annotate dir_plugins/REVEL.pm @ 3:49397129aec0 draft

Uploaded
author dvanzessen
date Mon, 15 Jul 2019 05:20:39 -0400
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 REVEL
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 REVEL.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31 ./vep -i variations.vcf --plugin REVEL,/path/to/revel/data.tsv.gz
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
32
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
33 =head1 DESCRIPTION
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
34
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
35 This is a plugin for the Ensembl Variant Effect Predictor (VEP) that
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
36 adds the REVEL score for missense variants to VEP output.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 Please cite the REVEL publication alongside the VEP if you use this resource:
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39 https://www.ncbi.nlm.nih.gov/pubmed/27666373
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 REVEL scores can be downloaded from: https://sites.google.com/site/revelgenomics/downloads
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42 and can be tabix-processed by:
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44 cat revel_all_chromosomes.csv | tr "," "\t" > tabbed_revel.tsv
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45 sed '1s/.*/#&/' tabbed_revel.tsv > new_tabbed_revel.tsv
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46 bgzip new_tabbed_revel.tsv
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47 tabix -f -s 1 -b 2 -e 2 new_tabbed_revel.tsv.gz
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49 The tabix utility must be installed in your path to use this plugin.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52 package REVEL;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
53
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
54 use strict;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
55 use warnings;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
56
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
57 use Bio::EnsEMBL::Utils::Sequence qw(reverse_comp);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
58
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
59 use Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
60
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
61 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
62
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
63 sub new {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64 my $class = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66 my $self = $class->SUPER::new(@_);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 $self->expand_left(0);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69 $self->expand_right(0);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71 $self->get_user_params();
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73 return $self;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81 return { REVEL => 'Rare Exome Variant Ensemble Learner '};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85 my ($self, $tva) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86 # only for missense variants
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 return {} unless grep {$_->SO_term eq 'missense_variant'} @{$tva->get_all_OverlapConsequences};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 my $vf = $tva->variation_feature;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90 my $allele = $tva->variation_feature_seq;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91 my ($res) = grep {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 $_->{alt} eq $allele &&
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93 $_->{start} eq $vf->{start} &&
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94 $_->{end} eq $vf->{end} &&
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95 $_->{altaa} eq $tva->peptide
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96 } @{$self->get_data($vf->{chr}, $vf->{start}, $vf->{end})};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 return $res ? $res->{result} : {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101 sub parse_data {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 my ($self, $line) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104 my ($c, $s, $ref, $alt, $refaa, $altaa, $revel_value) = split /\t/, $line;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107 alt => $alt,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108 start => $s,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109 end => $s,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110 altaa => $altaa,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 result => {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112 REVEL => $revel_value,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117 sub get_start {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118 return $_[1]->{start};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 sub get_end {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122 return $_[1]->{end};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
123 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
124
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
125 1;