|
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 CADD
|
|
|
27
|
|
|
28 =head1 SYNOPSIS
|
|
|
29
|
|
|
30 mv CADD.pm ~/.vep/Plugins
|
|
|
31 ./vep -i variations.vcf --plugin CADD,whole_genome_SNVs.tsv.gz,InDels.tsv.gz
|
|
|
32
|
|
|
33 =head1 DESCRIPTION
|
|
|
34
|
|
|
35 A VEP plugin that retrieves CADD scores for variants from one or more
|
|
|
36 tabix-indexed CADD data files.
|
|
|
37
|
|
|
38 Please cite the CADD publication alongside the VEP if you use this resource:
|
|
|
39 http://www.ncbi.nlm.nih.gov/pubmed/24487276
|
|
|
40
|
|
|
41 The tabix utility must be installed in your path to use this plugin. The CADD
|
|
|
42 data files can be downloaded from
|
|
|
43 http://cadd.gs.washington.edu/download
|
|
|
44
|
|
|
45 =cut
|
|
|
46
|
|
|
47 package CADD;
|
|
|
48
|
|
|
49 use strict;
|
|
|
50 use warnings;
|
|
|
51
|
|
|
52 use Bio::EnsEMBL::Utils::Sequence qw(reverse_comp);
|
|
|
53
|
|
|
54 use Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin;
|
|
|
55
|
|
|
56 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin);
|
|
|
57
|
|
|
58 sub new {
|
|
|
59 my $class = shift;
|
|
|
60
|
|
|
61 my $self = $class->SUPER::new(@_);
|
|
|
62
|
|
|
63 $self->expand_left(0);
|
|
|
64 $self->expand_right(0);
|
|
|
65
|
|
|
66 $self->get_user_params();
|
|
|
67
|
|
|
68 return $self;
|
|
|
69 }
|
|
|
70
|
|
|
71 sub feature_types {
|
|
|
72 return ['Feature','Intergenic'];
|
|
|
73 }
|
|
|
74
|
|
|
75 sub get_header_info {
|
|
|
76 my $self = shift;
|
|
|
77 return {
|
|
|
78 CADD_PHRED => 'PHRED-like scaled CADD score',
|
|
|
79 CADD_RAW => 'Raw CADD score'
|
|
|
80 }
|
|
|
81 }
|
|
|
82
|
|
|
83 sub run {
|
|
|
84 my ($self, $tva) = @_;
|
|
|
85
|
|
|
86 my $vf = $tva->variation_feature;
|
|
|
87
|
|
|
88 # get allele, reverse comp if needed
|
|
|
89 my $allele = $tva->variation_feature_seq;
|
|
|
90 reverse_comp(\$allele) if $vf->{strand} < 0;
|
|
|
91
|
|
|
92 return {} unless $allele =~ /^[ACGT-]+$/;
|
|
|
93
|
|
|
94 my ($res) = grep {
|
|
|
95 $_->{alt} eq $allele &&
|
|
|
96 $_->{start} eq $vf->{start} &&
|
|
|
97 $_->{end} eq $vf->{end}
|
|
|
98 } @{$self->get_data($vf->{chr}, $vf->{start} - 2, $vf->{end})};
|
|
|
99
|
|
|
100 return $res ? $res->{result} : {};
|
|
|
101 }
|
|
|
102
|
|
|
103 sub parse_data {
|
|
|
104 my ($self, $line) = @_;
|
|
|
105
|
|
|
106 my ($c, $s, $ref, $alt, $raw, $phred) = split /\t/, $line;
|
|
|
107
|
|
|
108 # do VCF-like coord adjustment for mismatched subs
|
|
|
109 my $e = ($s + length($ref)) - 1;
|
|
|
110 if(length($alt) != length($ref)) {
|
|
|
111 $s++;
|
|
|
112 $ref = substr($ref, 1);
|
|
|
113 $alt = substr($alt, 1);
|
|
|
114 $ref ||= '-';
|
|
|
115 $alt ||= '-';
|
|
|
116 }
|
|
|
117
|
|
|
118 return {
|
|
|
119 alt => $alt,
|
|
|
120 start => $s,
|
|
|
121 end => $e,
|
|
|
122 result => {
|
|
|
123 CADD_RAW => $raw,
|
|
|
124 CADD_PHRED => $phred
|
|
|
125 }
|
|
|
126 };
|
|
|
127 }
|
|
|
128
|
|
|
129 sub get_start {
|
|
|
130 return $_[1]->{start};
|
|
|
131 }
|
|
|
132
|
|
|
133 sub get_end {
|
|
|
134 return $_[1]->{end};
|
|
|
135 }
|
|
|
136
|
|
|
137 1; |
