annotate add_fst_column.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
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_add_fst_column" name="Add an FST column" version="1.0.0">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
2 <description>to a table</description>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
3
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
4 <command interpreter="python">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
5 add_fst_column.py "$input" "$p1_input" "$p2_input" "$data_source" "$min_reads" "$min_qual" "$retain" "$discard_fixed" "$biased" "$output"
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
6 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
7 #set $arg = '%s:%s' % ($individual_col, $individual)
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
8 "$arg"
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
9 #end for
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
10 </command>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
11
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
12 <inputs>
7
e29f4d801bb0 change wsf -> snp; wpf -> sap
Richard Burhans <burhans@bx.psu.edu>
parents: 0
diff changeset
13 <param name="input" type="data" format="snp" label="SNP table" />
0
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
14 <param name="p1_input" type="data" format="ind" label="Population 1 individuals" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
15 <param name="p2_input" type="data" format="ind" label="Population 2 individuals" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
16
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
17 <param name="data_source" type="select" format="integer" label="Data source">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
18 <option value="0" selected="true">sequence coverage</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
19 <option value="1">estimated genotype</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
20 </param>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
21
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
22 <param name="min_reads" type="integer" min="0" value="0" label="Minimum total read count for a population" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
23 <param name="min_qual" type="integer" min="0" value="0" label="Minimum individual genotype quality" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
24
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
25 <param name="retain" type="select" label="Special treatment">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
26 <option value="0" selected="true">Skip row</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
27 <option value="1">Set FST = -1</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
28 </param>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
29
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
30 <param name="discard_fixed" type="select" label="Apparently fixed SNPs">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
31 <option value="0">Retain SNPs that appear fixed in the two populations</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
32 <option value="1" selected="true">Delete SNPs that appear fixed in the two populations</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
33 </param>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
34
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
35 <param name="biased" type="select" label="FST estimator">
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
36 <option value="0" selected="true">Wright's original definition</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
37 <option value="1">Weir's unbiased estimator</option>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
38 </param>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
39
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
40 </inputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
41
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
42 <outputs>
7
e29f4d801bb0 change wsf -> snp; wpf -> sap
Richard Burhans <burhans@bx.psu.edu>
parents: 0
diff changeset
43 <data name="output" format="snp" metadata_source="input" />
0
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
44 </outputs>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
45
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
46 <tests>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
47 <test>
7
e29f4d801bb0 change wsf -> snp; wpf -> sap
Richard Burhans <burhans@bx.psu.edu>
parents: 0
diff changeset
48 <param name="input" value="test_in/sample.snp" ftype="snp" />
0
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
49 <param name="p1_input" value="test_in/a.ind" ftype="ind" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
50 <param name="p2_input" value="test_in/b.ind" ftype="ind" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
51 <param name="data_source" value="0" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
52 <param name="min_reads" value="3" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
53 <param name="min_qual" value="0" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
54 <param name="retain" value="0" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
55 <param name="discard_fixed" value="1" />
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
56 <param name="biased" value="0" />
7
e29f4d801bb0 change wsf -> snp; wpf -> sap
Richard Burhans <burhans@bx.psu.edu>
parents: 0
diff changeset
57 <output name="output" file="test_out/add_fst_column/add_fst_column.snp" />
0
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
58 </test>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
59 </tests>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
60
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
61 <help>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
62 **What it does**
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
63
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
64 The user specifies a SNP table and two "populations" of individuals,
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
65 both previously defined using the Galaxy tool to select individuals from
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
66 a SNP table. No individual can be in both populations. Other choices are
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
67 as follows.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
68
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
69 Data source. The allele frequencies of a SNP in the two populations can be
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
70 estimated either by the total number of reads of each allele, or by adding
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
71 the frequencies inferred from genotypes of individuals in the populations.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
72
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
73 After specifying the data source, the user sets lower bounds on amount
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
74 of data required at a SNP. For estimating the Fst using read counts,
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
75 the bound is the minimum count of reads of the two alleles in a population.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
76 For estimations based on genotype, the bound is the minimum reported genotype
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
77 quality per individual.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
78
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
79 The user specifies whether the SNPs that violate the lower bound should be
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
80 ignored or the Fst set to -1.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
81
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
82 The user specifies whether SNPs where both populations appear to be fixed
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
83 for the same allele should be retained or discarded.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
84
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
85 Finally, the user chooses which definition of Fst to use: Wright's original
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
86 definition or Weir's unbiased estimator.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
87
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
88 A column is appended to the SNP table giving the Fst for each retained SNP.
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
89 </help>
2c498d40ecde Uploaded
miller-lab
parents:
diff changeset
90 </tool>