annotate variant_effect_predictor/Bio/Index/EMBL.pm @ 3:d30fa12e4cc5 default tip

Merge heads 2:a5976b2dce6f and 1:09613ce8151e which were created as a result of a recently fixed bug.
author devteam <devteam@galaxyproject.org>
date Mon, 13 Jan 2014 10:38:30 -0500
parents 1f6dce3d34e0
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
1 # $Id: EMBL.pm,v 1.21.2.1 2003/03/19 16:23:08 heikki Exp $
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
2 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
3 # BioPerl module for Bio::Index::EMBL
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
4 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
5 # Cared for by Ewan Birney <birney@sanger.ac.uk>
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
6 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
7 # You may distribute this module under the same terms as perl itself
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
8
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
9 # POD documentation - main docs before the code
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
10
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
11 =head1 NAME
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
12
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
13 Bio::Index::EMBL - Interface for indexing (multiple) EMBL/Swissprot
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
14 .dat files (ie flat file embl/swissprot format).
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
15
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
16 =head1 SYNOPSIS
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
17
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
18 # Complete code for making an index for several
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
19 # EMBL files
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
20 use Bio::Index::EMBL;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
21 use strict;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
22
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
23 my $Index_File_Name = shift;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
24 my $inx = Bio::Index::EMBL->new('-filename' => $Index_File_Name,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
25 '-write_flag' => 'WRITE');
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
26 $inx->make_index(@ARGV);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
27
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
28 # Print out several sequences present in the index
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
29 # in Fasta format
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
30 use Bio::Index::EMBL;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
31 use strict;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
32
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
33 my $Index_File_Name = shift;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
34 my $inx = Bio::Index::EMBL->new('-filename' => $Index_File_Name);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
35 my $out = Bio::SeqIO->new('-format' => 'Fasta','-fh' => \*STDOUT);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
36
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
37 foreach my $id (@ARGV) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
38 my $seq = $inx->fetch($id); # Returns Bio::Seq object
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
39 $out->write_seq($seq);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
40 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
41
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
42 # alternatively
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
43
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
44 my $seq1 = $inx->get_Seq_by_id($id);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
45 my $seq2 = $inx->get_Seq_by_acc($acc);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
46
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
47 =head1 DESCRIPTION
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
48
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
49 Inherits functions for managing dbm files from Bio::Index::Abstract.pm,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
50 and provides the basic funtionallity for indexing EMBL files, and
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
51 retrieving the sequence from them. Heavily snaffled from James Gilbert's
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
52 Fasta system. Note: for best results 'use strict'.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
53
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
54 =head1 FEED_BACK
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
55
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
56 =head2 Mailing Lists
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
57
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
58 User feedback is an integral part of the evolution of this and other
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
59 Bioperl modules. Send your comments and suggestions preferably to one
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
60 of the Bioperl mailing lists. Your participation is much appreciated.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
61
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
62 bioperl-l@bioperl.org - General discussion
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
63 http://bioperl.org/MailList.shtml - About the mailing lists
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
64
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
65
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
66
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
67 =head2 Reporting Bugs
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
68
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
69 Report bugs to the Bioperl bug tracking system to help us keep track
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
70 the bugs and their resolution. Bug reports can be submitted via
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
71 email or the web:
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
72
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
73 bioperl-bugs@bio.perl.org
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
74 http://bugzilla.bioperl.org/
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
75
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
76 =head1 AUTHOR - Ewan Birney
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
77
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
78 Email - birney@sanger.ac.uk
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
79
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
80 =head1 APPENDIX
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
81
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
82 The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
83
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
84 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
85
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
86
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
87 # Let's begin the code...
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
88
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
89
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
90 package Bio::Index::EMBL;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
91
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
92 use vars qw($VERSION @ISA);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
93 use strict;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
94
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
95 use Bio::Index::AbstractSeq;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
96 use Bio::Seq;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
97
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
98 @ISA = qw(Bio::Index::AbstractSeq);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
99
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
100 sub _type_stamp {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
101 return '__EMBL_FLAT__'; # What kind of index are we?
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
102 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
103
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
104 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
105 # Suggested fix by Michael G Schwern <schwern@pobox.com> to
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
106 # get around a clash with CPAN shell...
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
107 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
108
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
109 BEGIN {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
110 $VERSION = 0.1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
111 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
112
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
113 sub _version {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
114 return $VERSION;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
115 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
116
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
117 =head2 _index_file
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
118
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
119 Title : _index_file
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
120 Usage : $index->_index_file( $file_name, $i )
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
121 Function: Specialist function to index EMBL format files.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
122 Is provided with a filename and an integer
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
123 by make_index in its SUPER class.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
124 Example :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
125 Returns :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
126 Args :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
127
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
128 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
129
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
130 sub _index_file {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
131 my( $self,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
132 $file, # File name
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
133 $i # Index-number of file being indexed
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
134 ) = @_;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
135
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
136 my( $begin, # Offset from start of file of the start
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
137 # of the last found record.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
138 $id, # ID of last found record.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
139 @accs, # accession of last record. Also put into the index
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
140 );
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
141
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
142 $begin = 0;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
143
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
144 open EMBL, $file or $self->throw("Can't open file for read : $file");
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
145
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
146 # Main indexing loop
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
147 $id = undef;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
148 @accs = ();
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
149 while (<EMBL>) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
150 if( /^\/\// ) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
151 if( ! defined $id ) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
152 $self->throw("Got to a end of entry line for an EMBL flat file with no parsed ID. Considering this a problem!");
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
153 next;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
154 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
155 if( ! @accs ) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
156 $self->warn("For id [$id] in embl flat file, got no accession number. Storing id index anyway");
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
157 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
158
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
159 $self->add_record($id, $i, $begin);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
160
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
161 foreach my $acc (@accs) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
162 if( $acc ne $id ) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
163 $self->add_record($acc, $i, $begin);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
164 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
165 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
166 } elsif (/^ID\s+(\S+)/) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
167 $id = $1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
168 # not sure if I like this. Assummes tell is in bytes.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
169 # we could tell before each line and save it.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
170 $begin = tell(EMBL) - length( $_ );
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
171
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
172 } elsif (/^AC\s+(.*)?/) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
173 push @accs , split (/[; ]+/, $1);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
174 } else {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
175 # do nothing
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
176 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
177 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
178
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
179 close EMBL;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
180 return 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
181 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
182
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
183 =head2 _file_format
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
184
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
185 Title : _file_format
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
186 Usage : Internal function for indexing system
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
187 Function: Provides file format for this database
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
188 Example :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
189 Returns :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
190 Args :
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
191
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
192
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
193 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
194
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
195 sub _file_format{
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
196 my ($self,@args) = @_;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
197
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
198 return 'EMBL';
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
199 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
200
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
201
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
202
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
203 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
204
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
205
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
206
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
207
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
208
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
209
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
210
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
211
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
212
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
213