annotate filter_gd_snp.xml @ 39:e56023008e36 default tip

Changed revision of package_fisher_0_1_4 to be2fc454d121 Changed revision of package_matplotlib_1_2 to a03ee94316b5

<tool id="gd_filter_gd_snp" name="Filter SNPs" version="1.2.0">
  <description>: Discard some SNPs based on coverage, quality or spacing</description>

  <command interpreter="python">
    #import json
    #import base64
    #import zlib
    #set $ind_names = $input.dataset.metadata.individual_names
    #set $ind_colms = $input.dataset.metadata.individual_columns
    #set $ind_dict = dict(zip($ind_names, $ind_colms))
    #set $ind_json = json.dumps($ind_dict, separators=(',',':'))
    #set $ind_comp = zlib.compress($ind_json, 9)
    #set $ind_arg = base64.b64encode($ind_comp)
    filter_gd_snp.py '$input' '$output'
    #if str($input.dataset.metadata.dbkey) == '?'
      '0'
    #else
      '$input.dataset.metadata.ref'
    #end if
    '$min_spacing' '$lo_genotypes' '$input_type.p1_input'
    #if $input_type.choice == '0'
      'gd_snp' '$input_type.lo_coverage' '$input_type.hi_coverage' '$input_type.low_ind_cov' '$input_type.lo_quality'
    #else if $input_type.choice == '1'
      'gd_genotype' '0' '0' '0' '0'
    #end if
    '$ind_arg'
  </command>

  <inputs>
    <conditional name="input_type">
      <param name="choice" type="select" format="integer" label="Input format">
        <option value="0" selected="true">gd_snp</option>
        <option value="1">gd_genotype</option>
      </param>
      <when value="0">
        <param name="input" type="data" format="gd_snp" label="SNP dataset" />
        <param name="p1_input" type="data" format="gd_indivs" label="Population individuals" />
        <param name="lo_coverage" type="text" value="0" label="Lower bound on total coverage">
          <sanitizer>
            <valid initial="string.digits">
              <!-- &#37; is the percent (%) character -->
              <add value="&#37;" />
            </valid>
          </sanitizer>
        </param>
        <param name="hi_coverage" type="text" value="1000" label="Upper bound on total coverage">
          <sanitizer>
            <valid initial="string.digits">
              <!-- &#37; is the percent (%) character -->
              <add value="&#37;" />
            </valid>
          </sanitizer>
        </param>
        <param name="low_ind_cov" type="integer" min="0" value="0" label="Lower bound on individual coverage" />
        <param name="lo_quality" type="integer" min="0" value="0" label="Lower bound on individual quality values" />
      </when>
      <when value="1">
        <param name="input" type="data" format="gd_genotype" label="Genotype dataset" />
        <param name="p1_input" type="data" format="gd_indivs" label="Population individuals" />
      </when>
    </conditional>
    <param name="min_spacing" type="integer" min="0" value="0" label="Minimum spacing between SNPs" />
    <param name="lo_genotypes" type="integer" min="0" value="0" label="Lower bound on the number of defined genotypes" />
  </inputs>

  <outputs>
    <data name="output" format="input" format_source="input" metadata_source="input" />
  </outputs>

  <requirements>
    <requirement type="package" version="0.1">gd_c_tools</requirement>
  </requirements>

  <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 gd_snp_, gd_genotype_, and gd_indivs_ formats.
The output dataset is in gd_snp_ or gd_genotype_ format.  (`Dataset missing?`_)

.. _gd_snp: ./static/formatHelp.html#gd_snp
.. _gd_genotype: ./static/formatHelp.html#gd_genotype
.. _gd_indivs: ./static/formatHelp.html#gd_indivs
.. _Dataset missing?: ./static/formatHelp.html

-----

**What it does**

For a gd_snp dataset, the user specifies that some of the individuals
form a "population", by supplying a list that has been previously created
using the Specify Individuals tool.  SNPs are then discarded if their
total coverage for the population is too low or too high, or if their
coverage or quality score for any individual in the population is too low.

The upper and lower bounds on total population coverage can be specified
either as read counts or as percentiles (e.g. "5%", with no decimal
places).  For percentile bounds the SNPs are ranked by read count, so
for example, a lower bound of "10%" means that the least-covered 10%
of the SNPs will be discarded, while an upper bound of, say, "80%" will
discard all SNPs above the 80% mark, i.e. the top 20%.  The threshold
for the lower bound on individual coverage can only be specified as a
plain read count.

For either a gd_snp or gd_genotype dataset, the user can specify a
minimum number of defined genotypes (i.e., not -1) and/or a minimum
spacing relative to the reference sequence.  An error is reported if the
user requests a minimum spacing but no reference sequence is available.

-----

**Example**

- input gd_snp::

    Contig161_chr1_4641264_4641879   115  C  T  73.5   chr1   4641382  C   6  0  2  45   8  0  2  51   15  0  2  72   5  0  2  42   6  0  2  45   10  0  2  57   Y  54  0.323  0
    Contig48_chr1_10150253_10151311   11  A  G  94.3   chr1  10150264  A   1  0  2  30   1  0  2  30    1  0  2  30   3  0  2  36   1  0  2  30    1  0  2  30   Y  22  +99.   0
    Contig20_chr1_21313469_21313570   66  C  T  54.0   chr1  21313534  C   4  0  2  39   4  0  2  39    5  0  2  42   4  0  2  39   4  0  2  39    5  0  2  42   N   1  +99.   0
    etc.

- input individuals::

    9   PB1
    13  PB2
    17  PB3

- output when the lower bound on individual coverage is "3"::

    Contig161_chr1_4641264_4641879   115  C  T  73.5   chr1   4641382  C   6  0  2  45   8  0  2  51   15  0  2  72   5  0  2  42   6  0  2  45   10  0  2  57   Y  54  0.323  0
    Contig20_chr1_21313469_21313570   66  C  T  54.0   chr1  21313534  C   4  0  2  39   4  0  2  39    5  0  2  42   4  0  2  39   4  0  2  39    5  0  2  42   N   1  +99.   0
    etc.

  </help>
</tool>