annotate emboss_5/emboss_trimest.xml @ 5:2cf967772a40

Fix for emboss_format_corrector.py. Datatypes should be changed before the job is run.

<tool id="EMBOSS: trimest102" name="trimest" version="5.0.0">
  <description>Trim poly-A tails off EST sequences</description>
  <requirements><requirement type="package" version="5.0.0">emboss</requirement></requirements>
  <command>trimest -sequence $input1 -outseq $out_file1 -minlength "$minlength" -mismatches "$mismatches" -reverse $reverse -tolower $tolower -fiveprime $fiveprime -osformat2 $out_format1
  -auto</command>
  <inputs>
    <param format="fasta" name="input1" type="data">
      <label>Sequences</label>
    </param>
    <param name="minlength" size="4" type="text" value="4">
      <label>Minimum length that a poly-A (or poly-T) tail must have before it is removed</label>
    </param>
    <param name="mismatches" size="4" type="text" value="1">
      <label>Number of fewer mismatched non-A bases in a poly-A tail</label>
    </param>
    <param name="reverse" type="select">
      <label>Change the sequence to the forward sense when it is written out</label>
      <option value="yes">Yes</option>
      <option value="no">No</option>
    </param>
    <param name="tolower" type="select">
      <label>Mask poly-A by converting to lowercase</label>
      <option value="no">No</option>
      <option value="yes">Yes</option>
    </param>
    <param name="fiveprime" type="select">
      <label>Inspect 5' end of the sequence for poly-T tails</label>
      <option value="yes">Yes</option>
      <option value="no">No</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="minlength" value="4"/>
      <param name="mismatches" value="1"/>
      <param name="reverse" value="yes"/>
      <param name="tolower" value="no"/>
      <param name="fiveprime" value="yes"/>
      <param name="out_format1" value="fasta"/>
      <output name="out_file1" file="emboss_trimest_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/trimest.html

------

**Citation**

For the underlying tool, please cite `Rice P, Longden I, Bleasby A. EMBOSS: the European Molecular Biology Open Software Suite. Trends Genet. 2000 Jun;16(6):276-7. &lt;http://www.ncbi.nlm.nih.gov/pubmed/10827456&gt;`_

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>