<tool id="targetfinder" name="Plant small RNA target prediction tool" version="1.7.0">
    <requirements>
        <requirement type="package" version="1.7">targetfinder</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
        targetfinder_threads.pl
            -f $f
            -d $d
            -c $c
            -t "\${GALAXY_SLOTS:-12}"
            $r
            -o $output1
    ]]></command>
    <inputs>
        <param label="Input small RNA sequences file" help="(-f) FASTA-format" name="f" type="data" format="fasta" />
        <param label="Target sequence database file" help="(-d) FASTA-format" name="d" type="data" format="fasta" />
        <param label="Prediction score cutoff value" help="(-c) DEFAULT = 4" name="c" type="float" value="4.0" />
        <param label="Search reverse strand for targets?" help="(-r) Use this option if the database is genomic DNA." name="r" type="boolean" falsevalue="" truevalue="-r" checked="false" />
    </inputs>
    <outputs>
        <data name="output1" format="data"/>
    </outputs>
    <tests>
        <test>
            <param name="f" value="ath_miRNAs_test.fa"/>
            <param name="d" value="Antirrhinum_majus.mRNA.EST.fasta"/>
            <param name="r" value=""/>
            <param name="c" value="4.0"/>
            <param name="t" value="1"/>
            <output name="output1" file="ath_miRNAs_predicted_targets.txt" compare="contains"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

TargetFinder will computationally predict small RNA binding sites on target transcripts from a sequence database.

This is done by aligning the input small RNA sequence against all transcripts,
followed by site scoring using a position-weighted scoring matrix.

**Input**

-f Input small RNA sequences file (FASTA-format).

-d Target sequence database file (FASTA-format)

**Output**

Each predicted target site is printed out separately.
The output consists of two parts.

The first is a description line and the second is a base-pairing diagram of the target and small RNA (query) sequence.

The description line contains the query name, the description line from the target sequence database, and the target prediction score.

The base-pairing diagram has the target site sequence on top in 5'-3' orientation and the query sequence on the bottom in 3'-5' orientation.

Between the target site sequece and the query sequence are base pair symbols.

A ":" (colon) symbol represents an ordinary Watson-Crick base pair, a "." (period) represents a G:U base pair, and a " " (space) represents a mismatch.

If a small RNA is predicted to target a sequence more than once, each target site will be output as separate output.
]]></help>
    <citations>
        <citation type="doi">10.1016/j.cell.2005.04.004</citation>
        <citation type="doi">10.1371/journal.pone.0000219</citation>
        <citation type="doi">10.1007/978-1-60327-005-2_4</citation>
    </citations>
</tool>