|
12
|
1 <tool id="gd_dpmix" name="Admixture" version="1.0.0">
|
|
|
2 <description>using dynamic programming</description>
|
|
|
3
|
|
|
4 <command interpreter="python">
|
|
|
5 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"
|
|
|
6 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
|
|
|
7 #set $arg = '%s:%s' % ($individual_col, $individual)
|
|
|
8 "$arg"
|
|
|
9 #end for
|
|
|
10 </command>
|
|
|
11
|
|
|
12 <inputs>
|
|
|
13 <param name="input" type="data" format="gd_snp" label="Dataset">
|
|
|
14 <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" />
|
|
|
15 </param>
|
|
|
16 <param name="ap1_input" type="data" format="gd_indivs" label="Ancestral population 1 individuals" />
|
|
|
17 <param name="ap2_input" type="data" format="gd_indivs" label="Ancestral population 2 individuals" />
|
|
|
18 <param name="p_input" type="data" format="gd_indivs" label="Potentially admixed individuals" />
|
|
|
19
|
|
|
20 <param name="data_source" type="select" format="integer" label="Data source">
|
|
|
21 <option value="0" selected="true">sequence coverage</option>
|
|
|
22 <option value="1">estimated genotype</option>
|
|
|
23 </param>
|
|
|
24
|
|
|
25 <param name="switch_penalty" type="integer" min="0" value="10" label="Switch penalty" />
|
|
|
26 </inputs>
|
|
|
27
|
|
|
28 <outputs>
|
|
|
29 <data name="output" format="tabular" />
|
|
|
30 <data name="output2" format="html" />
|
|
|
31 </outputs>
|
|
|
32
|
|
|
33 <tests>
|
|
|
34 <test>
|
|
|
35 <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
|
|
|
36 <param name="ap1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" />
|
|
|
37 <param name="ap2_input" value="test_in/b.gd_indivs" ftype="gd_indivs" />
|
|
|
38 <param name="p_input" value="test_in/c.gd_indivs" ftype="gd_indivs" />
|
|
|
39 <param name="data_source" value="0" />
|
|
|
40 <param name="switch_penalty" value="10" />
|
|
|
41
|
|
|
42 <output name="output" file="test_out/dpmix/dpmix.tabular" />
|
|
|
43
|
|
|
44 <output name="output2" file="test_out/dpmix/dpmix.html" ftype="html" compare="diff" lines_diff="2">
|
|
|
45 <extra_files type="file" name="dpmix.pdf" value="test_out/dpmix/dpmix.pdf" compare="sim_size" delta = "10000" />
|
|
|
46 <extra_files type="file" name="misc.txt" value="test_out/dpmix/misc.txt" />
|
|
|
47 </output>
|
|
|
48 </test>
|
|
|
49 </tests>
|
|
|
50
|
|
|
51 <help>
|
|
|
52 **What it does**
|
|
|
53
|
|
|
54 The user specifies two "ancestral" populations (i.e., sources for
|
|
|
55 chromosomes) and a set of potentially admixed individuals, and chooses
|
|
|
56 between the sequence coverage or the estimated genotypes to measure
|
|
|
57 the similarity of genomic intervals in admixed individuals to the two
|
|
|
58 classes of ancestral chromosomes. The user also picks a "switch penalty",
|
|
|
59 typically between 10 and 100. For each potentially admixed individual,
|
|
|
60 the program divides the genome into three "genotypes": (0) homozygous
|
|
|
61 for the second ancestral population (i.e., both chromosomes from that
|
|
|
62 population), (1) heterozygous, or (2) homozygous for the second ancestral
|
|
|
63 population. Parts of a chromosome that are labeled as "heterochromatic"
|
|
|
64 are given the non-genotype, 3. Smaller values of the switch penalty
|
|
|
65 (corresponding to more ancient admixture events) generally lead to the
|
|
|
66 reconstruction of more frequent changes between genotypes.
|
|
|
67 </help>
|
|
|
68 </tool>
|
