view utils_find-boxes.xml @ 4:63df1e23f4ff draft

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/segmentation_fold_galaxy_wrapper commit 00690c63c51a7f7563f2428c313d7fa75f2657e5-dirty

<tool id="smf_utils_find-boxes" name="find-boxes" version="@VERSION@-1">
    <description>Finds all occurances of two given boxes (sequence motifs) within a FASTA file</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>
    
    <requirements>
        <requirement type="package" version="2.7.10">python</requirement>
        <requirement type="package" version="1.9">numpy</requirement>
        <requirement type="package" version="0.8.2.1">pysam</requirement>
        <requirement type="package" version="0.6.1">htseq</requirement>
        <requirement type="package" version="2.0.1">segmentation-fold-utils</requirement>
    </requirements>
    
    <expand macro="stdio" />

    <version_command>@VERSION_COMMAND_UTILS@</version_command>
    
    <command><![CDATA[
        segmentation-fold-utils
            find-boxes
                --box1 '${box1}'
                --box2 '${box2}'
                $forward
                $reverse
                '${fasta_input}'
                '${bed_output}'
    ]]></command>

    <inputs>
        <param name="fasta_input"
               type="data"
               format="fasta"
               argument="-f"
               label="Fasta file with RNA-sequece" />

        <param name="box1"
               type="text"
               value="NRUGAUG"
               argument="--box1"
               label="Sequence of box1 (default = C-box: 'NRUGAUG')"
               help="Sequence encoding can be found at the following url: https://en.wikipedia.org/wiki/FASTA_format#Sequence_representations" />

        <param name="box2"
               type="text"
               value="CUGA"
               argument="--box2"
               label="Sequence of box2 (default = D-box: 'CUGA')"
               help="Sequence encoding can be found at the following url: https://en.wikipedia.org/wiki/FASTA_format#Sequence_representations" />

        <param name="forward"
               type="boolean"
               truevalue="--forward"
               falsevalue="--no-forward"
               checked="true"
               label="Search in the forward direction of the reference sequence" />

        <param name="reverse"
               type="boolean"
               truevalue="--reverse"
               falsevalue="--no-reverse"
               checked="true"
               label="Search in the reverse complement of the reference sequence" />
    </inputs>

    <outputs>
        <data format="bed"
              name="bed_output"
              label="${tool.name} on ${str($fasta_input.hid) + ': ' + $fasta_input.name}" />
    </outputs>

    <tests>
        <test>
            <param name="fasta_input" value="FindBoxes.genome.fa" format="fasta" />
            <param name="box1" value="NRUGAUG" />
            <param name="box2" value="CUGA" />
            <param name="forward" value="--forward" />
            <param name="reverse" value="--reverse" />
            
            <output name="bed_output" file="FindBoxes.test_02.bed" />
        </test>
    </tests>
    
    <help><![CDATA[
Scans a FASTA reference for BOX motifs (like C- and D-box) and reports them in a BED file
    ]]></help>
    
    <expand macro="citations" />
</tool>