annotate evaluate_population_numbers.xml @ 0:2c498d40ecde

Uploaded
author miller-lab
date Mon, 09 Apr 2012 12:03:06 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
1 <tool id="gd_evaluate_population_numbers" name="Evaluate" version="1.0.0">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
2 <description>possible numbers of populations</description>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
3
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
4 <command interpreter="bash">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
5 evaluate_population_numbers.bash "${input.extra_files_path}/admix.ped" "$output" "$max_populations"
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
6 </command>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
7
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
8 <inputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
9 <param name="input" type="data" format="wped" label="Dataset" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
10 <param name="max_populations" type="integer" min="1" value="5" label="Maximum number of populations" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
11 </inputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
12
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
13 <outputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
14 <data name="output" format="txt" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
15 </outputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
16
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
17 <!--
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
18 <tests>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
19 <test>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
20 <param name="input" value="fake" ftype="wped" >
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
21 <metadata name="base_name" value="admix" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
22 <composite_data value="test_out/prepare_population_structure/prepare_population_structure.html" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
23 <composite_data value="test_out/prepare_population_structure/admix.ped" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
24 <composite_data value="test_out/prepare_population_structure/admix.map" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
25 <edit_attributes type="name" value="fake" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
26 </param>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
27 <param name="max_populations" value="2" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
28
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
29 <output name="output" file="test_out/evaluate_population_numbers/evaluate_population_numbers.txt" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
30 </test>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
31 </tests>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
32 -->
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
33
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
34 <help>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
35 **What it does**
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
36
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
37 The users selects a set of data generated by the Galaxy tool to "prepare
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
38 to look for population structure". For all possible numbers K of ancestral
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
39 populations, from 1 up to a user-specified maximum, this tool produces values
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
40 that indicate how well the data can be explained as genotypes from individuals
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
41 derived from K ancestral populations. These values are computed by a 5-fold
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
42 cross-validation procedure, so that a good choice for K will exhibit a low
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
43 cross-validation error compared with other potential settings for K.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
44
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
45 **Acknowledgments**
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
46
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
47 We use the program "Admixture", downloaded from
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
48
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
49 http://www.genetics.ucla.edu/software/admixture/
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
50
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
51 and described in the paper "Fast model-based estimation of ancestry in
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
52 unrelated individuals" by David H. Alexander, John Novembre and Kenneth Lange,
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
53 Genome Research 19 (2009), pp. 1655-1664. Admixture is called with the "--cv"
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
54 flag to produce these values.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
55 </help>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
56 </tool>