annotate hicup_filter.xml @ 5:daf29b40670f draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/hicup commit 5466e3345d762ed53686d80568929c2e15652eef

<tool id="hicup_filter" name="Hicup Filter" version="@VERSION@+galaxy0" profile="18.01">
    <description>classifies read pairs, identifying valid Hi-C di-tags</description>
    <macros>
        <import>hicup_macros.xml</import>
    </macros>
    <expand macro="requirements_hicup"/>
    <command detect_errors="exit_code"><![CDATA[
        #for $i, $file in enumerate($inputFiles):
            #if $file.ext != 'sam':
                ln -s '$file' ./${i}.bam  &&
            #end if
        #end for
        hicup_filter --zip --digest '$digest'
        #if $advanced_options.longest:
            --longest '$advanced_options.longest'
        #end if
        #if $advanced_options.shortest:
            --shortest '$advanced_options.shortest'
        #end if
        #for $i, $file in enumerate($inputFiles):
            #if $file.ext != 'sam':
                ./${i}.bam
            #else:
                '$file'
            #end if
        #end for
    ]]></command>
    <inputs>
        <param name="inputFiles" type="data" multiple="true" format="sam,qname_sorted.bam" label="Input files in BAM or SAM fomat"/>
        <param argument="--digest" type="data" format="tabular" label="Genome digest file" help="Specify the genome digest file (created by hicup_digester)"/>
        <section name="advanced_options" title="Advanced options">
            <expand macro="filter_longest_shortest" />
        </section>
    </inputs>
    <outputs>
        <data name="dataset_filt" format="qname_sorted.bam" from_work_dir="*.filt.bam" label="filt.bam" />
        <data name="hicup_filter_summary" format="tabular" from_work_dir="hicup_filter_summary*.txt" label="hicup_filter_summary.txt" />
        <data name="contiguous_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*contiguous.filter.bam" label="contiguous.filter.bam" />
        <data name="re_ligation_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*re_ligation.filter.bam" label="re_ligation.filter.bam" />
        <data name="same_dangling_ends_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*same_dangling_ends.filter.bam" label="same_dangling_ends.filter.bam" />
        <data name="invalid_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*invalid.filter.bam" label="invalid.filter.bam" />
        <data name="same_circularised_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*same_circularised.filter.bam" label="same_circularised.filter.bam" />
        <data name="same_internal_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*same_internal.filter.bam" label="same_internal.filter.bam" />
        <data name="wrong_size_filter" format="qname_sorted.bam" from_work_dir="hicup_filter_ditag_rejects*/*wrong_size.filter.bam" label="wrong_size.filter.bam"/>
        <data name="filter_piechart" format="svg" from_work_dir="*filter_piechart.svg" label="Filter piechart" />
        <data name="ditag_size_distribution" format="svg" from_work_dir="*.ditag_size_distribution.svg" label="Ditag size distribution" />
    </outputs>
    <tests>
        <test>
            <param name="inputFiles" value="dataset1_2.pair.bam" ftype="qname_sorted.bam" />
            <param name="digest" value="digester_file.txt" ftype="tabular" />
            <output name="hicup_filter_summary">
                <assert_contents>
                    <has_text_matching expression="\s+1143\s+544\s+44\s+440\s+60\s+599\s+21\s+73\s+466\s+39\s+0\s+0"/>
                </assert_contents>
            </output>
            <output name="dataset_filt" file="dataset1_2.filt.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="contiguous_filter" file="dataset1_2_contiguous.filter.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="re_ligation_filter" file="dataset1_2_re_ligation.filter.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="same_dangling_ends_filter" file="dataset1_2_same_dangling_ends.filter.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="invalid_filter" file="dataset1_2_invalid.filter.bam"  lines_diff="11" ftype="qname_sorted.bam" />
            <output name="same_circularised_filter" file="dataset1_2_same_circularised.filter.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="same_internal_filter" file="dataset1_2_same_internal.filter.bam" lines_diff="11" ftype="qname_sorted.bam" />
            <output name="filter_piechart" file="dataset1_2.pair.bam.filter_piechart.svg" ftype="svg" compare="sim_size"/>
            <output name="ditag_size_distribution" file="dataset1_2.ditag_size_distribution.svg" ftype="svg" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[

    For help please consult the documentation of HiCUP: https://www.bioinformatics.babraham.ac.uk/projects/hicup/read_the_docs/html/index.html

    To get more information about the filter visit: https://www.bioinformatics.babraham.ac.uk/projects/hicup/read_the_docs/html/index.html#hicup-filter
    ]]></help>
    <expand macro="citation_hicup" />
</tool>