view Sambamba_markdup.xml @ 1:a348429b6fec draft default tip

planemo upload for repository https://github.com/biod/sambamba commit 99bb4ed496a9cce79ab0a7e613230cf63a44d9f9
author bgruening
date Mon, 10 Feb 2025 19:12:43 +0000
parents 6c916a5a6afb
children
line wrap: on
line source

<tool id="sambamba_markdup" name="Sambamba markdup" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="23.2" license="MIT">
    <description>Finds and marks duplicate reads in BAM files</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
        sambamba markdup 
               $remove_duplicates
            -l $compression_level
               '${input_bam}'
               '${output}'
            --nthreads \${GALAXY_SLOTS:-4}
            --tmpdir '\${TMPDIR:-.}'
            #if $log_out
                2>&1 | tee '${log}'
            #end if
    ]]></command>
    <inputs>
        <!-- For deduplication the input bam needs to be coordinate sorted, hence the input file is expected to be coordinate sorted -->
        <param name="input_bam" type="data" format="bam" label="Input BAM file"/>
        <param argument="--compression-level" type="integer" value="5" min="0" max="9" label="Level of compression for merged BAM file, number from 0 to 9"/>
        <param argument="--remove-duplicates" type="boolean" truevalue="-r" falsevalue="" label="Remove duplicates instead of just marking them"/>
        <param name="log_out" type="boolean" label="Output log file?" truevalue="yes" falsevalue="no"/>
    </inputs>
    <outputs>
        <data name="output" format="bam" label="${tool.name} on ${on_string}: Output BAM"/>
        <data name="log" format="txt" label="${tool.name} on ${on_string}: Output Log">
            <filter>log_out</filter>
        </data>
    </outputs>
    <tests>
        <!-- sambamba markdup without dropped reads -->
        <test expect_num_outputs="2">
            <param name="input_bam" value="2.bam" ftype="bam"/>
            <param name="compression_level" value="5"/>
            <param name="remove_duplicates" value="false"/>
            <param name="log_out" value="yes"/>
            <output name="output" file="2.markdup.bam" ftype="bam" lines_diff="4"/>
            <output name="log" file="2.markdup.txt" ftype="txt"/>
        </test>
        <!-- sambamba markdup with dropped reads -->
        <test expect_num_outputs="1">
            <param name="input_bam" value="2.bam" ftype="bam"/>
            <param name="compression_level" value="5"/>
            <param name="remove_duplicates" value="true"/>
            <param name="log_out" value="no"/>
            <output name="output" file="2.markdup_removed.bam" ftype="bam" lines_diff="4"/>
        </test>
    </tests>
    <help>
<![CDATA[

Sambamba_markdup marks (by default) or removes duplicate reads. To determine whether a read is a duplicate or not, the same criteria as in Picard are used.

]]>
    </help>
    <expand macro="citations"/>
</tool>