view fetch_fasta_from_NCBI.xml @ 2:50f5ef3313bb draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/fetch_fasta_from_ncbi commit e496484ae6792b1a90fd99aa5f4b70e2039ce3e7
author artbio
date Sun, 15 Oct 2017 20:13:13 -0400
parents 7e41bbb94159
children 8be88084f89c
line wrap: on
line source

<tool id="retrieve_fasta_from_NCBI" name="Retrieve FASTA from NCBI" version="2.1.1">
  <description></description>
  <command><![CDATA[
      python '$__tool_directory__'/fetch_fasta_from_NCBI.py
      -i "$queryString"
      -d $dbname
      -o '$outfilename'
      -l '$logfile'
      #if $date_condition.date_filter == "YES":
          --datetype $date_condition.datetype
          --mindate $date_condition.mindate
          --maxdate $date_condition.maxdate
      #end if
  ]]></command>

  <inputs>
    <param name="queryString" type="text" size="5x80" area="True" value="txid10239[orgn] NOT txid131567[orgn] AND complete[all] NOT partial[title] NOT phage[title]" label="Query to NCBI in entrez format" help="exemple:'Drosophila melanogaster[Organism] AND Gcn5[Title]">
      <sanitizer>
        <valid initial="string.printable">
          <remove value="&quot;"/>
          <remove value="\"/>
        </valid>
        <mapping initial="none">
          <add source="&quot;" target="\&quot;"/>
          <add source="\" target="\\"/>
        </mapping>
      </sanitizer>
    </param>
    <param name="dbname" type="select" label="NCBI database">
      <option value="nuccore">Nucleotide</option>
      <option value="protein">Protein</option>
    </param>
    <conditional name="date_condition">
        <param name="date_filter" type="boolean" label="Filter the sequences by date?" truevalue="YES" falsevalue="NO" checked="false"/>
        <when value="YES">
            <param name="datetype" type="select">
                <option value="pdat">Publication date</option>
                <option value="mdat">Modification date</option>
            </param>
            <param name="mindate" type="text" help="Date must follow one of the following formats: YYYY/MM/DD, YYYY/MM or YYYY"/>
            <param name="maxdate" type="text" help="Date must follow one of the following formats: YYYY/MM/DD, YYYY/MM or YYYY"/>
        </when>
        <when value="NO"/>
    </conditional>
  </inputs>
  <outputs>
    <data name="outfilename" format="fasta" label="${tool.name} (${dbname.value_label}) with queryString '${queryString.value}'" />
    <data format="txt" name="logfile" label="${tool.name}: log"/>
  </outputs>
  <tests>
    <test>
        <param name="queryString" value="9629650[gi]" />
        <param name="dbname" value="nuccore" />
        <output name="outfilename" ftype="fasta" file="output.fa" />
        <!--  <output name="logfile" ftype="txt" file="log.txt" />  log.txt changes with timestamp. removed to pass the  test -->
    </test>
    <test>
        <param name="queryString" value="CU929326[Accession]" />
        <param name="dbname" value="nuccore" />
        <param name="date_filter" value="YES"/>
        <param name="datetype" value="pdat"/>
        <param name="mindate" value="2008/09"/>
        <param name="maxdate" value="2008/09"/>
        <output name="outfilename" ftype="fasta" file="zebra_output.fa" />
    </test>
  </tests>
  <help>
**What it does**

This tool retrieves nucleotide/peptide sequences from the corresponding NCBI database for a given entrez query.

The tool is preset with "txid10239[orgn] NOT txid131567[orgn] AND complete NOT partial[title] NOT phage[title]" for metaVisitor use purpose

See `Entrez help`_ for explanation of query formats

Be sure to use the appropriate NCBI query syntax. Always use [] to specify the search fields.

Note that the tool may fail in case of interrupted connexion with the NCBI database (see the log dataset)

**Acknowledgments**

This Galaxy tool has been adapted from the galaxy tool `get_fasta_from_taxon`_.

It is Copyright © 2014-2015 `CNRS and University Pierre et Marie Curie`_ and is released under the `MIT license`_.

.. _Entrez help: https://www.ncbi.nlm.nih.gov/books/NBK3837/#EntrezHelp.Entrez_Searching_Options
.. _get_fasta_from_taxon: https://toolshed.g2.bx.psu.edu/view/crs4/get_fasta_from_taxon
.. _CNRS and University Pierre et Marie Curie: http://www.ibps.upmc.fr/en
.. _MIT license: http://opensource.org/licenses/MIT

  </help>
  <citations>
      <citation type="doi">10.1186/1471-2105-14-73</citation>
  </citations>
</tool>