|
0
|
1 <tool id="gd_modify_gd_snp" name="Modify gd_snp" version="1.0.0">
|
|
|
2 <description>modify a gd_snp dataset</description>
|
|
|
3
|
|
|
4 <command interpreter="python">
|
|
|
5 modify_snp_table.py "$input" "$p1_input" "$output"
|
|
|
6 #if $limit_coverage.choice == "0"
|
|
|
7 "-1" "-1" "-1" "-1"
|
|
|
8 #else
|
|
|
9 "${limit_coverage.lo_coverage}" "${limit_coverage.hi_coverage}" "${limit_coverage.low_ind_cov}" "${limit_coverage.lo_quality}"
|
|
|
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="gd_snp" label="gd_snp dataset" />
|
|
|
19 <param name="p1_input" type="data" format="gd_indivs" label="Population individuals" />
|
|
|
20 <conditional name="limit_coverage">
|
|
|
21 <param name="choice" type="select" format="integer" label="Option">
|
|
|
22 <option value="0" selected="true">add columns to the gd_snp table</option>
|
|
|
23 <option value="1">discard some SNPs</option>
|
|
|
24 </param>
|
|
|
25 <when value="0" />
|
|
|
26 <when value="1">
|
|
|
27 <param name="lo_coverage" type="integer" min="0" value="0" label="Lower bound on total coverage" />
|
|
|
28 <param name="hi_coverage" type="integer" min="0" value="1000" label="Upper bound on total coverage" />
|
|
|
29 <param name="low_ind_cov" type="integer" min="0" value="0" label="Lower bound on individual coverage" />
|
|
|
30 <param name="lo_quality" type="integer" min="0" value="0" label="Lower bound on individual quality values" />
|
|
|
31 </when>
|
|
|
32 </conditional>
|
|
|
33 </inputs>
|
|
|
34
|
|
|
35 <outputs>
|
|
|
36 <data name="output" format="gd_snp" metadata_source="input" />
|
|
|
37 </outputs>
|
|
|
38
|
|
|
39 <tests>
|
|
|
40 <test>
|
|
|
41 <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
|
|
|
42 <param name="p1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" />
|
|
|
43 <param name="choice" value="1" />
|
|
|
44 <param name="lo_coverage" value="0" />
|
|
|
45 <param name="hi_coverage" value="1000" />
|
|
|
46 <param name="low_ind_cov" value="3" />
|
|
|
47 <param name="lo_quality" value="30" />
|
|
|
48 <output name="output" file="test_out/modify_snp_table/modify.gd_snp" />
|
|
|
49 </test>
|
|
|
50 </tests>
|
|
|
51
|
|
|
52 <help>
|
|
|
53 **Dataset formats**
|
|
|
54
|
|
|
55 The input datasets are gd_snp_ and gd_indivs_ formats.
|
|
|
56 The output dataset is in gd_snp_ format. (`Dataset missing?`_)
|
|
|
57
|
|
|
58 .. _Dataset missing?: ./static/formatHelp.html
|
|
|
59 .. _gd_snp: ./static/formatHelp.html#gd_snp
|
|
|
60 .. _gd_indivs: ./static/formatHelp.html#gd_indivs
|
|
|
61
|
|
|
62 **What it does**
|
|
|
63
|
|
|
64 The user specifies that some of the individuals in the selected gd_snp_ table are
|
|
|
65 form a "population" that has been previously defined using the Galaxy tool to
|
|
|
66 select individuals from a gd_snp dataset. One option is for the program to append
|
|
|
67 four columns to the table, giving the total counts for the two alleles, the
|
|
|
68 "genotype" for the population and the maximum quality value, taken over all
|
|
|
69 individuals in the population. If all defined genotypes in the population
|
|
|
70 are 2 (agree with the reference), the population's genotype is 2; similarly
|
|
|
71 for 0; otherwise the genotype is 1 (unless all individuals have undefined
|
|
|
72 genotype, in which case it is -1. The other option is to remove rows from
|
|
|
73 the table for which the total coverage for the population is either too low
|
|
|
74 or too high, and/or if the individual coverage or quality value is too low.
|
|
|
75
|
|
|
76 .. _gd_snp: ./static/formatHelp.html#gd_snp
|
|
|
77
|
|
|
78 **Examples**
|
|
|
79
|
|
|
80 - input gd_snp::
|
|
|
81
|
|
|
82 Contig161_chr1_4641264_4641879 115 C T 73.5 chr1 4641382 C 6 0 2 45 8 0 2 51 15 0 2 72 5 0 2 42 6 0 2 45 10 0 2 57 Y 54 0.323 0
|
|
|
83 Contig48_chr1_10150253_10151311 11 A G 94.3 chr1 10150264 A 1 0 2 30 1 0 2 30 1 0 2 30 3 0 2 36 1 0 2 30 1 0 2 30 Y 22 +99. 0
|
|
|
84 Contig20_chr1_21313469_21313570 66 C T 54.0 chr1 21313534 C 4 0 2 39 4 0 2 39 5 0 2 42 4 0 2 39 4 0 2 39 5 0 2 42 N 1 +99. 0
|
|
|
85 etc.
|
|
|
86
|
|
|
87 - input individuals::
|
|
|
88
|
|
|
89 9 PB1
|
|
|
90 13 PB2
|
|
|
91 17 PB3
|
|
|
92
|
|
|
93 - output from appending columns::
|
|
|
94
|
|
|
95 Contig161_chr1_4641264_4641879 115 C T 73.5 chr1 4641382 C 6 0 2 45 8 0 2 51 15 0 2 72 5 0 2 42 6 0 2 45 10 0 2 57 Y 54 0.323 0 29 0 2 72
|
|
|
96 Contig48_chr1_10150253_10151311 11 A G 94.3 chr1 10150264 A 1 0 2 30 1 0 2 30 1 0 2 30 3 0 2 36 1 0 2 30 1 0 2 30 Y 22 +99. 0 3 0 2 30
|
|
|
97 Contig20_chr1_21313469_21313570 66 C T 54.0 chr1 21313534 C 4 0 2 39 4 0 2 39 5 0 2 42 4 0 2 39 4 0 2 39 5 0 2 42 N 1 +99. 0 13 0 2 42
|
|
|
98 etc.
|
|
|
99
|
|
|
100 - output from filter SNPs with minimum count of 3 for the individuals::
|
|
|
101
|
|
|
102 Contig161_chr1_4641264_4641879 115 C T 73.5 chr1 4641382 C 6 0 2 45 8 0 2 51 15 0 2 72 5 0 2 42 6 0 2 45 10 0 2 57 Y 54 0.323 0
|
|
|
103 Contig20_chr1_21313469_21313570 66 C T 54.0 chr1 21313534 C 4 0 2 39 4 0 2 39 5 0 2 42 4 0 2 39 4 0 2 39 5 0 2 42 N 1 +99. 0
|
|
|
104 etc.
|
|
|
105
|
|
|
106 </help>
|
|
|
107 </tool>
|
