|
0
|
1 #
|
|
|
2 #
|
|
|
3 # BioPerl module for Bio::Index::Fastq
|
|
|
4 #
|
|
|
5 # Cared for by Tony Cox <avc@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::Fastq - Interface for indexing (multiple) fastq files
|
|
|
14
|
|
|
15 =head1 SYNOPSIS
|
|
|
16
|
|
|
17 # Complete code for making an index for several
|
|
|
18 # fastq files
|
|
|
19 use Bio::Index::Fastq;
|
|
|
20 use strict;
|
|
|
21
|
|
|
22 my $Index_File_Name = shift;
|
|
|
23 my $inx = Bio::Index::Fastq->new(
|
|
|
24 '-filename' => $Index_File_Name,
|
|
|
25 '-write_flag' => 1);
|
|
|
26 $inx->make_index(@ARGV);
|
|
|
27
|
|
|
28 # Print out several sequences present in the index
|
|
|
29 # in Fastq format
|
|
|
30 use Bio::Index::Fastq;
|
|
|
31 use strict;
|
|
|
32
|
|
|
33 my $Index_File_Name = shift;
|
|
|
34 my $inx = Bio::Index::Fastq->new('-filename' => $Index_File_Name);
|
|
|
35 my $out = Bio::SeqIO->new('-format' => 'Fastq','-fh' => \*STDOUT);
|
|
|
36
|
|
|
37 foreach my $id (@ARGV) {
|
|
|
38 my $seq = $inx->fetch($id); # Returns Bio::Seq::SeqWithQuality object
|
|
|
39 $out->write_seq($seq);
|
|
|
40 }
|
|
|
41
|
|
|
42 # or, alternatively
|
|
|
43
|
|
|
44 my $seq = $inx->get_Seq_by_id($id); #identical to fetch
|
|
|
45
|
|
|
46 =head1 DESCRIPTION
|
|
|
47
|
|
|
48 Inherits functions for managing dbm files from Bio::Index::Abstract.pm,
|
|
|
49 and provides the basic funtionallity for indexing fastq files, and
|
|
|
50 retrieving the sequence from them. Note: for best results 'use strict'.
|
|
|
51
|
|
|
52 Bio::Index::Fastq supports the Bio::DB::BioSeqI interface, meaning
|
|
|
53 it can be used as a Sequence database for other parts of bioperl
|
|
|
54
|
|
|
55 =head1 FEED_BACK
|
|
|
56
|
|
|
57 =head2 Mailing Lists
|
|
|
58
|
|
|
59 User feedback is an integral part of the evolution of this and other
|
|
|
60 Bioperl modules. Send your comments and suggestions preferably to one
|
|
|
61 of the Bioperl mailing lists. Your participation is much appreciated.
|
|
|
62
|
|
|
63 bioperl-l@bioperl.org - General discussion
|
|
|
64 http://bioperl.org/MailList.shtml - About the mailing lists
|
|
|
65
|
|
|
66 =head2 Reporting Bugs
|
|
|
67
|
|
|
68 Report bugs to the Bioperl bug tracking system to help us keep track
|
|
|
69 the bugs and their resolution. Bug reports can be submitted via
|
|
|
70 email or the web:
|
|
|
71
|
|
|
72 bioperl-bugs@bio.perl.org
|
|
|
73 http://bugzilla.bioperl.org/
|
|
|
74
|
|
|
75 =head1 AUTHOR - Tony Cox
|
|
|
76
|
|
|
77 Email - avc@sanger.ac.uk
|
|
|
78
|
|
|
79 =head1 APPENDIX
|
|
|
80
|
|
|
81 The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
|
|
|
82
|
|
|
83 =cut
|
|
|
84
|
|
|
85
|
|
|
86 # Let the code begin...
|
|
|
87
|
|
|
88
|
|
|
89 package Bio::Index::Fastq;
|
|
|
90
|
|
|
91 use vars qw($VERSION @ISA);
|
|
|
92 use strict;
|
|
|
93
|
|
|
94 use Bio::Index::AbstractSeq;
|
|
|
95 use Bio::Seq;
|
|
|
96
|
|
|
97 @ISA = qw(Bio::Index::AbstractSeq);
|
|
|
98
|
|
|
99 #
|
|
|
100 # Suggested fix by Michael G Schwern <schwern@pobox.com> to
|
|
|
101 # get around a clash with CPAN shell...
|
|
|
102 #
|
|
|
103
|
|
|
104 BEGIN {
|
|
|
105 $VERSION = 0.2;
|
|
|
106 }
|
|
|
107
|
|
|
108 sub _version {
|
|
|
109 return $VERSION;
|
|
|
110 }
|
|
|
111
|
|
|
112 =head2 _file_format
|
|
|
113
|
|
|
114 Title : _file_format
|
|
|
115 Function: The file format for this package, which is needed
|
|
|
116 by the SeqIO system when reading the sequence.
|
|
|
117 Returns : 'Fastq'
|
|
|
118
|
|
|
119 =cut
|
|
|
120
|
|
|
121 sub _file_format {
|
|
|
122 return 'Fastq';
|
|
|
123 }
|
|
|
124
|
|
|
125
|
|
|
126
|
|
|
127 =head2 _index_file
|
|
|
128
|
|
|
129 Title : _index_file
|
|
|
130 Usage : $index->_index_file( $file_name, $i )
|
|
|
131 Function: Specialist function to index FASTQ format files.
|
|
|
132 Is provided with a filename and an integer
|
|
|
133 by make_index in its SUPER class.
|
|
|
134 Example :
|
|
|
135 Returns :
|
|
|
136 Args :
|
|
|
137
|
|
|
138 =cut
|
|
|
139
|
|
|
140 sub _index_file {
|
|
|
141 my( $self,
|
|
|
142 $file, # File name
|
|
|
143 $i, # Index-number of file being indexed
|
|
|
144 ) = @_;
|
|
|
145
|
|
|
146 my( $begin, # Offset from start of file of the start
|
|
|
147 # of the last found record.
|
|
|
148 );
|
|
|
149
|
|
|
150 $begin = 0;
|
|
|
151
|
|
|
152 my $id_parser = $self->id_parser;
|
|
|
153 my $c = 0;
|
|
|
154 open FASTQ, $file or $self->throw("Can't open file for read : $file");
|
|
|
155 # Main indexing loop
|
|
|
156 while (<FASTQ>) {
|
|
|
157 if (/^@/) {
|
|
|
158 # $begin is the position of the first character after the '@'
|
|
|
159 my $begin = tell(FASTQ) - length( $_ ) + 1;
|
|
|
160 foreach my $id (&$id_parser($_)) {
|
|
|
161 $self->add_record($id, $i, $begin);
|
|
|
162 $c++;
|
|
|
163 }
|
|
|
164 }
|
|
|
165 }
|
|
|
166
|
|
|
167 close FASTQ;
|
|
|
168 return ($c);
|
|
|
169 }
|
|
|
170
|
|
|
171 =head2 id_parser
|
|
|
172
|
|
|
173 Title : id_parser
|
|
|
174 Usage : $index->id_parser( CODE )
|
|
|
175 Function: Stores or returns the code used by record_id to
|
|
|
176 parse the ID for record from a string. Useful
|
|
|
177 for (for instance) specifying a different
|
|
|
178 parser for different flavours of FASTQ file.
|
|
|
179 Returns \&default_id_parser (see below) if not
|
|
|
180 set. If you supply your own id_parser
|
|
|
181 subroutine, then it should expect a fastq
|
|
|
182 description line. An entry will be added to
|
|
|
183 the index for each string in the list returned.
|
|
|
184 Example : $index->id_parser( \&my_id_parser )
|
|
|
185 Returns : ref to CODE if called without arguments
|
|
|
186 Args : CODE
|
|
|
187
|
|
|
188 =cut
|
|
|
189
|
|
|
190 sub id_parser {
|
|
|
191 my( $self, $code ) = @_;
|
|
|
192
|
|
|
193 if ($code) {
|
|
|
194 $self->{'_id_parser'} = $code;
|
|
|
195 }
|
|
|
196 return $self->{'_id_parser'} || \&default_id_parser;
|
|
|
197 }
|
|
|
198
|
|
|
199
|
|
|
200
|
|
|
201 =head2 default_id_parser
|
|
|
202
|
|
|
203 Title : default_id_parser
|
|
|
204 Usage : $id = default_id_parser( $header )
|
|
|
205 Function: The default Fastq ID parser for Fastq.pm
|
|
|
206 Returns $1 from applying the regexp /^>\s*(\S+)/
|
|
|
207 to $header.
|
|
|
208 Returns : ID string
|
|
|
209 Args : a fastq header line string
|
|
|
210
|
|
|
211 =cut
|
|
|
212
|
|
|
213 sub default_id_parser {
|
|
|
214 if ($_[0] =~ /^@\s*(\S+)/) {
|
|
|
215 return $1;
|
|
|
216 } else {
|
|
|
217 return;
|
|
|
218 }
|
|
|
219 }
|
|
|
220
|
|
|
221 1;
|
