view ssake.xml @ 0:0ec408bcfc80 draft

Uploaded
author crs4
date Wed, 11 Sep 2013 12:51:21 -0400
parents
children 386166019772
line wrap: on
line source

<tool id="ssake" name="SSAKE" version="0.0.10">
  <description>short DNA sequences assembler</description>
  <requirements>
    <requirement type="package" version="3.8">ssake</requirement>
  </requirements>
  <command interpreter="python">
  ssake.py
  #if $kind_of_reads.kind_of_reads_select == '0'
    --if_unpaired $infile
  #else
    --if_paired_r1 $infile_r1
    --if_paired_r2 $infile_r2
    --iz ${kind_of_reads.insert_size}
    -k ${kind_of_reads.minnumlinks}
    -e ${kind_of_reads.error}
    -a ${kind_of_reads.maxlinkratio}
    -x ${kind_of_reads.minoverlap}
  #end if
  #if $seeds
    -s $seeds
  #end if
  -w $mindepthofcoverage
  -m $minoverlap
  -o $mincall
  -r $baseratio
  --ignore_header 1
  --kind_of_reads ${kind_of_reads.kind_of_reads_select}
  --out1 $contig
  --out2 $short
  --out3 $singlets
  --logfile $log
  </command>
  <inputs>
    <conditional name="kind_of_reads">
      <param name="kind_of_reads_select" type="select" label="Kind of reads (-p)">
        <option value="0">Unpaired </option>
        <option value="1">Paired and equal (both files must have the same number of sequences, arranged in the same order)</option>
        <option value="2">Paired and unequal (files can have different number of sequences in any order)</option>
      </param>
      <when value="0">
        <param name="infile" type="data" format="fasta" label="Input FASTA file" />
      </when>
      <when value="1">
        <param name="infile_r1" type="data" format="fasta" label="Input FASTA file (read 1)" />
        <param name="infile_r2" type="data" format="fasta" label="Input FASTA file (read 2)" />
        <param name="insert_size" type="integer" value="200" label="Library insert size" />
        <param name="minnumlinks" type="integer" value="4" label="Minimum number of links (read pairs) to compute scaffold (-k)" />
        <param name="error" type="float" value="0.75" min="0" max="1" label="Error (%) allowed on mean distance (-e)" />
        <param name="maxlinkratio" type="float" value="0.5" label="Maximum link ratio between two best contig pairs (-a)" />
        <param name="minoverlap" type="integer" value="20" label="Minimum overlap required between contigs to merge adjacent contigs in a scaffold (-x)" />
      </when>
      <when value="2">
        <param name="infile_r1" type="data" format="fasta" label="Input FASTA file (read 1)" />
        <param name="infile_r2" type="data" format="fasta" label="Input FASTA file (read 2)" />
        <param name="insert_size" type="integer" value="200" label="Library insert size" />
        <param name="minnumlinks" type="integer" value="4" label="Minimum number of links (read pairs) to compute scaffold (-k)" />
        <param name="error" type="float" value="0.75" min="0" max="1" label="Error (%) allowed on mean distance (-e)" />
        <param name="maxlinkratio" type="float" value="0.5" label="Maximum link ratio between two best contig pairs (-a)" />
        <param name="minoverlap" type="integer" value="20" label="Minimum overlap required between contigs to merge adjacent contigs in a scaffold (-x)" />
      </when>
    </conditional>
    <param name="seeds" type="data" format="fasta" optional="true" label="FASTA file containing sequences to use as seeds exclusively (-s)" help="Optional, specify only if different from read set" />
    <param name="mindepthofcoverage" type="integer" value="1" label="Minimum depth of coverage allowed for contigs (-w)" />
    <param name="minoverlap" type="integer" value="20" label="Minimum number of overlapping bases with the seed/contig during overhang consensus build up (-m)" />
    <param name="mincall" type="integer" value="2" label="Minimum number of reads needed to call a base during an extension (-o)" />
    <param name="baseratio" type="float" value="0.7" label="Minimum base ratio used to accept a overhang consensus base (-r)" />
  </inputs>

  <outputs>
    <data name="contig" format="fasta" label="${tool.name} on ${on_string}: contigs" />
    <data name="log" format="txt" label="${tool.name} on ${on_string}: log" />
    <data name="short" format="txt" label="${tool.name} on ${on_string}: unacceptable reads" />
    <data name="singlets" format="fasta" label="${tool.name} on ${on_string}: unassembled reads" />
  </outputs>
  <help>
**What it does**

SSAKE is a genomics application for de novo assembly of millions of very short DNA sequences.
It is an easy-to-use, robust, reliable and tractable clustering algorithm for very short sequence reads, such as those generated by Illumina Ltd.

**License and citation**

This Galaxy tool is Copyright © 2012-2013 `CRS4 Srl.`_ and is released under the `MIT license`_.

.. _CRS4 Srl.: http://www.crs4.it/
.. _MIT license: http://opensource.org/licenses/MIT

If you use this tool in Galaxy, please cite |Cuccuru2013|_.

.. |Cuccuru2013| replace:: Cuccuru, G., Orsini, M., Pinna, A., Sbardellati, A., Soranzo, N., Travaglione, A., Uva, P., Zanetti, G., Fotia, G. (2013) Orione, a web-based framework for NGS analysis in microbiology. *Submitted*
.. _Cuccuru2013: http://orione.crs4.it/

This tool uses `SSAKE`_, which is licensed separately. Please cite |Warren2007|_.

.. _SSAKE: http://www.bcgsc.ca/platform/bioinfo/software/ssake/
.. |Warren2007| replace:: Warren RL, Sutton GG, Jones SJM, Holt RA. 2007. Assembling millions of short DNA sequences using SSAKE. Bioinformatics. 23(4):500-501
.. _Warren2007: http://bioinformatics.oxfordjournals.org/content/23/4/500
  </help>
</tool>