Mercurial > repos > miller-lab > genome_diversity

comparison average_fst.xml @ 24:248b06e86022

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added gd_genotype datatype. Modified tools to support new datatype.
author Richard Burhans <burhans@bx.psu.edu>
date Tue, 28 May 2013 16:24:19 -0400
parents 95a05c1ef5d5
children 8997f2ca8c7a
comparison
equal deleted inserted replaced
23:66a183c44dd5 24:248b06e86022
1 <tool id="gd_average_fst" name="Overall FST" version="1.2.0"> 1 <tool id="gd_average_fst" name="Overall FST" version="1.3.0">
2 <description>: Estimate the relative fixation index between two populations</description> 2 <description>: Estimate the relative fixation index between two populations</description>
3 3
4 <command interpreter="python"> 4 <command interpreter="python">
5 average_fst.py "$input" "$p1_input" "$p2_input" "$data_source.ds_choice" "$data_source.min_value" "$discard_fixed" "$output" 5 average_fst.py "$input" "$p1_input" "$p2_input"
6 #if $use_randomization.ur_choice == '1' 6 #if $input_type.choice == '0'
7 "gd_snp" "$input_type.data_source.choice"
8 #if $input_type.data_source.choice == '0'
9 "$input_type.data_source.min_value"
10 #else if $input_type.data_source.choice == '1'
11 "1"
12 #end if
13 #else if $input_type.choice == '1'
14 "gd_genotype" "1" "1"
15 #end if
16 "$discard_fixed" "$output"
17 #if $use_randomization.choice == '0'
18 "0" "/dev/null"
19 #else if $use_randomization.choice == '1'
7 "$use_randomization.shuffles" "$use_randomization.p0_input" 20 "$use_randomization.shuffles" "$use_randomization.p0_input"
8 #else
9 "0" "/dev/null"
10 #end if 21 #end if
11 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns) 22 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
12 #set $arg = '%s:%s' % ($individual_col, $individual) 23 #set $arg = '%s:%s' % ($individual_col, $individual)
13 "$arg" 24 "$arg"
14 #end for 25 #end for
15 </command> 26 </command>
16 27
17 <inputs> 28 <inputs>
18 <param name="input" type="data" format="gd_snp" label="SNP dataset" /> 29 <conditional name="input_type">
30 <param name="choice" type="select" format="integer" label="Input format">
31 <option value="0" selected="true">gd_snp</option>
32 <option value="1">gd_genotype</option>
33 </param>
34
35 <when value="0">
36 <param name="input" type="data" format="gd_snp" label="SNP dataset" />
37
38 <conditional name="data_source">
39 <param name="choice" type="select" format="integer" label="Frequency metric">
40 <option value="0">sequence coverage</option>
41 <option value="1" selected="true">estimated genotype</option>
42 </param>
43
44 <when value="0">
45 <param name="min_value" type="integer" min="1" value="1" label="Minimum total read count for a population" />
46 </when>
47
48 <when value="1"/>
49 </conditional>
50 </when>
51
52 <when value="1">
53 <param name="input" type="data" format="gd_genotype" label="Genotype dataset" />
54 </when>
55 </conditional>
56
19 <param name="p1_input" type="data" format="gd_indivs" label="Population 1 individuals" /> 57 <param name="p1_input" type="data" format="gd_indivs" label="Population 1 individuals" />
20 <param name="p2_input" type="data" format="gd_indivs" label="Population 2 individuals" /> 58 <param name="p2_input" type="data" format="gd_indivs" label="Population 2 individuals" />
21
22 <conditional name="data_source">
23 <param name="ds_choice" type="select" format="integer" label="Frequency metric">
24 <option value="0">sequence coverage</option>
25 <option value="1" selected="true">estimated genotype</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 59
35 <param name="discard_fixed" type="select" label="For SNPs that appear to be fixed across both populations"> 60 <param name="discard_fixed" type="select" label="For SNPs that appear to be fixed across both populations">
36 <option value="0">retain</option> 61 <option value="0">retain</option>
37 <option value="1" selected="true">delete</option> 62 <option value="1" selected="true">delete</option>
38 </param> 63 </param>
39 64
40 <conditional name="use_randomization"> 65 <conditional name="use_randomization">
41 <param name="ur_choice" type="select" format="integer" label="Use randomization"> 66 <param name="choice" type="select" format="integer" label="Use randomization">
42 <option value="0" selected="true">no</option> 67 <option value="0" selected="true">no</option>
43 <option value="1">yes</option> 68 <option value="1">yes</option>
44 </param> 69 </param>
45 <when value="0" /> 70 <when value="0" />
46 <when value="1"> 71 <when value="1">
60 <param name="p1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" /> 85 <param name="p1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" />
61 <param name="p2_input" value="test_in/b.gd_indivs" ftype="gd_indivs" /> 86 <param name="p2_input" value="test_in/b.gd_indivs" ftype="gd_indivs" />
62 <param name="ds_choice" value="0" /> 87 <param name="ds_choice" value="0" />
63 <param name="min_value" value="3" /> 88 <param name="min_value" value="3" />
64 <param name="discard_fixed" value="1" /> 89 <param name="discard_fixed" value="1" />
65 <param name="ur_choice" value="0" /> 90 <param name="choice" value="0" />
66 <output name="output" file="test_out/average_fst/average_fst.txt" /> 91 <output name="output" file="test_out/average_fst/average_fst.txt" />
67 </test> 92 </test>
68 </tests> 93 </tests>
69 94
70 <help> 95 <help>
71 96
72 **Dataset formats** 97 **Dataset formats**
73 98
74 The input datasets are in gd_snp_ and gd_indivs_ formats. 99 The input datasets are in gd_snp_, gd_genotype_, and gd_indivs_ formats.
75 The output dataset is in text_ format. (`Dataset missing?`_) 100 The output dataset is in text_ format. (`Dataset missing?`_)
76 101
77 .. _gd_snp: ./static/formatHelp.html#gd_snp 102 .. _gd_snp: ./static/formatHelp.html#gd_snp
103 .. _gd_genotype: ./static/formatHelp.html#gd_genotype
78 .. _gd_indivs: ./static/formatHelp.html#gd_indivs 104 .. _gd_indivs: ./static/formatHelp.html#gd_indivs
79 .. _text: ./static/formatHelp.html#text 105 .. _text: ./static/formatHelp.html#text
80 .. _Dataset missing?: ./static/formatHelp.html 106 .. _Dataset missing?: ./static/formatHelp.html
81 107
82 ----- 108 -----
83 109
84 **What it does** 110 **What it does**
85 111
86 The user specifies a SNP table and two "populations" of individuals, both previously defined using the Galaxy tool to specify individuals from a SNP table. No individual can be in both populations. Other choices are as follows. 112 The user specifies a SNP table and two "populations" of individuals, both previously defined using the Galaxy tool to specify individuals from a SNP table. No individual can be in both populations. Other choices are as follows.
87 113
88 Frequency metric. The allele frequencies of a SNP in the two populations can be estimated either by the total number of reads of each allele, or by adding the frequencies inferred from genotypes of individuals in the populations. 114 Frequency metric. The allele frequencies of a SNP in the two populations can be estimated either by the total number of reads of each allele (if the table is in gd_snp format, but not with gd_genotype), or by adding the frequencies inferred from genotypes of individuals in the populations.
89 115
90 After specifying the frequency metric, the user sets lower bounds on amount of data required at a SNP. For estimating the FST using read counts, the bound is the minimum count of reads of the two alleles in a population. For estimations based on genotype, the bound is the minimum reported genotype quality per individual. SNPs not meeting these lower bounds are ignored. 116 After specifying the frequency metric, the user sets lower bounds on amount of data required at a SNP. For estimating the FST using read counts, the bound is the minimum count of reads of the two alleles in a population. For estimations based on genotype, the bound is the minimum reported genotype quality per individual. SNPs not meeting these lower bounds are ignored.
91 117
92 The user specifies whether SNPs where both populations appear to be fixed for the same allele should be retained or discarded. 118 The user specifies whether SNPs where both populations appear to be fixed for the same allele should be retained or discarded.
93 119