view filter-abund.xml @ 3:88740fc6d206 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/blob/master/tools/khmer/ commit bfa8bda732de882f6fa5f5375f8468ad229cceea
author iuc
date Wed, 09 Nov 2016 05:58:22 -0500
parents 03246d4ea8cd
children 8c6433857aa8
line wrap: on
line source

<tool id="khmer_filter_abundance" name="Filter reads" version="@WRAPPER_VERSION@.0">
    <description>
        by minimal k-mer abundance
    </description>
    <macros>
        <token name="@BINARY@">filter-abund.py</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version" />
    <command><![CDATA[
set -xu &&
#for $num, $input in enumerate($inputs)
    ln -s ${input} filter-abund-sequence-${num} &&
#end for
mkdir output && cd output &&
@BINARY@
--cutoff=${cutoff}
${variable_coverage}
@THREADS@
${input_countgraph_filename}
../filter-abund-sequence*
]]>
    </command>
    <inputs>
        <expand macro="input_sequences_filenames" />
        <param name="variable_coverage" type="boolean" checked="false" truevalue="--variable-coverage" falsevalue=""
            label="Variable coverage"
            help="Only trim when a sequence has high enough coverage; median abundance > 20 (--variable_coverage)" />
        <param name="cutoff" type="integer" value="2" label="Cutoff"
            help="Trim at k-mers below this abundance. (--cutoff)" />
        <expand macro="input_countgraph_filename" />
    </inputs>
    <outputs>
        <collection name="filter-abund-sequences" type="list">
            <discover_datasets pattern="__name__" directory="output" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="inputs" value="test-abund-read-2.fa" />
            <param name="input_countgraph_filename"
                value="test-abund-read-2.oxlicg" ftype="oxlicg" />
            <output_collection name="filter-abund-sequences" type="list">
                <element name="filter-abund-sequence-0.abundfilt">
                    <assert_contents>
                        <has_text text="GGTTGACGGGGCTCAGGG" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <test>
            <param name="inputs" value="test-abund-read-2.fa" />
            <param name="input_countgraph_filename"
                value="test-abund-read-2.oxlicg" ftype="oxlicg" />
            <param name="cutoff" value="1" />
            <output_collection name="filter-abund-sequences" type="list">
                <element name="filter-abund-sequence-0.abundfilt">
                    <assert_contents>
                        <has_text text="GGTTGACGGGGCTCAGGG" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
Trims fastq/fasta sequences at k-mers of a given abundance based on a provided k-mer countgraph

If the input sequences are from RNAseq or metagenome sequencing then
`--variable-coverage` should be used.

@HELP_FOOTER@
]]>
    </help>
    <citations>
        <expand macro="software-citation" />
        <expand macro="counting-citation" />
    </citations>
</tool>