annotate dir_plugins/MPC.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 MPC
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 MPC.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31 ./vep -i variations.vcf --plugin MPC,fordist_constraint_official_mpc_values.txt.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 A VEP plugin that retrieves MPC scores for variants from a tabix-indexed MPC data file.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
36
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37 MPC is a missense deleteriousness metric based on the analysis of genic regions
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 depleted of missense mutations in the Exome Agggregation Consortium (ExAC) data.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40 The MPC score is the product of work by Kaitlin Samocha (ks20@sanger.ac.uk).
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 Publication currently in pre-print: Samocha et al bioRxiv 2017 (TBD)
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43 The MPC score file is available to download from:
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45 ftp://ftp.broadinstitute.org/pub/ExAC_release/release1/regional_missense_constraint/
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47 The data are currently mapped to GRCh37 only. Not all transcripts are included; see
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48 README in the above directory for exclusion criteria.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52 package MPC;
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 my %INCLUDE_SO = map {$_ => 1} qw(missense_variant stop_lost stop_gained start_lost);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65 sub new {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66 my $class = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 my $self = $class->SUPER::new(@_);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70 $self->expand_left(0);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71 $self->expand_right(0);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73 $self->get_user_params();
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75 return $self;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83 return { MPC => 'MPC score' };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 my ($self, $tva) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 # only for missense variants
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90 return {} unless grep {$INCLUDE_SO{$_->SO_term}} @{$tva->get_all_OverlapConsequences};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 my $vf = $tva->variation_feature;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94 return {} unless $vf->{start} eq $vf->{end};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96 # get allele, reverse comp if needed
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97 my $allele = $tva->variation_feature_seq;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 reverse_comp(\$allele) if $vf->{strand} < 0;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100 return {} unless $allele =~ /^[ACGT]$/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 # get transcript stable ID
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103 my $tr_id = $tva->transcript->stable_id;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105 my ($res) = grep {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 $_->{pos} == $vf->{start} &&
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107 $_->{alt} eq $allele &&
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108 $_->{tr} eq $tr_id
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109 } @{$self->get_data($vf->{chr}, $vf->{start}, $vf->{end})};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 return $res ? { MPC => $res->{MPC} } : {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114 sub parse_data {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 my ($self, $line) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117 my @split = split /\t/, $line;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120 pos => $split[1],
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 alt => $split[3],
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122 tr => $split[5],
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
123 MPC => $split[-1],
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
124 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
125 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
126
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
127 sub get_start {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
128 return $_[1]->{pos};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
129 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
130
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
131 sub get_end {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
132 return $_[1]->{pos};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
133 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
134
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
135 1;