annotate gemini_roh.xml @ 4:ba3abde6775b draft default tip

Uploaded
author iuc
date Thu, 15 Jan 2015 15:33:48 -0500
parents 93bb0cfacefb
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
1 <tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.0">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
2 <description>Identifying runs of homozygosity</description>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
3 <expand macro="requirements" />
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
4 <expand macro="version_command" />
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
5 <macros>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
6 <import>gemini_macros.xml</import>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
7 <token name="@BINARY@">roh</token>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
8 </macros>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
9 <command>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
10 <![CDATA[
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
11 gemini @BINARY@
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
12 --min-snps $min_snps
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
13 --min-total-depth $min_total_depth
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
14 --min-gt-depth $min_gt_depth
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
15 --min-size $min_size
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
16 --max-hets $max_hets
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
17 --max-unknowns $max_unknowns
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
18 #if $samples.strip() != '':
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
19 -s "${samples}"
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
20 #end if
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
21 "${ infile }"
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
22 > "${ outfile }"
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
23 ]]>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
24 </command>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
25 <expand macro="stdio" />
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
26 <inputs>
2
93bb0cfacefb Uploaded
iuc
parents: 0
diff changeset
27 <expand macro="infile" />
0
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
28
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
29 <param name="min_snps" type="integer" value="25" size="5" label="Minimum number of expected homozygous SNPs" help="default: 25 (--min-snps)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
30 <validator type="in_range" min="0"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
31 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
32 <param name="min_total_depth" type="integer" value="20" size="10" label="The minimum overall sequencing depth requiredfor a SNP to be considered" help="default: 20 (--min-total-depth)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
33 <validator type="in_range" min="0"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
34 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
35 <param name="min_gt_depth" type="integer" value="0" size="10" label="The minimum required sequencing depth underlying a given sample's genotype for a SNP to be considered"
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
36 help="default: 0 (--min-gt-depth)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
37 <validator type="in_range" min="0"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
38 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
39 <param name="min_size" type="integer" value="100000" size="10" label="Minimum run size in base pairs" help="default: 100000 (--min-size)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
40 <validator type="in_range" min="1"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
41 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
42 <param name="max_hets" type="integer" value="1" size="5" label="Maximum number of allowed hets in the run" help="default: 1 (--max-hets)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
43 <validator type="in_range" min="1"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
44 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
45 <param name="max_unknowns" type="integer" value="3" size="5" label="Maximum number of allowed unknowns in the run" help="default: 3 (-max-unknowns)">
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
46 <validator type="in_range" min="0"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
47 </param>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
48
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
49 <param name="samples" size="30" type="text" value="" label="Comma separated list of samples to screen for ROHs" help="e.g S120,S450 (-s)"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
50
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
51 </inputs>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
52
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
53 <outputs>
2
93bb0cfacefb Uploaded
iuc
parents: 0
diff changeset
54 <data name="outfile" format="tabular" />
0
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
55 </outputs>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
56 <tests>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
57 <test>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
58 </test>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
59 </tests>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
60 <help>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
61
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
62 **What it does**
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
63
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
64 ===========================================================================
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
65 ``ROH``: Identifying runs of homozygosity
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
66 ===========================================================================
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
67 Runs of homozygosity are long stretches of homozygous genotypes that reflect
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
68 segments shared identically by descent and are a result of consanguinity or
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
69 natural selection. Consanguinity elevates the occurrence of rare recessive
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
70 diseases (e.g. cystic fibrosis) that represent homozygotes for strongly deleterious
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
71 mutations. Hence, the identification of these runs holds medical value.
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
72
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
73 The 'roh' tool in GEMINI returns runs of homozygosity identified in whole genome data.
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
74 The tool basically looks at every homozygous position on the chromosome as a possible
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
75 start site for the run and looks for those that could give rise to a potentially long
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
76 stretch of homozygous genotypes.
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
77
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
78 For e.g. for the given example allowing ``1 HET`` genotype (h) and ``2 UKW`` genotypes (u)
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
79 the possible roh runs (H) would be:
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
80
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
81
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
82 ::
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
83
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
84 genotype_run = H H H H h H H H H u H H H H H u H H H H H H H h H H H H H h H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
85 roh_run1 = H H H H h H H H H u H H H H H u H H H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
86 roh_run2 = H H H H u H H H H H u H H H H H H H h H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
87 roh_run3 = H H H H H u H H H H H H H h H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
88 roh_run4 = H H H H H H H h H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
89
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
90 roh returned for --min-snps = 20 would be:
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
91
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
92 ::
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
93
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
94 roh_run1 = H H H H h H H H H u H H H H H u H H H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
95 roh_run2 = H H H H u H H H H H u H H H H H H H h H H H H H
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
96
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
97
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
98 As you can see, the immediate homozygous position right of a break (h or u) would be the possible
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
99 start of a new roh run and genotypes to the left of a break are pruned since they cannot
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
100 be part of a longer run than we have seen before.
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
101
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
102
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
103 @CITATION@
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
104 </help>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
105 <expand macro="citations"/>
720cbfb4190d Imported from capsule None
iuc
parents:
diff changeset
106 </tool>