|
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 Please email comments or questions to the public Ensembl
|
|
|
21 developers list at <http://lists.ensembl.org/mailman/listinfo/dev>.
|
|
|
22
|
|
|
23 Questions may also be sent to the Ensembl help desk at
|
|
|
24 <http://www.ensembl.org/Help/Contact>.
|
|
|
25
|
|
|
26 =cut
|
|
|
27
|
|
|
28 =head1 NAME
|
|
|
29
|
|
|
30 ExACpLI - Add ExAC pLI to the VEP output
|
|
|
31
|
|
|
32 =head1 SYNOPSIS
|
|
|
33
|
|
|
34 mv ExACpLI.pm ~/.vep/Plugins
|
|
|
35 mv ExACpLI_values.txt ~/.vep/Plugins
|
|
|
36 ./vep -i variants.vcf --plugin ExACpLI
|
|
|
37
|
|
|
38 =head1 DESCRIPTION
|
|
|
39
|
|
|
40
|
|
|
41 A VEP plugin that adds the probabililty of a gene being
|
|
|
42 loss-of-function intolerant (pLI) to the VEP output.
|
|
|
43
|
|
|
44 Lek et al. (2016) estimated pLI using the expectation-maximization
|
|
|
45 (EM) algorithm and data from 60,706 individuals from
|
|
|
46 ExAC (http://exac.broadinstitute.org/about). The closer pLI is to 1,
|
|
|
47 the more likely the gene is loss-of-function (LoF) intolerant.
|
|
|
48
|
|
|
49 Note: the pLI was calculated using a representative transcript and
|
|
|
50 is reported by gene in the plugin.
|
|
|
51
|
|
|
52 The data for the plugin is provided by Kaitlin Samocha and Daniel MacArthur.
|
|
|
53 See https://www.ncbi.nlm.nih.gov/pubmed/27535533 for a description
|
|
|
54 of the dataset and analysis.
|
|
|
55
|
|
|
56 The ExACpLI_values.txt file is found alongside the plugin in the
|
|
|
57 VEP_plugins GitHub repository. The file contains the fields gene and pLI
|
|
|
58 extracted from the file at
|
|
|
59
|
|
|
60 ftp://ftp.broadinstitute.org/pub/ExAC_release/release0.3/functional_gene_constraint/
|
|
|
61 fordist_cleaned_exac_r03_march16_z_pli_rec_null_data.txt
|
|
|
62
|
|
|
63 To use another values file, add it as a parameter i.e.
|
|
|
64
|
|
|
65 ./vep -i variants.vcf --plugin ExACpLI,values_file.txt
|
|
|
66
|
|
|
67
|
|
|
68 =cut
|
|
|
69
|
|
|
70 package ExACpLI;
|
|
|
71
|
|
|
72 use strict;
|
|
|
73 use warnings;
|
|
|
74
|
|
|
75 use DBI;
|
|
|
76
|
|
|
77 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
|
|
|
78
|
|
|
79 sub new {
|
|
|
80 my $class = shift;
|
|
|
81
|
|
|
82 my $self = $class->SUPER::new(@_);
|
|
|
83
|
|
|
84 my $file = $self->params->[0];
|
|
|
85
|
|
|
86 if(!$file) {
|
|
|
87 my $plugin_dir = $INC{'ExACpLI.pm'};
|
|
|
88 $plugin_dir =~ s/ExACpLI\.pm//i;
|
|
|
89 $file = $plugin_dir.'/ExACpLI_values.txt';
|
|
|
90 }
|
|
|
91
|
|
|
92 die("ERROR: ExACpLI values file $file not found\n") unless $file && -e $file;
|
|
|
93
|
|
|
94 open my $fh, "<", $file;
|
|
|
95 my %scores;
|
|
|
96
|
|
|
97 while(<$fh>) {
|
|
|
98 chomp;
|
|
|
99 my ($gene, $score) = split;
|
|
|
100 next if $score eq 'pLI';
|
|
|
101 $scores{lc($gene)} = sprintf("%.2f", $score);
|
|
|
102 }
|
|
|
103
|
|
|
104 close $fh;
|
|
|
105
|
|
|
106 die("ERROR: No scores read from $file\n") unless scalar keys %scores;
|
|
|
107
|
|
|
108 $self->{scores} = \%scores;
|
|
|
109
|
|
|
110 return $self;
|
|
|
111 }
|
|
|
112
|
|
|
113 sub feature_types {
|
|
|
114 return ['Transcript'];
|
|
|
115 }
|
|
|
116
|
|
|
117 sub get_header_info {
|
|
|
118 return {
|
|
|
119 ExACpLI => "ExACpLI value for gene"
|
|
|
120 };
|
|
|
121 }
|
|
|
122
|
|
|
123 sub run {
|
|
|
124 my $self = shift;
|
|
|
125 my $tva = shift;
|
|
|
126
|
|
|
127 my $symbol = $tva->transcript->{_gene_symbol} || $tva->transcript->{_gene_hgnc};
|
|
|
128 return {} unless $symbol;
|
|
|
129
|
|
|
130 return $self->{scores}->{lc($symbol)} ? { ExACpLI => $self->{scores}->{lc($symbol)}} : {};
|
|
|
131 }
|
|
|
132
|
|
|
133 1;
|
|
|
134
|
