annotate dir_plugins/ExACpLI.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 Please email comments or questions to the public Ensembl
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
21 developers list at <http://lists.ensembl.org/mailman/listinfo/dev>.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
22
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
23 Questions may also be sent to the Ensembl help desk at
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
24 <http://www.ensembl.org/Help/Contact>.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
25
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
26 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
27
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
28 =head1 NAME
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
29
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
30 ExACpLI - Add ExAC pLI to the VEP output
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
32 =head1 SYNOPSIS
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
33
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
34 mv ExACpLI.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
35 mv ExACpLI_values.txt ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
36 ./vep -i variants.vcf --plugin ExACpLI
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 =head1 DESCRIPTION
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 A VEP plugin that adds the probabililty of a gene being
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42 loss-of-function intolerant (pLI) to the VEP output.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44 Lek et al. (2016) estimated pLI using the expectation-maximization
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45 (EM) algorithm and data from 60,706 individuals from
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46 ExAC (http://exac.broadinstitute.org/about). The closer pLI is to 1,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47 the more likely the gene is loss-of-function (LoF) intolerant.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49 Note: the pLI was calculated using a representative transcript and
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50 is reported by gene in the plugin.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52 The data for the plugin is provided by Kaitlin Samocha and Daniel MacArthur.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
53 See https://www.ncbi.nlm.nih.gov/pubmed/27535533 for a description
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
54 of the dataset and analysis.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
55
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
56 The ExACpLI_values.txt file is found alongside the plugin in the
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
57 VEP_plugins GitHub repository. The file contains the fields gene and pLI
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
58 extracted from the file at
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
59
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
60 ftp://ftp.broadinstitute.org/pub/ExAC_release/release0.3/functional_gene_constraint/
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
61 fordist_cleaned_exac_r03_march16_z_pli_rec_null_data.txt
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
62
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
63 To use another values file, add it as a parameter i.e.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65 ./vep -i variants.vcf --plugin ExACpLI,values_file.txt
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70 package ExACpLI;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72 use strict;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73 use warnings;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75 use DBI;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79 sub new {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80 my $class = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 my $self = $class->SUPER::new(@_);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84 my $file = $self->params->[0];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86 if(!$file) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 my $plugin_dir = $INC{'ExACpLI.pm'};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88 $plugin_dir =~ s/ExACpLI\.pm//i;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 $file = $plugin_dir.'/ExACpLI_values.txt';
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 die("ERROR: ExACpLI values file $file not found\n") unless $file && -e $file;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94 open my $fh, "<", $file;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95 my %scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97 while(<$fh>) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 chomp;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99 my ($gene, $score) = split;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100 next if $score eq 'pLI';
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101 $scores{lc($gene)} = sprintf("%.2f", $score);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104 close $fh;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 die("ERROR: No scores read from $file\n") unless scalar keys %scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108 $self->{scores} = \%scores;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110 return $self;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119 ExACpLI => "ExACpLI value for gene"
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
123 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
124 my $self = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
125 my $tva = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
126
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
127 my $symbol = $tva->transcript->{_gene_symbol} || $tva->transcript->{_gene_hgnc};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
128 return {} unless $symbol;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
129
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
130 return $self->{scores}->{lc($symbol)} ? { ExACpLI => $self->{scores}->{lc($symbol)}} : {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
131 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
132
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
133 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
134