annotate mapBed.xml @ 26:95a3b2c25bd1 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bedtools commit b75b9e79cf3186a22dc2e1e9d27c1a080b891b59

<tool id="bedtools_map" name="MapBed" version="@WRAPPER_VERSION@.0">
    <description>apply a function to a column for each overlapping interval</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <command>
<![CDATA[
        bedtools map
        -a '${inputA}'
        -b '${inputB}'
        $strand
        @C_AND_O_ARGUMENT@
        -f $overlap
        $reciprocal
        $split
        $header
        @GENOME_FILE_MAPBED@
        > "${output}"
]]>
    </command>
    <inputs>
        <param format="bam,@STD_BEDTOOLS_INPUTS@" name="inputA" type="data" label="File A (BAM/@STD_BEDTOOLS_INPUT_LABEL@)" />
        <param format="bam,@STD_BEDTOOLS_INPUTS@" name="inputB" type="data" label="File B (BAM/@STD_BEDTOOLS_INPUT_LABEL@)" />
        <expand macro="overlap" />
        <param name="reciprocal" type="boolean" checked="false" truevalue="-r" falsevalue=""
            label="Require reciprocal overlap"
            help="If set, the overlap between the BAM alignment and the BED interval must affect the above fraction of both the alignment and the BED interval. (-r)" />
        <expand macro="strand2" />
        <expand macro="c_and_o_argument">
            <param name="col" type="data_column" data_ref="inputA" label="Specify the column(s) that should be summarized" help="(-c)" />
        </expand>
        <expand macro="split" />
        <expand macro="print_header" />
        <conditional name="genome">
            <param name="genome_choose" argument="-g" type="select" 
                label="Specify a genome file the defines the expected chromosome order in the input files." >
                <option value="" selected="true">No</option>
                <option value="-g">Yes</option>
            </param>
            <when value="-g">
                <expand macro="input_conditional_genome_file" />
            </when>
            <when value="" />
        </conditional>
    </inputs>
    <outputs>
        <data format_source="inputA" name="output" metadata_source="inputA" label="Mapping of ${inputB.name} into ${inputA.name}" />
    </outputs>
    <tests>
        <test>
            <param name="inputA" value="mapBed1.bed" ftype="bed" />
            <param name="inputB" value="mapBed2.bed" ftype="bed" />
            <repeat name="c_and_o_argument_repeat">
                <param name="col" value="5" />
                <param name="operation" value="mean" />
            </repeat>
            <output name="output" file="mapBed_result1.bed" ftype="bed" />
        </test>
        <test>
            <param name="inputA" value="mapBed1.bed" ftype="bed" />
            <param name="inputB" value="mapBed2.bed" ftype="bed" />
            <repeat name="c_and_o_argument_repeat">
                <param name="col" value="5" />
                <param name="operation" value="collapse" />
            </repeat>
            <output name="output" file="mapBed_result2.bed" ftype="bed" />
        </test>
        <test>
            <param name="inputA" value="mapBed1.bed" ftype="bed" />
            <param name="inputB" value="mapBed2.bed" ftype="bed" />
            <repeat name="c_and_o_argument_repeat">
                <param name="col" value="5" />
                <param name="operation" value="collapse" />
            </repeat>
            <param name="strand" value="-S" />
            <output name="output" file="mapBed_result3.bed" ftype="bed" />
        </test>
        <test>
            <param name="inputA" value="mapBed1.bed" ftype="bed" />
            <param name="inputB" value="mapBed2.bed" ftype="bed" />
            <repeat name="c_and_o_argument_repeat">
                <param name="col" value="5" />
                <param name="operation" value="collapse" />
            </repeat>
            <param name="strand" value="-s" />
            <output name="output" file="mapBed_result4.bed" ftype="bed" />
        </test>
        <test>
            <param name="inputA" value="mapBed3.bed" ftype="bed" />
            <param name="inputB" value="mapBed4.bed" ftype="bed" />
            <repeat name="c_and_o_argument_repeat">
                <param name="col" value="5" />
                <param name="operation" value="collapse" />
            </repeat>
            <param name="strand" value="-s" />
            <param name="genome_choose" value="-g" />
            <param name="genome_file_opts_selector" value="hist" />
            <param name="genome" value="mm9.len" ftype="bed" />
            <output name="output" file="mapBed_result5.bed" ftype="bed" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

bedtools map allows one to map overlapping features in a B file onto features in an A file and apply statistics and/or summary operations on those features.

.. image:: $PATH_TO_IMAGES/map-glyph.png

.. class:: infomark

bedtools map requires each input file to be sorted by genome coordinate. For BED files, this can be done with sort -k1,1 -k2,2n. Other sorting criteria are allowed if a genome file (-g) is provides that specifies the expected chromosome order.

.. class:: infomark

The map tool is substantially faster in versions 2.19.0 and later. The plot below demonstrates the increased speed when, for example, counting the number of exome alignments that align to each exon. The bedtools times are compared to the bedops bedmap utility as a point of reference.

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