view dpmix.xml @ 8:30771a097f14

changed max line length from 5,000 to 50,000
author Richard Burhans <burhans@bx.psu.edu>
date Wed, 20 Jun 2012 14:02:30 -0400
parents e29f4d801bb0
children 9b92372de9f6
line wrap: on
line source

<tool id="gd_dpmix" name="Admixture" version="1.0.0">
  <description>using dynamic programming</description>

  <command interpreter="python">
    dpmix.py "$input" "$data_source" "$switch_penalty" "$ap1_input" "$ap2_input" "$p_input" "$output" "$output2" "$output2.files_path" "$input.dataset.metadata.dbkey" "$input.dataset.metadata.ref" "$GALAXY_DATA_INDEX_DIR" "gd.heterochromatic.loc"
    #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
      #set $arg = '%s:%s' % ($individual_col, $individual)
      "$arg"
    #end for
  </command>

  <inputs>
    <param name="input" type="data" format="snp" label="Dataset">
      <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" />
    </param>
    <param name="ap1_input" type="data" format="ind" label="Ancestral population 1 individuals" />
    <param name="ap2_input" type="data" format="ind" label="Ancestral population 2 individuals" />
    <param name="p_input" type="data" format="ind" label="Potentially admixed individuals" />

    <param name="data_source" type="select" format="integer" label="Data source">
      <option value="0" selected="true">sequence coverage</option>
      <option value="1">estimated genotype</option>
    </param>

    <param name="switch_penalty" type="integer" min="0" value="10" label="Switch penalty" />
  </inputs>

  <outputs>
    <data name="output" format="tabular" />
    <data name="output2" format="html" />
  </outputs>

  <tests>
    <test>
      <param name="input" value="test_in/sample.snp" ftype="snp" />
      <param name="ap1_input" value="test_in/a.ind" ftype="ind" />
      <param name="ap2_input" value="test_in/b.ind" ftype="ind" />
      <param name="p_input" value="test_in/c.ind" ftype="ind" />
      <param name="data_source" value="0" />
      <param name="switch_penalty" value="10" />

      <output name="output" file="test_out/dpmix/dpmix.tabular" />

      <output name="output2" file="test_out/dpmix/dpmix.html" ftype="html" compare="diff" lines_diff="2">
        <extra_files type="file" name="dpmix.pdf" value="test_out/dpmix/dpmix.pdf" compare="sim_size" delta = "10000" />
        <extra_files type="file" name="misc.txt" value="test_out/dpmix/misc.txt" />
      </output>
    </test>
  </tests>

  <help>
**What it does**

The user specifies two "ancestral" populations (i.e., sources for
chromosomes) and a set of potentially admixed individuals, and chooses
between the sequence coverage or the estimated genotypes to measure
the similarity of genomic intervals in admixed individuals to the two
classes of ancestral chromosomes.  The user also picks a "switch penalty",
typically between 10 and 100.  For each potentially admixed individual,
the program divides the genome into three "genotypes": (0) homozygous
for the second ancestral population (i.e., both chromosomes from that
population), (1) heterozygous, or (2) homozygous for the second ancestral
population.  Parts of a chromosome that are labeled as "heterochromatic"
are given the non-genotype, 3.  Smaller values of the switch penalty
(corresponding to more ancient admixture events) generally lead to the
reconstruction of more frequent changes between genotypes.
  </help>
</tool>