annotate dir_plugins/LoFtool.pm @ 10:f594c6bed58f draft default tip

Uploaded
author dvanzessen
date Tue, 21 Apr 2020 11:40:19 +0000
parents e545d0a25ffe
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
1 =head1 LICENSE
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
2
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
3 Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
4 Copyright [2016-2018] EMBL-European Bioinformatics Institute
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
5
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
6 Licensed under the Apache License, Version 2.0 (the "License");
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
7 you may not use this file except in compliance with the License.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
8 You may obtain a copy of the License at
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
9
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
10 http://www.apache.org/licenses/LICENSE-2.0
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
11
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
12 Unless required by applicable law or agreed to in writing, software
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
13 distributed under the License is distributed on an "AS IS" BASIS,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
14 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
15 See the License for the specific language governing permissions and
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
16 limitations under the License.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
17
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
18 =head1 CONTACT
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
19
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
20 Ensembl <http://www.ensembl.org/info/about/contact/index.html>
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
21
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
22 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
23
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
24 =head1 NAME
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
25
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
26 LoFtool
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
27
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
28 =head1 SYNOPSIS
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
29
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
30 mv LoFtool.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31 mv LoFtool_scores.txt ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
32 ./vep -i variants.vcf --plugin LoFtool
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
33
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
34 =head1 DESCRIPTION
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
35
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
36 Add LoFtool scores to the VEP output.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 LoFtool provides a rank of genic intolerance and consequent
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39 susceptibility to disease based on the ratio of Loss-of-function (LoF)
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40 to synonymous mutations for each gene in 60,706 individuals from ExAC,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 adjusting for the gene de novo mutation rate and evolutionary protein
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42 conservation. The lower the LoFtool gene score percentile the most
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43 intolerant is the gene to functional variation. For more details please see
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44 (Fadista J et al. 2017), PMID:27563026.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45 The authors would like to thank the Exome Aggregation Consortium and
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46 the groups that provided exome variant data for comparison. A full
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47 list of contributing groups can be found at http://exac.broadinstitute.org/about.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49 The LoFtool_scores.txt file is found alongside the plugin in the
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50 VEP_plugins GitHub repo.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52 To use another scores file, add it as a parameter i.e.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
53
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
54 ./vep -i variants.vcf --plugin LoFtool,scores_file.txt
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
55
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
56 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
57
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
58 package LoFtool;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
59
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
60 use strict;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
61 use warnings;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
62
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
63 use DBI;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67 sub new {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 my $class = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70 my $self = $class->SUPER::new(@_);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72 my $file = $self->params->[0];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74 if(!$file) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75 my $plugin_dir = $INC{'LoFtool.pm'};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76 $plugin_dir =~ s/LoFtool\.pm//i;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77 $file = $plugin_dir.'/LoFtool_scores.txt';
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80 die("ERROR: LoFtool scores file $file not found\n") unless $file && -e $file;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 open IN, $file;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83 my %scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85 while(<IN>) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86 chomp;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 my ($gene, $score) = split;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88 next if !defined($score) || $score eq 'LoFtool_percentile';
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 $scores{lc($gene)} = sprintf("%g", $score);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 close IN;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94 die("ERROR: No scores read from $file\n") unless scalar keys %scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96 $self->{scores} = \%scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 return $self;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107 LoFtool => "LoFtool score for gene"
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112 my $self = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113 my $tva = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 my $symbol = $tva->transcript->{_gene_symbol} || $tva->transcript->{_gene_hgnc};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116 return {} unless $symbol;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118 return $self->{scores}->{lc($symbol)} ? { LoFtool => $self->{scores}->{lc($symbol)}} : {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122