view make_gd_file.xml @ 28:184d14e4270d

Update to Miller Lab devshed revision 4ede22dd5500
author Richard Burhans <burhans@bx.psu.edu>
date Wed, 17 Jul 2013 12:46:46 -0400
parents 8997f2ca8c7a
children
line wrap: on
line source

<tool id="gd_make_gd_file" name="Make File" version="1.0.0">
  <description>: Build a gd_snp or gd_genotype file</description>

  <command interpreter="python">
    #import base64
    #set $preamble_arg = base64.b64encode(str($preamble_names))
    #set $species_arg = base64.b64encode(str($species))
    make_gd_file.py '$input' '$scaffold_col' '$pos_col' '$ref_col' '$rPos_col' '$preamble_arg' '$names' '$species_arg' '$dbkey' '$output_type' '$output'
  </command>

  <inputs>
    <param name="input" type="data" format="tabular" label="Input dataset" />
    <param name="scaffold_col" type="data_column" data_ref="input" label="Column with scaffold/contig" />
    <param name="pos_col" type="data_column" numerical="true" data_ref="input" label="Column with position" />
    <param name="ref_col" type="data_column" data_ref="input" label="Column with reference species chromosome" />
    <param name="rPos_col" type="data_column" numerical="true" data_ref="input" label="Column with reference species position" />

    <param name="preamble_names" type="text" area="true" size="5x40" label="Preamble column names">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <param name="names" type="data" format="txt" label="Names dataset" />

    <param name="species" type="text" label="Focus species">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <param name="dbkey" type="genomebuild" label="Reference species" />

    <param name="output_type" type="select" label="Output format">
      <option value="gd_snp" selected="true">gd_snp</option>
      <option value="gd_genotype">gd_genotype</option>
    </param>
  </inputs>

  <outputs>
    <data name="output" format="gd_snp">
      <change_format>
        <when input="output_type" value="gd_genotype" format="gd_genotype" />
      </change_format>
    </data>
  </outputs>

  <!--
  <tests>
    <test>
      <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
      <param name="p1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" />
      <param name="lo_coverage" value="0" />
      <param name="hi_coverage" value="1000" />
      <param name="low_ind_cov" value="3" />
      <param name="lo_quality" value="30" />
      <output name="output" file="test_out/modify_snp_table/modify.gd_snp" />
    </test>
  </tests>
  -->

  <help>
**Dataset formats**

The input datasets are in tabular_ and text_ formats.
The output dataset is in gd_snp_ or gd_genotype_ format.  (`Dataset missing?`_)

.. _tabular: ./static/formatHelp.html#tab
.. _text: ./static/formatHelp.html#text
.. _gd_snp: ./static/formatHelp.html#gd_snp
.. _gd_genotype: ./static/formatHelp.html#gd_genotype
.. _Dataset missing?: ./static/formatHelp.html

-----

**What it does**

This tool simplifies the job of creating a Galaxy file with format gd_snp
or gd_genotype.  Often, the most complex part of preparing one of these
files is to specify how individuals are related to columns of the table,
a task facilitated by this command.  Each gd_snp or gd_genotype file
typically has columnns giving:

1. scaffold/contig name
2. zero-based position in the scaffold/contig
3. reference species chromosome
4. zero-based position in the reference species chromosome

The user needs to specify the columns containing these data.  Columns are
numbered starting with 1.  The user also specifies brief column names for
these columns.  When the focus species and the reference species are the
same, the scaffold/contig name and reference species chromosome columns
will be identical, as will the position in the scaffold/contig and
position in the reference species chromosome columns.

To inform Galaxy about the correpondence between individuals and columns
of the table, the user directs the tool to a history item that lists
the individuals in order.  Each line starts with unique name for the
individuals (no embedded space or tab character), followed by an arbitrary
(possibly empty) set of words that are helpful for specifying groups
of individuals.
  </help>
</tool>