<tool id="EMBOSS: getorf42" name="getorf" version="5.0.0">
  <description>Finds and extracts open reading frames (ORFs)</description>
  <requirements><requirement type="package" version="5.0.0">emboss</requirement></requirements>
  <command>getorf -sequence $input1 -outseq $out_file1 -table $table -minsize $minsize -maxsize $maxsize -find $find -methionine $methionine -circular $circular -reverse $reverse -flanking $flanking
  -osformat2 $out_format1 -auto</command>
  <inputs>
    <param format="fasta" name="input1" type="data">
      <label>Sequences</label>
    </param>
    <param name="table" type="select">
      <label>Code to use</label>
      <option value="0">Standard</option>
      <option value="1">Standard (with alternative initiation codons)</option>
      <option value="2">Vertebrate Mitochondrial</option>
      <option value="3">Yeast Mitochondrial</option>
      <option value="4">Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option>
      <option value="5">Invertebrate Mitochondrial</option>
      <option value="6">Ciliate Macronuclear and Dasycladacean</option>
      <option value="9">Echinoderm Mitochondrial</option>
      <option value="10">Euplotid Nuclear</option>
      <option value="11">Bacterial</option>
      <option value="12">Alternative Yeast Nuclear</option>
      <option value="13">Ascidian Mitochondrial</option>
      <option value="14">Flatworm Mitochondrial</option>
      <option value="15">Blepharisma Macronuclear</option>
      <option value="16">Chlorophycean Mitochondrial</option>
      <option value="21">Trematode Mitochondrial</option>
      <option value="22">Scenedesmus obliquus</option>
      <option value="23">Thraustochytrium Mitochondrial</option>
    </param>
    <param name="minsize" size="10" type="text" value="30">
      <label>Minimum nucleotide size of ORF to report</label>
    </param>
    <param name="maxsize" size="10" type="text" value="1000000">
      <label>Maximum nucleotide size of ORF to report</label>
    </param>
    <param name="find" type="select">
      <label>What to output</label>
      <option value="0">Translation of regions between STOP codons</option>
      <option value="1">Translation of regions between START and STOP codons</option>
      <option value="2">Nucleic sequences between STOP codons</option>
      <option value="3">Nucleic sequences between START and STOP codons</option>
      <option value="4">Nucleotides flanking START codons</option>
      <option value="5">Nucleotides flanking initial STOP codons</option>
      <option value="6">Nucleotides flanking ending STOP codons</option>
    </param>
    <param name="methionine" type="select">
      <label>All START codons to code for Methionine</label>
      <option value="yes">Yes</option>
      <option value="no">No</option>
    </param>
    <param name="circular" type="select">
      <label>Circular sequence</label>
      <option value="no">No</option>
      <option value="yes">Yes</option>
    </param>
    <param name="reverse" type="select">
      <label>Find ORFs in the reverse complement</label>
      <option value="yes">Yes</option>
      <option value="no">No</option>
    </param>
    <param name="flanking" size="10" type="text" value="100">
      <label>Number of flanking nucleotides to output</label>
    </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="minsize" value="30"/>
      <param name="maxsize" value="1000000"/>
      <param name="find" value="0"/>
      <param name="methionine" value="yes"/>
      <param name="circular" value="no"/>
      <param name="reverse" value="yes"/>
      <param name="table" value="0"/>
      <param name="flanking" value="100"/>
      <param name="out_format1" value="fasta"/>
      <output name="out_file1" file="emboss_getorf_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/getorf.html
  </help>
</tool>