annotate dir_plugins/FATHMM.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 FATHMM
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 FATHMM.pm ~/.vep/Plugins
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
31 ./vep -i variations.vcf --plugin FATHMM,"python /path/to/fathmm/fathmm.py"
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 gets FATHMM scores and predictions for missense variants.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
36
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
37 You will need the fathmm.py script and its dependencies (Python, Python
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
38 MySQLdb). You should create a "config.ini" file in the same directory as the
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
39 fathmm.py script with the database connection options. More information about
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
40 how to set up FATHMM can be found on the FATHMM website at
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
41 https://github.com/HAShihab/fathmm.
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
42
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
43 A typical installation could consist of:
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
44
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
45 > wget https://raw.github.com/HAShihab/fathmm/master/cgi-bin/fathmm.py
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
46 > wget ftp://supfam2.cs.bris.ac.uk/FATHMM/database/fathmm.v2.1.SQL
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
47 > mysql -h[host] -P[port] -u[user] -p[pass] -e"CREATE DATABASE fathmm"
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
48 > mysql -h[host] -P[port] -u[user] -p[pass] -Dfathmm < fathmm.v2.1.SQL
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
49 > echo "[DATABASE]\nHOST = [host]\nPORT = [port]\nUSER = [user]\nPASSWD = [pass]\nDB = fathmm\n" > config.ini
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
50
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
51 =cut
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
52
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
53 package FATHMM;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
54
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
55 use strict;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
56 use warnings;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
57
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
58 use Bio::EnsEMBL::Variation::Utils::BaseVepPlugin;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
59
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
60 use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
61
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
62 sub new {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
63 my $class = shift;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
64
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
65 my $self = $class->SUPER::new(@_);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
66
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
67 # get command
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
68 my $command = $self->params->[0];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
69
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
70 die 'ERROR: No FATHMM command specified. Specify path to FATHMM with e.g. --plugin FATHMM,"python /path/to/fathmm/fathmm.py"\n' unless defined($command);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
71
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
72 die 'ERROR: Your FATHMM command does not look correct; it should looks something like "python /path/to/fathmm/fathmm.py"\n' unless $command =~ /python.+fathmm\.py/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
73
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
74 $self->{command} = $command;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
75
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
76 die 'ERROR: Temporary directory '.$self->{config}->{tmpdir}.' not found - specify an existing directory with --tmpdir [dir]\n' unless -d $self->{config}->{tmpdir};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
77
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
78 return $self;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
79 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
80
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
81 sub version {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
82 return 71;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
83 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
84
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
85 sub feature_types {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
86 return ['Transcript'];
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
87 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
88
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
89 sub get_header_info {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
90 return {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
91 FATHMM => "FATHMM prediction (score)",
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
92 };
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
93 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
94
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
95 sub run {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
96 my ($self, $tva) = @_;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
97
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
98 # only for missense variants
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
99 return {} unless grep {$_->SO_term eq 'missense_variant'} @{$tva->get_all_OverlapConsequences};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
100
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
101 # configure command
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
102 my $command = $self->{command};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
103 $command =~ m/(\s.+)\/.+/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
104 my $command_dir = $1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
105
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
106 # configure tmp dir and in/out files for FATHMM
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
107 my $tmp_dir = $self->{config}->{tmpdir};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
108 my $tmp_in_file = $tmp_dir."/fathmm_$$\.in";
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
109 my $tmp_out_file = $tmp_dir."/fatmm_$$\.out";
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
110
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
111 # get required input data from TVA
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
112 my $protein = $tva->transcript->{_protein} || $tva->transcript->translation->stable_id;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
113 my $aa_change = $tva->pep_allele_string;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
114 my $aa_pos = $tva->transcript_variation->translation_start;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
115 $aa_change =~ s/\//$aa_pos/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
116
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
117 # check we have valid strings
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
118 return {} unless $protein && $aa_change =~ /^[A-Z]\d+[A-Z]$/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
119
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
120 # write input file
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
121 open IN, ">$tmp_in_file" or die "ERROR: Could not write to file $tmp_in_file\n";
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
122 print IN "$protein $aa_change\n";
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
123 close IN;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
124
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
125 # run command
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
126 my $fathmm_err = `cd $command_dir; $command $tmp_in_file $tmp_out_file;`;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
127
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
128 # read output file
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
129 open OUT, $tmp_out_file or die "ERROR: Could not read from file $tmp_out_file\n";
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
130
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
131 my ($pred, $score);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
132 while(<OUT>) {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
133 next if /^\#/;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
134 chomp;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
135 my @data = split;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
136 ($pred, $score) = ($data[4], $data[5]);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
137 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
138 close OUT;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
139
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
140 # delete temporary files
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
141 unlink($tmp_in_file, $tmp_out_file);
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
142
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
143 return $pred && $score ? {
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
144 FATHMM => "$pred($score)",
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
145 } : {};
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
146 }
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
147
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
148 1;
e545d0a25ffe Uploaded
dvanzessen
parents:
diff changeset
149