<tool id="EMBOSS: wordmatch110" name="wordmatch" version="5.0.0">

  <description>Finds all exact matches of a given size between 2 sequences</description>

  <requirements><requirement type="package" version="5.0.0">emboss</requirement></requirements>

  <command>wordmatch -asequence $input1 -bsequence $input2 -outfile $out_file1 -aoutfeat $out_file2 -boutfeat $out_file3 -wordsize "$wordsize" -aformat3 $out_format1 -offormat4 $out_format2

  -offormat5 $out_format3 -auto</command>

  <inputs>

    <param format="fasta" name="input1" type="data">

      <label>Sequence 1</label>

    </param>

    <param format="fasta" name="input2" type="data">
      <label>Sequence 2</label>

    </param>

    <param name="wordsize" size="5" type="text" value="4">

      <label>Word size</label>

    </param>

    <param name="out_format1" type="select">

      <label>Output Alignment File Format</label>

      <option value="match">Match (m)</option>

      <option value="simple">Simple (m)</option>

      <option value="fasta">FASTA (m)</option>

      <option value="msf">MSF (m)</option>

      <option value="srs">SRS (m)</option>

      <option value="pair">Pair (p)</option>

      <option value="markx0">Markx0 (p)</option>

      <option value="markx1">Markx1 (p)</option>

      <option value="markx2">Markx2 (p)</option>

      <option value="markx3">Markx3 (p)</option>

      <option value="markx10">Markx10 (p)</option>

      <option value="srspair">SRS pair (p)</option>

      <option value="score">Score (p)</option>

    </param>

    <param name="out_format2" type="select">

      <label>Output Feature 1 File Format</label>

      <option value="gff">GFF</option>

      <option value="embl">EMBL</option>

      <option value="swiss">SwissProt</option>

    </param>

    <param name="out_format3" type="select">

      <label>Output Feature 2 File Format</label>

      <option value="gff">GFF</option>

      <option value="embl">EMBL</option>

      <option value="swiss">SwissProt</option>

    </param>

  </inputs>

  <outputs>

    <data format="match" name="out_file1" />

    <data format="gff" name="out_file2" />

    <data format="gff" name="out_file3" />

  </outputs>
  <!--   <tests>
    <test>
      <param name="input1" value="2.fasta"/>
      <param name="input2" value="1.fasta"/>
      <param name="wordsize" value="4"/>
      <param name="out_format1" value="fasta"/>
      <param name="out_format2" value="gff"/>
      <param name="out_format3" value="gff"/>
      <output name="ofile2" file="emboss_wordmatch_out.embl"/>
    </test> 
  </tests> test takes a long time to run-->

  <code file="emboss_format_corrector.py" />

  <help>

.. class:: warningmark 

The input datasets need to be sequences. 

----- 

    You can view the original documentation here_.
    
    .. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/wordmatch.html



------



**Citation**



If you use this tool in Galaxy, please cite `Blankenberg D, Taylor J, Schenck I, He J, Zhang Y, Ghent M, Veeraraghavan N, Albert I, Miller W, Makova KD, Hardison RC, Nekrutenko A. A framework for collaborative analysis of ENCODE data: making large-scale analyses biologist-friendly. Genome Res. 2007 Jun;17(6):960-4. &lt;http://www.ncbi.nlm.nih.gov/pubmed/17568012&gt;`_
  </help>
</tool>