|
0
|
1
|
|
|
2 #
|
|
|
3 # $Id: SwissPfam.pm,v 1.15 2002/10/22 07:38:33 lapp Exp $
|
|
|
4 #
|
|
|
5 # BioPerl module for Bio::Index::SwissPfam
|
|
|
6 #
|
|
|
7 # Cared for by Ewan Birney <birney@sanger.ac.uk>
|
|
|
8 #
|
|
|
9 # You may distribute this module under the same terms as perl itself
|
|
|
10
|
|
|
11 # POD documentation - main docs before the code
|
|
|
12
|
|
|
13 =head1 NAME
|
|
|
14
|
|
|
15 Bio::Index::SwissPfam - Interface for indexing swisspfam files
|
|
|
16
|
|
|
17 =head1 SYNOPSIS
|
|
|
18
|
|
|
19 use Bio::Index::SwissPfam;
|
|
|
20 use strict;
|
|
|
21
|
|
|
22 my $Index_File_Name = shift;
|
|
|
23 my $inx = Bio::Index::SwissPfam->new('-filename' => $Index_File_Name,
|
|
|
24 '-write_flag' => 'WRITE');
|
|
|
25 $inx->make_index(@ARGV);
|
|
|
26
|
|
|
27 use Bio::Index::SwissPfam;
|
|
|
28 use strict;
|
|
|
29
|
|
|
30 my $Index_File_Name = shift;
|
|
|
31 my $inx = Bio::Index::SwissPfam->new('-filename' => $Index_File_Name);
|
|
|
32
|
|
|
33 foreach my $id (@ARGV) {
|
|
|
34 my $seq = $inx->fetch($id); # Returns stream
|
|
|
35 while( <$seq> ) {
|
|
|
36 if(/^>/) {
|
|
|
37 print;
|
|
|
38 last;
|
|
|
39 }
|
|
|
40 }
|
|
|
41 }
|
|
|
42
|
|
|
43
|
|
|
44 =head1 DESCRIPTION
|
|
|
45
|
|
|
46 SwissPfam is one of the flat files released with Pfam. This modules
|
|
|
47 provides a way of indexing this module.
|
|
|
48
|
|
|
49 Inherits functions for managing dbm files from
|
|
|
50 Bio::Index::Abstract.pm, and provides the basic funtionallity for
|
|
|
51 indexing SwissPfam files. Only retrieves FileStreams at the
|
|
|
52 moment. Once we have something better (ie, an object!), will use
|
|
|
53 that. Heavily snaffled from James Gilbert's Fasta system. Note: for
|
|
|
54 best results 'use strict'.
|
|
|
55
|
|
|
56 =head1 FEED_BACK
|
|
|
57
|
|
|
58 =head2 Mailing Lists
|
|
|
59
|
|
|
60 User feedback is an integral part of the evolution of this and other
|
|
|
61 Bioperl modules. Send your comments and suggestions preferably to one
|
|
|
62 of the Bioperl mailing lists. Your participation is much appreciated.
|
|
|
63
|
|
|
64 bioperl-l@bioperl.org - General discussion
|
|
|
65 http://bioperl.org/MailList.shtml - About the mailing lists
|
|
|
66
|
|
|
67 =head2 Reporting Bugs
|
|
|
68
|
|
|
69 Report bugs to the Bioperl bug tracking system to help us keep track
|
|
|
70 the bugs and their resolution. Bug reports can be submitted via
|
|
|
71 email or the web:
|
|
|
72
|
|
|
73 bioperl-bugs@bio.perl.org
|
|
|
74 http://bugzilla.bioperl.org/
|
|
|
75
|
|
|
76 =head1 AUTHOR - Ewan Birney
|
|
|
77
|
|
|
78 Email - birney@sanger.ac.uk
|
|
|
79
|
|
|
80 =head1 APPENDIX
|
|
|
81
|
|
|
82 The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
|
|
|
83
|
|
|
84 =cut
|
|
|
85
|
|
|
86
|
|
|
87 # Let's begin the code...
|
|
|
88
|
|
|
89
|
|
|
90 package Bio::Index::SwissPfam;
|
|
|
91
|
|
|
92 use vars qw($VERSION @ISA);
|
|
|
93 use strict;
|
|
|
94
|
|
|
95 use Bio::Index::Abstract;
|
|
|
96 use Bio::Seq;
|
|
|
97
|
|
|
98 @ISA = qw(Bio::Index::Abstract);
|
|
|
99
|
|
|
100 #
|
|
|
101 # Suggested fix by Michael G Schwern <schwern@pobox.com> to
|
|
|
102 # get around a clash with CPAN shell...
|
|
|
103 #
|
|
|
104
|
|
|
105 BEGIN {
|
|
|
106 $VERSION = 0.1;
|
|
|
107 }
|
|
|
108
|
|
|
109 sub _version {
|
|
|
110 return $VERSION;
|
|
|
111 }
|
|
|
112
|
|
|
113 =head2 _index_file
|
|
|
114
|
|
|
115 Title : _index_file
|
|
|
116 Usage : $index->_index_file( $file_name, $i )
|
|
|
117 Function: Specialist function to index swisspfam format files.
|
|
|
118 Is provided with a filename and an integer
|
|
|
119 by make_index in its SUPER class.
|
|
|
120 Example :
|
|
|
121 Returns :
|
|
|
122 Args :
|
|
|
123
|
|
|
124 =cut
|
|
|
125
|
|
|
126 sub _index_file {
|
|
|
127 my( $self,
|
|
|
128 $file, # File name
|
|
|
129 $i # Index-number of file being indexed
|
|
|
130 ) = @_;
|
|
|
131
|
|
|
132 my( $begin, # Offset from start of file of the start
|
|
|
133 # of the last found record.
|
|
|
134 $end, # Offset from start of file of the end
|
|
|
135 # of the last found record.
|
|
|
136 $id, # ID of last found record.
|
|
|
137 $acc, # accession of last record. Also put into the index
|
|
|
138 $nid, $nacc, # new ids for the record just found
|
|
|
139 );
|
|
|
140
|
|
|
141 $begin = 0;
|
|
|
142 $end = 0;
|
|
|
143
|
|
|
144 open SP, $file or $self->throw("Can't open file for read : $file");
|
|
|
145
|
|
|
146 # Main indexing loop
|
|
|
147 while (<SP>) {
|
|
|
148 if (/^>(\S+)\s+\|=*\|\s+(\S+)/) {
|
|
|
149 $nid = $1;
|
|
|
150 $nacc = $2;
|
|
|
151 my $new_begin = tell(SP) - length( $_ );
|
|
|
152 $end = $new_begin - 1;
|
|
|
153
|
|
|
154 if( $id ) {
|
|
|
155 $self->add_record($id, $i, $begin, $end);
|
|
|
156 if( $acc ne $id ) {
|
|
|
157 $self->add_record($acc, $i, $begin, $end);
|
|
|
158 }
|
|
|
159 }
|
|
|
160 $begin = $new_begin;
|
|
|
161 $id = $nid;
|
|
|
162 $acc = $nacc;
|
|
|
163 }
|
|
|
164 }
|
|
|
165 # Don't forget to add the last record
|
|
|
166 $end = tell(SP);
|
|
|
167 $self->add_record($id, $i, $begin, $end) if $id;
|
|
|
168
|
|
|
169 close SP;
|
|
|
170 return 1;
|
|
|
171 }
|
|
|
172
|
|
|
173
|
|
|
174 =head2 fetch
|
|
|
175
|
|
|
176 Title : fetch
|
|
|
177 Usage : $index->fetch( $id )
|
|
|
178 Function: Returns a Bio::Seq object from the index
|
|
|
179 Example : $seq = $index->fetch( 'dJ67B12' )
|
|
|
180 Returns : Bio::Seq object
|
|
|
181 Args : ID
|
|
|
182
|
|
|
183 =cut
|
|
|
184
|
|
|
185 sub fetch {
|
|
|
186 my( $self, $id ) = @_;
|
|
|
187 my $desc;
|
|
|
188 my $db = $self->db();
|
|
|
189 if (my $rec = $db->{ $id }) {
|
|
|
190 my( @record );
|
|
|
191
|
|
|
192 my ($file, $begin, $end) = $self->unpack_record( $rec );
|
|
|
193
|
|
|
194 # Get the (possibly cached) filehandle
|
|
|
195 my $fh = $self->_file_handle( $file );
|
|
|
196
|
|
|
197 # move to start
|
|
|
198 seek($fh, $begin, 0);
|
|
|
199
|
|
|
200 return $fh;
|
|
|
201 } else {
|
|
|
202 $self->throw("Unable to find a record for $id in SwissPfam flat file index");
|
|
|
203 }
|
|
|
204 }
|
|
|
205
|
|
|
206 1;
|
