/
GFF.pm
250 lines (185 loc) · 5.49 KB
/
GFF.pm
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
=head1 LICENSE
Copyright [2016-2017] EMBL-European Bioinformatics Institute
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
=cut
=head1 CONTACT
Please email comments or questions to the public Ensembl
developers list at <http://lists.ensembl.org/mailman/listinfo/dev>.
Questions may also be sent to the Ensembl help desk at
<http://www.ensembl.org/Help/Contact>.
=cut
# EnsEMBL module for Bio::EnsEMBL::VEP::AnnotationSource::File::GFF
#
#
=head1 NAME
Bio::EnsEMBL::VEP::AnnotationSource::File::GFF - GFF annotation source
=head1 SYNOPSIS
my $as = Bio::EnsEMBL::VEP::AnnotationSource::File::GFF->new({
config => $config,
file => "my_genes.gff.gz"
});
$as->annotate_InputBuffer($ib);
=head1 DESCRIPTION
GFF3 format custom annotation source. GFF files must be chromosome/pos
sorted, compressed with bgzip and indexed with tabix.
Other aspects/limitations discussed here:
http://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#gff
=head1 METHODS
=cut
use strict;
use warnings;
package Bio::EnsEMBL::VEP::AnnotationSource::File::GFF;
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
use Bio::EnsEMBL::IO::Parser::GFF3Tabix;
use base qw(Bio::EnsEMBL::VEP::AnnotationSource::File::BaseGXF);
my %INCLUDE_FEATURE_TYPES = map {$_ => 1} qw(
aberrant_processed_transcript
CDS
C_gene_segment
exon
gene
J_gene_segment
lincRNA
lincRNA_gene
miRNA
miRNA_gene
mt_gene
nc_primary_transcript
NMD_transcript_variant
processed_pseudogene
processed_transcript
pseudogene
pseudogenic_transcript
RNA
rRNA
rRNA_gene
snoRNA
snoRNA_gene
snRNA
snRNA_gene
supercontig
transcript
VD_gene_segment
V_gene_segment
CDS
C_gene_segment
D_gene_segment
exon
gene
J_gene_segment
mRNA
ncRNA
primary_transcript
rRNA
transcript
tRNA
V_gene_segment
);
=head2 parser
Example : $parser = $as->parser();
Description: Get ensembl-io parser to read from file
Returntype : Bio::EnsEMBL::IO::Parser::GFF3Tabix
Exceptions : none
Caller : general
Status : Stable
=cut
sub parser {
my $self = shift;
return $self->{parser} ||= Bio::EnsEMBL::IO::Parser::GFF3Tabix->open($self->file, must_parse_metadata => 0);
}
=head2 include_feature_types
Example : $types = $as->include_feature_types();
Description: Get hashref of GFF record types this class can parse
Returntype : hashref
Exceptions : none
Caller : general
Status : Stable
=cut
sub include_feature_types {
return \%INCLUDE_FEATURE_TYPES;
}
=head2 _record_get_parent_id
Arg 1 : hashref $record_hash
Example : $id = $as->_record_get_parent_id($record);
Description: Get ID of parent record for this record
Returntype : string
Exceptions : none
Caller : general
Status : Stable
=cut
sub _record_get_parent_id {
my ($self, $record) = @_;
if(!exists($record->{_parent_id})) {
my $attributes = $record->{attributes};
$record->{_parent_id} = $attributes->{Parent} || $attributes->{parent};
}
return $record->{_parent_id};
}
=head2 _record_get_id
Arg 1 : hashref $record_hash
Example : $id = $as->_record_get_id($record);
Description: Get ID of this record
Returntype : string
Exceptions : none
Caller : general
Status : Stable
=cut
sub _record_get_id {
my ($self, $record) = @_;
if(!exists($record->{_id})) {
my $attributes = $record->{attributes};
$record->{_id} = $attributes->{ID} || $attributes->{Name} || $attributes->{id} || $attributes->{name};
}
return $record->{_id};
}
=head2 _record_get_biotype
Arg 1 : hashref $transcript_record_hash
Arg 2 : hashref $gene_record_hash
Example : $biotype = $as->_record_get_biotype($tr_record, $gene_record);
Description: Get sequence ontology (SO) biotype of this record. Attempts to
find it in the "biotype" or "transcript_type" attribute fields,
and if that fails (as it will for RefSeq GFFs), make an
educated guess looking at the record type and various other
attributes.
Returntype : string
Exceptions : none
Caller : general
Status : Stable
=cut
sub _record_get_biotype {
my ($self, $record, $gene_record) = @_;
if(!exists($record->{_biotype})) {
# Ensembl-y GFFs have biotype as an attribute
my $biotype = $record->{attributes}->{biotype} || $record->{attributes}->{transcript_type};
# others we need to (guess) work it out
if(!$biotype) {
my $type = lc($record->{type});
if($type eq 'mrna') {
$biotype = 'protein_coding';
}
elsif($type eq 'ncrna') {
$biotype = $record->{attributes}->{ncrna_class};
}
elsif($type =~ /^([a-z]+)_gene_segment$/) {
$biotype = 'IG_'.uc($1).'_gene';
}
elsif($gene_record && ($gene_record->{attributes}->{description} || '') =~ /^microRNA/) {
$biotype = 'miRNA';
}
elsif($record->{attributes}->{gbkey}) {
$biotype = $record->{attributes}->{gbkey};
}
}
$record->{_biotype} = $biotype;
}
return $record->{_biotype};
}
1;