name="Close_End_Mapped" type="data" label="${input_file.element_identifier} Close End Mapped"/>
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="X_100000_Hum1.bam" ftype="bam"/>
            <param name="insert_size" value="250"/>
            <param name="reference" value="dm6.fa" ftype="fasta"/>
            <param name="chromosome" value="ALL"/>
            <output name="Deletions" file="X_100000_Hum1.bam_Deletions" ftype="txt"/>
            <output name="Short_Insertions" file="X_100000_Hum1.bam_Short_Insertions" ftype="txt"/>
            <output name="Long_Insertions" file="X_100000_Hum1.bam_Long_Insertions" ftype="txt"/>
            <output name="Inversions" file="X_100000_Hum1.bam_Inversions" ftype="txt"/>
            <output name="Tandem_Duplications" file="X_100000_Hum1.bam_Tandem_Duplications" ftype="txt"/>
            <output name="Breakpoints" file="X_100000_Hum1.bam_Breakpoints" ftype="txt"/>
            <output name="Read_Pair" file="X_100000_Hum1.bam_Read_Pair_Evidence" ftype="txt"/>
            <output name="INT_Final" file="X_100000_Hum1.bam_INT_final" ftype="txt"/>
            <output name="Close_End_Mapped" file="X_100000_Hum1.bam_Close_End_Mapped" ftype="txt"/>
        </test>
    </tests>
    <help> <![CDATA[

Pindel can detect breakpoints of large deletions, medium sized insertions, inversions, tandem duplications and other structural variants at single-based resolution from next-generation sequencing data. It uses a pattern growth approach to identify the breakpoints of these variants from paired-end short reads.

The following inputs/parameters are required:
- One or more BAM alignment files produced by BWA
- Expected Insert Size for each alignment file
- Sample label for each alignment file
- Reference genome in fasta format (same one used in alignment)
- Which chromosome to operate on

The following output files are produced by Pindel:
- Deletions
- Short Insertions
- Long Insertions
- Inversions
- Tandom Duplications
- Breakpoints
- Read Pair Evidence
- INT_final
- Close End Mapped

    ]]> </help>
    <citations>
        <citation type="doi">doi:10.1093/bioinformatics/btp394</citation>
    </citations>
</tool>