view bedgraph_to_bigwig.xml @ 0:3290b79cd9f3 draft default tip

planemo upload

<?xml version="1.0"?>
<tool id="bedgraph_to_bigwig" name="bedGraphToBigWig" version="1.0">
    <description>Converts a bedGraph file to bigWig format</description>

    <macros>
        <import>ucsc_macros.xml</import>
    </macros>

    <requirements>
        <requirement type="package" version="340">ucsc_bigwig</requirement>
        <requirement type="package" version="340">ucsc_bigbed</requirement>
    </requirements>

    <command detect_errors="exit_code">
<![CDATA[
    @OPTIONAL_PARAM_FUNC@

    ## Allow UCSC track and browser lines in input file
    awk '$0 !~ /^(track|browser) /' "${bedgraph_input}" |

        #if str($bed_clip) == "bedClip":
            bedClip -verbose=2
                stdin "${chrominfo_input}" stdout |
        #end if

        sort -k 1,1 -k 2,2n  > "${bedgraph_input}".sorted &&

        bedGraphToBigWig
            $optional_param("-blockSize", $adv.block_size)
            $optional_param("-itemsPerSlot", $adv.items_per_slot)
            ${adv.no_compression}
            "${bedgraph_input}".sorted "${chrominfo_input}" "${bw_output}"
]]>
    </command>

    <expand macro="environment_LC_COLLATE" />

    <inputs>
        <param name="bedgraph_input" type="data" format="bedgraph"
                label="bedGraph input file" />

        <param name="chrominfo_input" type="data" format="tabular"
                label="Chromosomes sizes file" />

        <param name="bed_clip" type="boolean" checked="false"
                truevalue="bedClip" falsevalue=""
                label="Remove BED items that extend beyond the scaffolds"
                help="bedClip" />

        <section name="adv" title="Advanced options" expanded="false">
            <param name="block_size" type="integer" label="Block size"
                    min="1" optional="true"
                    help="Number of items to bundle in r-tree" />

            <param name="items_per_slot" type="integer" label="Items per slot"
                    min="1" optional="true"
                    help="Number of data points bundled at the lowest level" />

            <param name="no_compression" type="boolean" checked="false"
                    truevalue="-unc" falsevalue=""
                    label="Do not use compression"
                    help="-unc" />
        </section>
    </inputs>
    <outputs>
        <data name="bw_output" format="bigwig" />
    </outputs>
    <tests>
        <test>
            <!-- Test bedGraphToBigWig with default settings -->
            <param name="bedgraph_input" value="contigs.bedgraph" ftype="bedgraph" />
            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
            <output name="bw_output" file="contigs.bedgraph.bw" />
        </test>
        <test>
            <!-- Test bedGraphToBigWig with advanced options -->
            <param name="bedgraph_input" value="contigs.bedgraph" ftype="bedgraph" />
            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
            <param name="block_size" value="200" />
            <param name="items_per_slot" value="500" />
            <param name="no_compression" value="-unc" />
            <output name="bw_output" file="contigs.bedgraph_advanced.bw" />
        </test>
        <test>
            <!-- Test bedGraphToBigWig with default settings -->
            <param name="bedgraph_input" value="contigs.clip.bedGraph" ftype="bedgraph" />
            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
            <param name="bed_clip" value="bedClip" />
            <output name="bw_output" file="contigs.bedgraph_clip.bw" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

bedGraphToBigWig converts a `bedGraph <https://genome.ucsc.edu/goldenpath/help/bedgraph.html>`_ file
to the `bigWig format <https://genome.ucsc.edu/goldenpath/help/bigWig.html>`_.

----

**The bedGraph format**

The first three columns of the bedGraph file are the same as the
`BED format <https://genome.ucsc.edu/FAQ/FAQformat.html#format1>`_, and it uses
a `zero-start, half-open <http://genome.ucsc.edu/blog/the-ucsc-genome-browser-coordinate-counting-systems/>`_
coordinate system. The fourth column of the bedGraph file contains the data values::

    chromA chromStartA chromEndA dataValueA
    chromB chromStartB chromEndB dataValueB

----

.. class:: infomark

**Chromosomes sizes file**

This tool requires a chromosomes sizes (``chrom.sizes``) file, which lists the size of
each scaffold within an assembly. For genome assemblies that are hosted by UCSC,
the ``chrom.sizes`` file is available through the
`Sequence and Annotation Downloads <http://hgdownload.cse.ucsc.edu/downloads.html>`_ page.
The `twoBitInfo <https://genome.ucsc.edu/goldenpath/help/twoBit.html>`_ tool
can be used to generate the ``chrom.sizes`` for the genome assemblies that are not hosted
by UCSC.

    ]]></help>

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