|
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 Downstream
|
|
|
27
|
|
|
28 =head1 SYNOPSIS
|
|
|
29
|
|
|
30 mv Downstream.pm ~/.vep/Plugins
|
|
|
31 ./vep -i variations.vcf --plugin Downstream
|
|
|
32
|
|
|
33 =head1 DESCRIPTION
|
|
|
34
|
|
|
35 This is a plugin for the Ensembl Variant Effect Predictor (VEP) that
|
|
|
36 predicts the downstream effects of a frameshift variant on the protein
|
|
|
37 sequence of a transcript. It provides the predicted downstream protein
|
|
|
38 sequence (including any amino acids overlapped by the variant itself),
|
|
|
39 and the change in length relative to the reference protein.
|
|
|
40
|
|
|
41 Note that changes in splicing are not predicted - only the existing
|
|
|
42 translateable (i.e. spliced) sequence is used as a source of
|
|
|
43 translation. Any variants with a splice site consequence type are
|
|
|
44 ignored.
|
|
|
45
|
|
|
46 =cut
|
|
|
47
|
|
|
48 package Downstream;
|
|
|
49
|
|
|
50 use strict;
|
|
|
51 use warnings;
|
|
|
52
|
|
|
53 use Bio::EnsEMBL::Variation::Utils::BaseVepPlugin;
|
|
|
54 use POSIX qw(ceil);
|
|
|
55
|
|
|
56 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
|
|
|
57
|
|
|
58 sub version {
|
|
|
59 return '2.3';
|
|
|
60 }
|
|
|
61
|
|
|
62 sub feature_types {
|
|
|
63 return ['Transcript'];
|
|
|
64 }
|
|
|
65
|
|
|
66 sub variant_feature_types {
|
|
|
67 return ['VariationFeature'];
|
|
|
68 }
|
|
|
69
|
|
|
70 sub get_header_info {
|
|
|
71 return {
|
|
|
72 DownstreamProtein => "Predicted downstream translation for frameshift mutations",
|
|
|
73 ProteinLengthChange => "Predicted change in protein product length",
|
|
|
74 };
|
|
|
75 }
|
|
|
76
|
|
|
77 sub run {
|
|
|
78 my ($self, $tva) = @_;
|
|
|
79
|
|
|
80 my @ocs = @{$tva->get_all_OverlapConsequences};
|
|
|
81
|
|
|
82 if(grep {$_->SO_term eq 'frameshift_variant'} @ocs) {
|
|
|
83
|
|
|
84 # can't do it for splice sites
|
|
|
85 return {} if grep {$_->SO_term =~ /splice/} @ocs;
|
|
|
86
|
|
|
87 my $tv = $tva->transcript_variation;
|
|
|
88 my $tr = $tv->transcript;
|
|
|
89 my $cds_seq = defined($tr->{_variation_effect_feature_cache}) ? $tr->{_variation_effect_feature_cache}->{translateable_seq} : $tr->translateable_seq;
|
|
|
90
|
|
|
91 # get the sequence to translate
|
|
|
92 my ($low_pos, $high_pos) = sort {$a <=> $b} ($tv->cds_start, $tv->cds_end);
|
|
|
93 my $is_insertion = $tv->cds_start > $tv->cds_end ? 1 : 0;
|
|
|
94 my $last_complete_codon = (ceil($low_pos / 3) - 1) * 3;
|
|
|
95 my $before_var_seq = substr $cds_seq, $last_complete_codon, $low_pos - $last_complete_codon - ($is_insertion ? 0 : 1);
|
|
|
96 my $after_var_seq = substr $cds_seq, $high_pos - ($is_insertion ? 1 : 0);
|
|
|
97 my $to_translate = $before_var_seq.$tva->feature_seq.$after_var_seq;
|
|
|
98 my $three_prime_utr_seq = $tr->three_prime_utr->seq() if ($tr->three_prime_utr);
|
|
|
99 $to_translate = $to_translate.$three_prime_utr_seq if ($three_prime_utr_seq);
|
|
|
100 $to_translate =~ s/\-//g;
|
|
|
101
|
|
|
102 # create a bioperl object
|
|
|
103 my $codon_seq = Bio::Seq->new(
|
|
|
104 -seq => $to_translate,
|
|
|
105 -moltype => 'dna',
|
|
|
106 -alphabet => 'dna'
|
|
|
107 );
|
|
|
108
|
|
|
109 # get codon table
|
|
|
110 my $codon_table;
|
|
|
111 if(defined($tr->{_variation_effect_feature_cache})) {
|
|
|
112 $codon_table = $tr->{_variation_effect_feature_cache}->{codon_table} || 1;
|
|
|
113 }
|
|
|
114 else {
|
|
|
115 my ($attrib) = @{$tr->slice->get_all_Attributes('codon_table')};
|
|
|
116 $codon_table = $attrib ? $attrib->value || 1 : 1;
|
|
|
117 }
|
|
|
118
|
|
|
119 # translate
|
|
|
120 my $new_pep = $codon_seq->translate(undef, undef, undef, $codon_table)->seq();
|
|
|
121 $new_pep =~ s/\*.*//;
|
|
|
122
|
|
|
123 # compare lengths
|
|
|
124 my $translation = defined($tr->{_variation_effect_feature_cache}) && defined($tr->{_variation_effect_feature_cache}->{peptide}) ? $tr->{_variation_effect_feature_cache}->{peptide} : $tr->translation->seq;
|
|
|
125 my $new_length = ($tv->translation_start < $tv->translation_end ? $tv->translation_start : $tv->translation_end) + length($new_pep);
|
|
|
126
|
|
|
127 return {
|
|
|
128 DownstreamProtein => $new_pep,
|
|
|
129 ProteinLengthChange => $new_length - length($translation),
|
|
|
130 };
|
|
|
131 }
|
|
|
132
|
|
|
133 return {};
|
|
|
134 }
|
|
|
135
|
|
|
136 1;
|
|
|
137
|
