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