annotate quantifier.xml @ 2:d5ea61ff12eb draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2_quantifier commit 3103ebed1a420c7d3415b67ef532ea579edf9faa

<tool id="rbc_mirdeep2_quantifier" name="MiRDeep2 Quantifier" version="2.0.0">
    <description>fast quantitation of reads mapping to known miRBase precursors</description>
    <requirements>
        <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
<![CDATA[
    quantifier.pl 
    
    -p $precursors 
    
    -m $mature 
    
    -r $reads
    
    #if $species.value != 'all'
        -t $species
    #end if
    
    #if $star_sequences
        -s $star_sequences
    #end if
    
    $sortReadsInPDF
    $flexibleIdMapping
    $skipFileConversion
    $wholePrecursAsMature
    $discardReadMultiMap
    
    -e $upstreamNtides
    -f $downstreamNtides
    -g $allowedMismatches
    -y galaxy
    
     ## html output
    ;
    cp expression_galaxy.html $html 2> /dev/null
    
    ## move pdf directory to be accessible from the new index.html
    ;
    mkdir -p $html.files_path 2> /dev/null
    ;
    cp -R pdfs_galaxy $html.files_path 2> /dev/null
    
]]>
    </command>
    <inputs>
        <param name="reads" format="fasta" type="data" label="Collapsed deep sequencing reads" help="Reads in fasta format. (-r)"/>
        <param name="precursors" format="fasta" type="data" label="Precursor sequences" help="miRNA precursor sequences from miRBase. (-p)"/>
        <param name="mature" format="fasta" type="data" label="Mature miRNA sequences" help="Mature miRNA sequences from miRBase. (-m)"/>
        <param name="species" type="select" label="Search in species" help="If not searching in a specific species all species in your files will be analyzed. (-t)">
            <option value="all">All species</option>
            <option value="tni">tetraodon</option>
            <option value="dps">d.pseudoobscura</option>
            <option value="dya">d.yakuba</option>
            <option value="ame">a.mellifera</option>
            <option value="dmo">d.mojavensis</option>
            <option value="cel">worm</option>
            <option value="aga">a.gambiae</option>
            <option value="cbr">c.briggsae</option>
            <option value="cin">c.intestinalis</option>
            <option value="mmu">mouse</option>
            <option value="xtr">x.tropicalis</option>
            <option value="eca">horse</option>
            <option value="cfa">dog</option>
            <option value="fru">fugu</option>
            <option value="bta">cow</option>
            <option value="der">d.erecta</option>
            <option value="dgr">d.grimshawi</option>
            <option value="gga">chicken</option>
            <option value="spu">s.purpuratus</option>
            <option value="bfl">lancelet</option>
            <option value="ptr">chimp</option>
            <option value="dse">d.sechellia</option>
            <option value="dpe">d.persimilis</option>
            <option value="dvi">d.virilis</option>
            <option value="rno">rat</option>
            <option value="dme">d.melanogaster</option>
            <option value="lca">cat</option>
            <option value="sja">c.japonica</option>
            <option value="dan">d.ananassae</option>
            <option value="hsa">human</option>
            <option value="dsi">d.simulans</option>
        </param>
        <param name="star_sequences" format="fasta" type="data" optional="true" label="Star sequences" help="From miRBase in fasta format (optional) (-s)"/>
        
       <!-- <param name="generatePDFs" type="boolean" checked="true" truevalue="" falsevalue="-d" label="Generate PDFs" help="(-d)"/> -->
        <param name="sortReadsInPDF" type="boolean" checked="true" truevalue="" falsevalue="-o" label="Sort reads by sample in PDF" help="(-o)"/>
        <param name="flexibleIdMapping" type="boolean" checked="false" truevalue="-k" falsevalue="" label="Include ID-flexible mapping" help="Also considers precursor-mature mappings that have different ids, eg let7c would be allowed to map to pre-let7a. (-k)"/>
        <param name="skipFileConversion" type="boolean" checked="false" truevalue="-n" falsevalue="" label="Skip file conversion" help="(-n)"/>
        <param name="skipPrecursMapping" type="boolean" checked="false" truevalue="-x" falsevalue="" label="Skip mapping against precursor" help="(-x)"/>
        <!-- <param name="noMrdPDF" type="boolean" checked="false" truevalue="-j" falsevalue="" label="Do not create output.mrd file or PDFs" help="(-j)"/> -->
        <param name="wholePrecursAsMature" type="boolean" checked="false" truevalue="-w" falsevalue="" label="Consider the whole precursor as the 'mature sequence'" help="(-w)"/>
        <param name="discardReadMultiMap" type="boolean" checked="false" truevalue="-U" falsevalue="" label="Discard all read multimapper" help="(-U)"/>
        
        <param name="upstreamNtides" type="integer" value="2" min="0" label="Upstream nucleotides" help="Number of nucleotides upstream of the mature sequence to consider. (-e)"/>
        <param name="downstreamNtides" type="integer" value="5" min="0" label="Downstream nucleotides" help="Number of nucleotides downstream of the mature sequence to consider. (-f)"/>
        <param name="allowedMismatches" type="integer" value="1" min="0" label="Allowed mismatches" help="Number of allowed mismatches when mapping reads to precursors. (-g)"/>
    </inputs>
    <outputs>
        <data name="miRNAsExpressed" format="tabular" from_work_dir="miRNAs_expressed_all_samples_galaxy.csv" label="output of ${tool.name} on ${on_string}"/>
        <data format="html" name="html" label="${tool.name} on ${on_string} (html report)"/>
    </outputs>
    <tests>
        <test>
            <param name="reads" value="reads_collapsed.fa"/>
            <param name="precursors" value="precursors_ref_this_species.fa"/>
            <param name="mature" value="mature_ref_this_species.fa"/>
            <param name="species" value="cel"/>
            <output name="miRNAsExpressed" file="miRNAs_expressed_all_samples.csv"/>
            <output name="html" file="expression_galaxy.html"/>
        </test>
    </tests>
    <help>
<![CDATA[

**What it does**

The module maps the deep sequencing reads to predefined miRNA precursors and determines by that the expression of the corresponding miRNAs. 
First, the predefined mature miRNA sequences are mapped to the predefined precursors. Optionally, predefined star sequences can be mapped to the precursors too. 
By that the mature and star sequence in the precursors are determined. Second, the deep sequencing reads are mapped to the precursors. 
The number of reads falling into an interval 2nt upstream and 5nt downstream of the mature/star sequence is determined.
]]>

**Input**

A FASTA file with precursor sequences, a FASTA file with mature miRNA sequences, a FASTA file with deep sequencing reads and optionally a FASTA file with star sequences and the 3 letter code of the species of interest.

**Output**

A tab separated file with miRNA identifiers and its read count, a signature file, a html file that gives an overview of all miRNAs the input data and a pdfs that contains for each miRNA a pdf file showing its signature and structure.

    </help>
    <citations>
        <citation type="doi">10.1093/nar/gkr688</citation>
        <citation type="doi">10.1002/0471250953.bi1210s36</citation>
    </citations>
</tool>