|
1
|
1 <tool id="gd_average_fst" name="Average FST" version="1.0.0">
|
|
|
2 <description>of two populations</description>
|
|
|
3
|
|
|
4 <command interpreter="python">
|
|
|
5 average_fst.py "$input" "$p1_input" "$p2_input" "$data_source.ds_choice" "$data_source.min_value" "$discard_fixed" "$biased" "$output"
|
|
|
6 #if $use_randomization.ur_choice == '1'
|
|
|
7 "$use_randomization.shuffles" "$use_randomization.p0_input"
|
|
|
8 #else
|
|
|
9 "0" "/dev/null"
|
|
|
10 #end if
|
|
|
11 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
|
|
|
12 #set $arg = '%s:%s' % ($individual_col, $individual)
|
|
|
13 "$arg"
|
|
|
14 #end for
|
|
|
15 </command>
|
|
|
16
|
|
|
17 <inputs>
|
|
|
18 <param name="input" type="data" format="wsf" label="SNP table" />
|
|
|
19 <param name="p1_input" type="data" format="ind" label="Population 1 individuals" />
|
|
|
20 <param name="p2_input" type="data" format="ind" label="Population 2 individuals" />
|
|
|
21
|
|
|
22 <conditional name="data_source">
|
|
|
23 <param name="ds_choice" type="select" format="integer" label="Data source">
|
|
|
24 <option value="0" selected="true">sequence coverage and ..</option>
|
|
|
25 <option value="1">estimated genotype and ..</option>
|
|
|
26 </param>
|
|
|
27 <when value="0">
|
|
|
28 <param name="min_value" type="integer" min="1" value="1" label="Minimum total read count for a population" />
|
|
|
29 </when>
|
|
|
30 <when value="1">
|
|
|
31 <param name="min_value" type="integer" min="1" value="1" label="Minimum individual genotype quality" />
|
|
|
32 </when>
|
|
|
33 </conditional>
|
|
|
34
|
|
|
35 <param name="discard_fixed" type="select" label="Apparently fixed SNPs">
|
|
|
36 <option value="0">Retain SNPs that appear fixed in the two populations</option>
|
|
|
37 <option value="1" selected="true">Delete SNPs that appear fixed in the two populations</option>
|
|
|
38 </param>
|
|
|
39
|
|
|
40 <param name="biased" type="select" label="FST estimator">
|
|
|
41 <option value="0" selected="true">Wright's original definition</option>
|
|
|
42 <option value="1">Weir's unbiased estimator</option>
|
|
|
43 </param>
|
|
|
44
|
|
|
45 <conditional name="use_randomization">
|
|
|
46 <param name="ur_choice" type="select" format="integer" label="Use randomization">
|
|
|
47 <option value="0" selected="true">No</option>
|
|
|
48 <option value="1">Yes</option>
|
|
|
49 </param>
|
|
|
50 <when value="0" />
|
|
|
51 <when value="1">
|
|
|
52 <param name="shuffles" type="integer" min="0" value="0" label="Shuffles" />
|
|
|
53 <param name="p0_input" type="data" format="ind" label="Individuals for randomization" />
|
|
|
54 </when>
|
|
|
55 </conditional>
|
|
|
56 </inputs>
|
|
|
57
|
|
|
58 <outputs>
|
|
|
59 <data name="output" format="txt" />
|
|
|
60 </outputs>
|
|
|
61
|
|
|
62 <tests>
|
|
|
63 <test>
|
|
|
64 <param name="input" value="genome_diversity/test_in/sample.wsf" ftype="wsf" />
|
|
|
65 <param name="p1_input" value="genome_diversity/test_in/a.ind" ftype="ind" />
|
|
|
66 <param name="p2_input" value="genome_diversity/test_in/b.ind" ftype="ind" />
|
|
|
67 <param name="ds_choice" value="0" />
|
|
|
68 <param name="min_value" value="3" />
|
|
|
69 <param name="discard_fixed" value="1" />
|
|
|
70 <param name="biased" value="0" />
|
|
|
71 <param name="ur_choice" value="0" />
|
|
|
72 <output name="output" file="genome_diversity/test_out/average_fst/average_fst.txt" />
|
|
|
73 </test>
|
|
|
74 </tests>
|
|
|
75
|
|
|
76 <help>
|
|
|
77 **What it does**
|
|
|
78
|
|
|
79 The user specifies a SNP table and two "populations" of individuals,
|
|
|
80 both previously defined using the Galaxy tool to select individuals from
|
|
|
81 a SNP table. No individual can be in both populations. Other choices are
|
|
|
82 as follows.
|
|
|
83
|
|
|
84 Data source. The allele frequencies of a SNP in the two populations can be
|
|
|
85 estimated either by the total number of reads of each allele, or by adding
|
|
|
86 the frequencies inferred from genotypes of individuals in the populations.
|
|
|
87
|
|
|
88 After specifying the data source, the user sets lower bounds on amount
|
|
|
89 of data required at a SNP. For estimating the Fst using read counts,
|
|
|
90 the bound is the minimum count of reads of the two alleles in a population.
|
|
|
91 For estimations based on genotype, the bound is the minimum reported genotype
|
|
|
92 quality per individual. SNPs not meeting these lower bounds are ignored.
|
|
|
93
|
|
|
94 The user specifies whether SNPs where both populations appear to be fixed
|
|
|
95 for the same allele should be retained or discarded.
|
|
|
96
|
|
|
97 The user chooses which definition of Fst to use: Wright's original definition
|
|
|
98 or Weir's unbiased estimator.
|
|
|
99
|
|
|
100 Finally, the user decides whether to use randomizations. If so, then the
|
|
|
101 user specifies how many randomly generated population pairs (retaining
|
|
|
102 the numbers of individuals of the originals) to generate, as well as the
|
|
|
103 "population" of additional individuals (not in the first two populations)
|
|
|
104 that can be used in the randomization process.
|
|
|
105
|
|
|
106 The program prints the average Fst for the original populations and the
|
|
|
107 number of SNPs used to compute it. If randomizations were requested,
|
|
|
108 it prints the average Fst for each randomly generated population pair,
|
|
|
109 ending with a summary that includes the maximum and average value, and the
|
|
|
110 highest-scoring population pair.
|
|
|
111 </help>
|
|
|
112 </tool>
|
