annotate dir_plugins/Downstream.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 Downstream
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 Downstream.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31 ./vep -i variations.vcf --plugin Downstream
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 predicts the downstream effects of a frameshift variant on the protein
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37 sequence of a transcript. It provides the predicted downstream protein
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 sequence (including any amino acids overlapped by the variant itself),
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39 and the change in length relative to the reference protein.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 Note that changes in splicing are not predicted - only the existing
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42 translateable (i.e. spliced) sequence is used as a source of
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43 translation. Any variants with a splice site consequence type are
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44 ignored.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48 package Downstream;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50 use strict;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51 use warnings;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
53 use Bio::EnsEMBL::Variation::Utils::BaseVepPlugin;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
54 use POSIX qw(ceil);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
55
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
56 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
57
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
58 sub version {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
59 return '2.3';
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
60 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
61
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
62 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
63 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66 sub variant_feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67 return ['VariationFeature'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72 DownstreamProtein => "Predicted downstream translation for frameshift mutations",
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73 ProteinLengthChange => "Predicted change in protein product length",
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78 my ($self, $tva) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80 my @ocs = @{$tva->get_all_OverlapConsequences};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 if(grep {$_->SO_term eq 'frameshift_variant'} @ocs) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84 # can't do it for splice sites
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85 return {} if grep {$_->SO_term =~ /splice/} @ocs;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 my $tv = $tva->transcript_variation;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88 my $tr = $tv->transcript;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 my $cds_seq = defined($tr->{_variation_effect_feature_cache}) ? $tr->{_variation_effect_feature_cache}->{translateable_seq} : $tr->translateable_seq;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91 # get the sequence to translate
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 my ($low_pos, $high_pos) = sort {$a <=> $b} ($tv->cds_start, $tv->cds_end);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93 my $is_insertion = $tv->cds_start > $tv->cds_end ? 1 : 0;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94 my $last_complete_codon = (ceil($low_pos / 3) - 1) * 3;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95 my $before_var_seq = substr $cds_seq, $last_complete_codon, $low_pos - $last_complete_codon - ($is_insertion ? 0 : 1);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96 my $after_var_seq = substr $cds_seq, $high_pos - ($is_insertion ? 1 : 0);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97 my $to_translate = $before_var_seq.$tva->feature_seq.$after_var_seq;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 my $three_prime_utr_seq = $tr->three_prime_utr->seq() if ($tr->three_prime_utr);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99 $to_translate = $to_translate.$three_prime_utr_seq if ($three_prime_utr_seq);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100 $to_translate =~ s/\-//g;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 # create a bioperl object
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103 my $codon_seq = Bio::Seq->new(
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104 -seq => $to_translate,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105 -moltype => 'dna',
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 -alphabet => 'dna'
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107 );
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109 # get codon table
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110 my $codon_table;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 if(defined($tr->{_variation_effect_feature_cache})) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112 $codon_table = $tr->{_variation_effect_feature_cache}->{codon_table} || 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114 else {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 my ($attrib) = @{$tr->slice->get_all_Attributes('codon_table')};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116 $codon_table = $attrib ? $attrib->value || 1 : 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119 # translate
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120 my $new_pep = $codon_seq->translate(undef, undef, undef, $codon_table)->seq();
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 $new_pep =~ s/\*.*//;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
123 # compare lengths
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
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;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
125 my $new_length = ($tv->translation_start < $tv->translation_end ? $tv->translation_start : $tv->translation_end) + length($new_pep);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
126
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
127 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
128 DownstreamProtein => $new_pep,
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
129 ProteinLengthChange => $new_length - length($translation),
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
130 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
131 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
132
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
133 return {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
134 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
135
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
136 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
137