annotate artbio_bam_cleaning.xml @ 4:15ada8e1580a draft

"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/artbio_bam_cleaning commit 13e2d0837000c2557f9590aa861a9fd5bc16cbcc"

<tool id="artbio_bam_cleaning" name="ARTbio bam cleaning" version="1.6+galaxy4">
    <description>
        on flags and PCR Duplicates and MD recalibration
    </description>
    <macros>
        <import>macro.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="1.6">samtools</requirement>
        <requirement type="package" version="0.7.1">sambamba</requirement>
        <requirement type="package" version="1.3.2">freebayes</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Error occured" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[
    @pipefail@
    @set_fasta_index@
    #set input_base = 'input'   
    ln -f -s $input_bam.metadata.bam_index input.bam.bai &&
    ln -s $input_bam input.bam &&
    sambamba view -h -t \${GALAXY_SLOTS:-2} --filter='mapping_quality >= 1 and not(unmapped) and not(mate_is_unmapped)' -f 'bam' $input_base".bam"
    #if $skip_rmdup == 'no':
        | samtools rmdup -s - - | tee $input_base".filt1.dedup.bam"
    #end if
    | bamleftalign --fasta-reference reference.fa -c --max-iterations "5" -
    | samtools calmd  -C 50 -b -@ \${GALAXY_SLOTS:-2} - reference.fa > $calmd
    && sambamba view -h -t \${GALAXY_SLOTS:-2} --filter='mapping_quality <= 254' -f 'bam' -o $fullfilter $calmd
    ]]></command>
    <inputs>
        <expand macro="reference_source_conditional" />
        <param name="input_bam" type="data" format="bam" label="BAM or SAM file to process"/>
            <param name="skip_rmdup" type="select" label="skip remove pcr duplicate step ?" display="radio"
                   help="useful if duplicates are already marked by other tools">
                <option value="no" selected="true">No</option>
                <option value="yes">Yes</option>
            </param>
    </inputs>
    <outputs>
        <data name="calmd" format="bam" label="CalMD filter (for lumpy-smoove)" />
        <data name="fullfilter" format="bam" label="Full filtering (for somatic-varscan)" />
    </outputs>
    <tests>
        <test>
            <param name="input_bam" value="match_chr21_DBA_974.bam" ftype="bam" />
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" value="chr21.fa" />
            <output name="calmd" file="calmd.bam" ftype="bam" />
            <output name="fullfilter" file="full.bam" ftype="bam" />
        </test>
        <test>
            <param name="input_bam" value="match_chr21_DBA_974.bam" ftype="bam" />
            <param name="reference_source_selector" value="history" />
            <param name="skip_rmdup" value="yes" />
            <param name="ref_file" value="chr21.fa" />
            <output name="calmd" file="normdup_calmd.bam" ftype="bam" />
            <output name="fullfilter" file="normdup_full.bam" ftype="bam" />
        </test>
    </tests>
    <help>
ARTbio bam cleaning overview
============================

This tool is wrapping several cleaning steps to produce bam files suitable for subsequent
analyses with lumpy-smoove (or other large structural variation callers) or with
somatic-varscan (or small structural variation callers)


Workflow 
=============

The tool is using the following command line for filtering:

::

    sambamba view -h -t 8 --filter='mapping_quality >= 1 and not(unmapped) and not(mate_is_unmapped)' -f 'bam' $input_base".bam"
    &#124; samtools rmdup - -
    &#124;tee $input_base".filt1.dedup.bam" &#124; bamleftalign --fasta-reference reference.fa -c --max-iterations "5" -
    &#124; samtools calmd  -C 50 -b -@ 4 - reference.fa &gt; $input_base".filt1.dedup.bamleft.calmd.bam" ;
    sambamba view -h -t 8 --filter='mapping_quality &lt;&#61; 254' -f 'bam' -o $input_base".filt1.dedup.bamleft.calmd.filt2.bam" $input_base".filt1.dedup.bamleft.calmd.bam"
    
Purpose
--------

This "workflow" tool was generated in order to limit the number of ``python metadata/set.py`` jobs
which occur at each step of standard galaxy workflows. Indeed, these jobs are poorly optimized and may last considerable
amounts of time when datasets are large, at each step, lowering the overall performance of the workflow.

    </help>
    <citations>
        <citation type="doi">10.1371/journal.pone.0168397</citation>
    </citations>
</tool>