<tool id="EMBOSS: splitter92" name="splitter" version="5.0.0">

  <description>Split a sequence into (overlapping) smaller sequences</description>

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

  <command>splitter -sequence $input1 -outseq $out_file1 -size "$size" -overlap "$overlap" -addoverlap $addoverlap -osformat2 $out_format1 -auto</command>

  <inputs>

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

      <label>Sequences</label>

    </param>

    <param name="size" size="10" type="text" value="10000">

      <label>Size to split at</label>

    </param>

    <param name="overlap" size="4" type="text" value="0">

      <label>Overlap between split sequences</label>

    </param>

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

      <label>Add overlap to size</label>

      <option value="no">No</option>

      <option value="yes">Yes</option>

    </param>

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

      <label>Output Sequence File Format</label>

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

      <option value="acedb">ACeDB (m)</option>

      <option value="asn1">ASN.1 (m)</option>

      <option value="clustal">Clustal (m)</option>

      <option value="codata">CODATA (m)</option>

      <option value="embl">EMBL (m)</option>

      <option value="fitch">Fitch (m)</option>

      <option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>

      <option value="genbank">GENBANK (m)</option>

      <option value="gff">GFF (m)</option>

      <option value="hennig86">Hennig86 (m)</option>

      <option value="ig">Intelligenetics (m)</option>

      <option value="jackknifer">Jackknifer (m)</option>

      <option value="jackknifernon">Jackknifernon (m)</option>

      <option value="mega">Mega (m)</option>

      <option value="meganon">Meganon (m)</option>

      <option value="msf">Wisconsin Package GCG's MSF (m)</option>

      <option value="pir">NBRF (PIR) (m)</option>

      <option value="ncbi">NCBI style FASTA (m)</option>

      <option value="nexus">Nexus/PAUP (m)</option>

      <option value="nexusnon">Nexusnon/PAUPnon (m)</option>

      <option value="phylip">PHYLIP interleaved (m)</option>

      <option value="phylipnon">PHYLIP non-interleaved (m)</option>

      <option value="selex">SELEX (m)</option>

      <option value="staden">Staden (s)</option>

      <option value="strider">DNA strider (m)</option>

      <option value="swiss">SwisProt entry (m)</option>

      <option value="text">Plain sequence (s)</option>

      <option value="treecon">Treecon (m)</option>

    </param>

  </inputs>

  <outputs>

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

  </outputs>
  <tests>
    <test>
      <param name="input1" value="2.fasta"/>
      <param name="size" value="10000"/>
      <param name="overlap" value="0"/>
      <param name="addoverlap" value="no"/>
      <param name="out_format1" value="fasta"/>
      <output name="out_file1" file="emboss_splitter_out.fasta"/>
    </test>
  </tests>

  <code file="emboss_format_corrector.py" />

  <help>

.. class:: warningmark

The input dataset needs to be sequences.

-----

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