annotate select_snps.xml @ 24:248b06e86022

Added gd_genotype datatype. Modified tools to support new datatype.

<tool id="gd_select_snps" name="Sample SNPs" version="1.0.0">
  <description>: Select a specified number of SNPs, uniformly spaced</description>

  <command interpreter="python">
    select_snps.py "--input=$input" "--output=$output" "--index_dir=$GALAXY_DATA_INDEX_DIR" "--num_snps=$num_snps"
    #if $override_metadata.choice == "0":
      "--ref_chrom_col=${input.metadata.ref}" "--ref_pos_col=${input.metadata.rPos}" "--ref_species=${input.metadata.dbkey}"
    #else
      "--ref_chrom_col=$ref_col" "--ref_pos_col=$rpos_col" "--ref_species=$ref_species"
    #end if
  </command>

  <inputs>
    <param format="tabular" name="input" type="data" label="SNP dataset">
      <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" />
    </param>
    <param name="num_snps" type="integer" value="10" optional="false" min="1" label="Number of SNPs"/>
    <conditional name="override_metadata">
      <param name="choice" type="select" format="integer" label="Choose columns" help="Datasets in gd_snp format have the column information in the metadata, all others must be chosen." >
        <option value="0" selected="true">No, get columns from metadata</option>
        <option value="1" >Yes, choose columns</option>
      </param>
      <when value="0" />
      <when value="1">
        <param name="ref_col" type="data_column" data_ref="input" numerical="false" label="Column with reference chromosome"/>
        <param name="rpos_col" type="data_column" data_ref="input" numerical="true" label="Column with reference position"/>
        <param name="ref_species" type="select" label="Choose reference species">
          <options from_file="gd.ref_species.txt">
            <column name="name" index="1"/>
            <column name="value" index="0"/>
          </options>
        </param>
      </when>
    </conditional>
  </inputs>

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

  <tests>
    <test>
      <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp"/>
      <param name="num_snps" value="100"/>
      <param name="choice" value="0"/>
      <output name="output" file="test_out/select_snps/select_snps.gd_snp" />
    </test>
  </tests>


  <help>

**Dataset formats**

The input and output datasets are in tabular_ format.
(`Dataset missing?`_)

.. _tabular: ./static/formatHelp.html#tab
.. _Dataset missing?: ./static/formatHelp.html

-----

**What it does**

This tool attempts to select a specified number of SNPs from the dataset, making
them approximately uniformly spaced relative to the reference genome. The number
actually selected may be slightly more than the specified number.

-----

**Example**

- input (gd_snp format)::

    chr2_75111355_75112576    314  A  C  L  F  chr2   75111676  C  F  15  4  53   2   9  48   Y  96   0.369  0.355  0.396  0
    chr8_93901796_93905612   2471  A  C  A  A  chr8   93904264  A  A  8   0  51   10  2  14   Y  961  0.016  0.534  0.114  2
    chr10_7434473_7435447    524   T  C  S  S  chr10  7435005   T  S  11  5  90   14  0  69   Y  626  0.066  0.406  0.727  0
    chr14_80021455_80022064  138   G  A  H  H  chr14  80021593  G  H  14  0  69   9   6  124  Y  377  0.118  0.997  0.195  1
    chr15_64470252_64471048  89    G  A  Y  Y  chr15  64470341  G  Y  5   6  109  14  0  69   Y  312  0.247  0.998  0.393  0
    chr18_48070585_48071386  514   C  T  E  K  chr18  48071100  T  K  7   7  46   14  0  69   Y  2    0.200  0.032  0.163  0
    chr18_50154905_50155664  304   A  G  Y  C  chr18  50155208  A  Y  4   2  17   5   1  22   Y  8    0.022  0.996  0.128  0
    chr18_57379354_57380496  315   C  T  V  V  chr18  57379669  G  V  11  0  60   9   6  62   Y  726  0.118  0.048  0.014  1
    chr19_14240610_14242055  232   C  T  A  V  chr19  14240840  C  A  18  8  56   15  5  42   Y  73   0.003  0.153  0.835  0
    chr19_39866997_39874915  3117  C  T  P  P  chr19  39870110  C  P  3   7  65   14  2  32   Y  6    0.321  0.911  0.462  4
    etc.

- output::

    chr2_75111355_75112576    314  A  C  L  F  chr2   75111676  C  F  15  4  53   2   9  48   Y  96   0.369  0.355  0.396  0
    chr8_93901796_93905612   2471  A  C  A  A  chr8   93904264  A  A  8   0  51   10  2  14   Y  961  0.016  0.534  0.114  2
    chr10_7434473_7435447    524   T  C  S  S  chr10  7435005   T  S  11  5  90   14  0  69   Y  626  0.066  0.406  0.727  0
    chr14_80021455_80022064  138   G  A  H  H  chr14  80021593  G  H  14  0  69   9   6  124  Y  377  0.118  0.997  0.195  1
    chr15_64470252_64471048  89    G  A  Y  Y  chr15  64470341  G  Y  5   6  109  14  0  69   Y  312  0.247  0.998  0.393  0
    chr18_48070585_48071386  514   C  T  E  K  chr18  48071100  T  K  7   7  46   14  0  69   Y  2    0.200  0.032  0.163  0
    chr19_14240610_14242055  232   C  T  A  V  chr19  14240840  C  A  18  8  56   15  5  42   Y  73   0.003  0.153  0.835  0
    etc.

  </help>
</tool>