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