|
0
|
1 #
|
|
|
2 # $Id: Fasta.pm,v 1.20 2002/10/22 07:38:33 lapp Exp $
|
|
|
3 #
|
|
|
4 # BioPerl module for Bio::Index::Fasta
|
|
|
5 #
|
|
|
6 # Cared for by James Gilbert <jgrg@sanger.ac.uk>
|
|
|
7 #
|
|
|
8 # You may distribute this module under the same terms as perl itself
|
|
|
9
|
|
|
10 # POD documentation - main docs before the code
|
|
|
11
|
|
|
12 =head1 NAME
|
|
|
13
|
|
|
14 Bio::Index::Fasta - Interface for indexing (multiple) fasta files
|
|
|
15
|
|
|
16 =head1 SYNOPSIS
|
|
|
17
|
|
|
18 # Complete code for making an index for several
|
|
|
19 # fasta files
|
|
|
20 use Bio::Index::Fasta;
|
|
|
21 use strict;
|
|
|
22
|
|
|
23 my $Index_File_Name = shift;
|
|
|
24 my $inx = Bio::Index::Fasta->new(
|
|
|
25 '-filename' => $Index_File_Name,
|
|
|
26 '-write_flag' => 1);
|
|
|
27 $inx->make_index(@ARGV);
|
|
|
28
|
|
|
29 # Print out several sequences present in the index
|
|
|
30 # in Fasta format
|
|
|
31 use Bio::Index::Fasta;
|
|
|
32 use strict;
|
|
|
33
|
|
|
34 my $Index_File_Name = shift;
|
|
|
35 my $inx = Bio::Index::Fasta->new('-filename' => $Index_File_Name);
|
|
|
36 my $out = Bio::SeqIO->new('-format' => 'Fasta','-fh' => \*STDOUT);
|
|
|
37
|
|
|
38 foreach my $id (@ARGV) {
|
|
|
39 my $seq = $inx->fetch($id); # Returns Bio::Seq object
|
|
|
40 $out->write_seq($seq);
|
|
|
41 }
|
|
|
42
|
|
|
43 # or, alternatively
|
|
|
44
|
|
|
45 my $seq = $inx->get_Seq_by_id($id); #identical to fetch
|
|
|
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 fasta files, and
|
|
|
51 retrieving the sequence from them. Note: for best results 'use strict'.
|
|
|
52
|
|
|
53 Bio::Index::Fasta supports the Bio::DB::BioSeqI interface, meaning
|
|
|
54 it can be used a a Sequence database for other parts of bioperl
|
|
|
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 - James Gilbert
|
|
|
77
|
|
|
78 Email - jgrg@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 the code begin...
|
|
|
88
|
|
|
89
|
|
|
90 package Bio::Index::Fasta;
|
|
|
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 #
|
|
|
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 = 0.2;
|
|
|
107 }
|
|
|
108
|
|
|
109 sub _version {
|
|
|
110 return $VERSION;
|
|
|
111 }
|
|
|
112
|
|
|
113 =head2 _file_format
|
|
|
114
|
|
|
115 Title : _file_format
|
|
|
116 Function: The file format for this package, which is needed
|
|
|
117 by the SeqIO system when reading the sequence.
|
|
|
118 Returns : 'Fasta'
|
|
|
119
|
|
|
120 =cut
|
|
|
121
|
|
|
122 sub _file_format {
|
|
|
123 return 'Fasta';
|
|
|
124 }
|
|
|
125
|
|
|
126
|
|
|
127
|
|
|
128 =head2 _index_file
|
|
|
129
|
|
|
130 Title : _index_file
|
|
|
131 Usage : $index->_index_file( $file_name, $i )
|
|
|
132 Function: Specialist function to index FASTA format files.
|
|
|
133 Is provided with a filename and an integer
|
|
|
134 by make_index in its SUPER class.
|
|
|
135 Example :
|
|
|
136 Returns :
|
|
|
137 Args :
|
|
|
138
|
|
|
139 =cut
|
|
|
140
|
|
|
141 sub _index_file {
|
|
|
142 my( $self,
|
|
|
143 $file, # File name
|
|
|
144 $i, # Index-number of file being indexed
|
|
|
145 ) = @_;
|
|
|
146
|
|
|
147 my( $begin, # Offset from start of file of the start
|
|
|
148 # of the last found record.
|
|
|
149 );
|
|
|
150
|
|
|
151 $begin = 0;
|
|
|
152
|
|
|
153 my $id_parser = $self->id_parser;
|
|
|
154
|
|
|
155 open FASTA, $file or $self->throw("Can't open file for read : $file");
|
|
|
156
|
|
|
157 # Main indexing loop
|
|
|
158 while (<FASTA>) {
|
|
|
159 if (/^>/) {
|
|
|
160 # $begin is the position of the first character after the '>'
|
|
|
161 my $begin = tell(FASTA) - length( $_ ) + 1;
|
|
|
162
|
|
|
163 foreach my $id (&$id_parser($_)) {
|
|
|
164 $self->add_record($id, $i, $begin);
|
|
|
165 }
|
|
|
166 }
|
|
|
167 }
|
|
|
168
|
|
|
169 close FASTA;
|
|
|
170 return 1;
|
|
|
171 }
|
|
|
172
|
|
|
173 =head2 id_parser
|
|
|
174
|
|
|
175 Title : id_parser
|
|
|
176 Usage : $index->id_parser( CODE )
|
|
|
177 Function: Stores or returns the code used by record_id to
|
|
|
178 parse the ID for record from a string. Useful
|
|
|
179 for (for instance) specifying a different
|
|
|
180 parser for different flavours of FASTA file.
|
|
|
181 Returns \&default_id_parser (see below) if not
|
|
|
182 set. If you supply your own id_parser
|
|
|
183 subroutine, then it should expect a fasta
|
|
|
184 description line. An entry will be added to
|
|
|
185 the index for each string in the list returned.
|
|
|
186 Example : $index->id_parser( \&my_id_parser )
|
|
|
187 Returns : ref to CODE if called without arguments
|
|
|
188 Args : CODE
|
|
|
189
|
|
|
190 =cut
|
|
|
191
|
|
|
192 sub id_parser {
|
|
|
193 my( $self, $code ) = @_;
|
|
|
194
|
|
|
195 if ($code) {
|
|
|
196 $self->{'_id_parser'} = $code;
|
|
|
197 }
|
|
|
198 return $self->{'_id_parser'} || \&default_id_parser;
|
|
|
199 }
|
|
|
200
|
|
|
201
|
|
|
202
|
|
|
203 =head2 default_id_parser
|
|
|
204
|
|
|
205 Title : default_id_parser
|
|
|
206 Usage : $id = default_id_parser( $header )
|
|
|
207 Function: The default Fasta ID parser for Fasta.pm
|
|
|
208 Returns $1 from applying the regexp /^>\s*(\S+)/
|
|
|
209 to $header.
|
|
|
210 Returns : ID string
|
|
|
211 Args : a fasta header line string
|
|
|
212
|
|
|
213 =cut
|
|
|
214
|
|
|
215 sub default_id_parser {
|
|
|
216 if ($_[0] =~ /^>\s*(\S+)/) {
|
|
|
217 return $1;
|
|
|
218 } else {
|
|
|
219 return;
|
|
|
220 }
|
|
|
221 }
|
|
|
222
|
|
|
223 1;
|
