|
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 FATHMM_MKL
|
|
|
27
|
|
|
28 =head1 SYNOPSIS
|
|
|
29
|
|
|
30 mv FATHMM_MKL.pm ~/.vep/Plugins
|
|
|
31 ./vep -i input.vcf --plugin FATHMM_MKL,fathmm-MKL_Current.tab.gz
|
|
|
32
|
|
|
33 =head1 DESCRIPTION
|
|
|
34
|
|
|
35 A VEP plugin that retrieves FATHMM-MKL scores for variants from a tabix-indexed
|
|
|
36 FATHMM-MKL data file.
|
|
|
37
|
|
|
38 See https://github.com/HAShihab/fathmm-MKL for details.
|
|
|
39
|
|
|
40 NB: The currently available data file is for GRCh37 only.
|
|
|
41
|
|
|
42 =cut
|
|
|
43
|
|
|
44 package FATHMM_MKL;
|
|
|
45
|
|
|
46 use strict;
|
|
|
47 use warnings;
|
|
|
48
|
|
|
49 use Bio::EnsEMBL::Utils::Sequence qw(reverse_comp);
|
|
|
50
|
|
|
51 use Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin;
|
|
|
52
|
|
|
53 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin);
|
|
|
54
|
|
|
55 sub new {
|
|
|
56 my $class = shift;
|
|
|
57
|
|
|
58 my $self = $class->SUPER::new(@_);
|
|
|
59
|
|
|
60 $self->expand_left(0);
|
|
|
61 $self->expand_right(0);
|
|
|
62
|
|
|
63 return $self;
|
|
|
64 }
|
|
|
65
|
|
|
66 sub feature_types {
|
|
|
67 return ['Feature','Intergenic'];
|
|
|
68 }
|
|
|
69
|
|
|
70 sub get_header_info {
|
|
|
71 my $self = shift;
|
|
|
72 return {
|
|
|
73 FATHMM_MKL_C => 'FATHMM-MKL coding score',
|
|
|
74 FATHMM_MKL_NC => 'FATHMM-MKL non-coding score',
|
|
|
75 }
|
|
|
76 }
|
|
|
77
|
|
|
78 sub run {
|
|
|
79 my ($self, $tva) = @_;
|
|
|
80
|
|
|
81 my $vf = $tva->variation_feature;
|
|
|
82
|
|
|
83 return {} unless $vf->{start} eq $vf->{end};
|
|
|
84
|
|
|
85 # get allele, reverse comp if needed
|
|
|
86 my $allele = $tva->variation_feature_seq;
|
|
|
87 reverse_comp(\$allele) if $vf->{strand} < 0;
|
|
|
88
|
|
|
89 return {} unless $allele =~ /^[ACGT]$/;
|
|
|
90
|
|
|
91 # adjust coords, file is BED-like (but not 0-indexed, go figure...)
|
|
|
92 my ($s, $e) = ($vf->{start}, $vf->{end} + 1);
|
|
|
93
|
|
|
94 foreach my $data(@{$self->get_data($vf->{chr}, $s, $e)}) {
|
|
|
95 if($data->{start} == $s && $allele eq $data->{alt}) {
|
|
|
96 return $data->{result};
|
|
|
97 }
|
|
|
98 }
|
|
|
99
|
|
|
100 return {};
|
|
|
101 }
|
|
|
102
|
|
|
103 sub parse_data {
|
|
|
104 my ($self, $line) = @_;
|
|
|
105
|
|
|
106 my ($c, $s, $e, $ref, $alt, $nc_score, $nc_groups, $c_score, $c_groups) = split /\t/, $line;
|
|
|
107
|
|
|
108 return {
|
|
|
109 start => $s,
|
|
|
110 end => $e - 1,
|
|
|
111 alt => $alt,
|
|
|
112 result => {
|
|
|
113 FATHMM_MKL_C => $c_score,
|
|
|
114 FATHMM_MKL_NC => $nc_score,
|
|
|
115 }
|
|
|
116 };
|
|
|
117 }
|
|
|
118
|
|
|
119 sub get_start {
|
|
|
120 return $_[1]->{start};
|
|
|
121 }
|
|
|
122
|
|
|
123 sub get_end {
|
|
|
124 return $_[1]->{end};
|
|
|
125 }
|
|
|
126
|
|
|
127 1;
|
|
|
128
|
