|
0
|
1 # $Id: EPCR.pm,v 1.8 2002/12/01 00:05:21 jason Exp $
|
|
|
2 #
|
|
|
3 # BioPerl module for Bio::Tools::EPCR
|
|
|
4 #
|
|
|
5 # Cared for by Jason Stajich <jason@bioperl.org>
|
|
|
6 #
|
|
|
7 # Copyright Jason Stajich
|
|
|
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::Tools::EPCR - Parse ePCR output and make features
|
|
|
16
|
|
|
17 =head1 SYNOPSIS
|
|
|
18
|
|
|
19 # A simple annotation pipeline wrapper for ePCR data
|
|
|
20 # assuming ePCR data is already generated in file seq1.epcr
|
|
|
21 # and sequence data is in fasta format in file called seq1.fa
|
|
|
22
|
|
|
23 use Bio::Tools::EPCR;
|
|
|
24 use Bio::SeqIO;
|
|
|
25 my $parser = new Bio::Tools::EPCR(-file => 'seq1.epcr');
|
|
|
26 my $seqio = new Bio::SeqIO(-format => 'fasta', -file => 'seq1.fa');
|
|
|
27 my $seq = $seqio->next_seq || die("cannot get a seq object from SeqIO");
|
|
|
28
|
|
|
29 while( my $feat = $parser->next_feature ) {
|
|
|
30 # add EPCR annotation to a sequence
|
|
|
31 $seq->add_SeqFeature($feat);
|
|
|
32 }
|
|
|
33 my $seqout = new Bio::SeqIO(-format => 'embl');
|
|
|
34 $seqout->write_seq($seq);
|
|
|
35
|
|
|
36
|
|
|
37 =head1 DESCRIPTION
|
|
|
38
|
|
|
39 This object serves as a parser for ePCR data, creating a
|
|
|
40 Bio::SeqFeatureI for each ePCR hit. These can be processed or added
|
|
|
41 as annotation to an existing Bio::SeqI object for the purposes of
|
|
|
42 automated annotation.
|
|
|
43
|
|
|
44 =head1 FEEDBACK
|
|
|
45
|
|
|
46 =head2 Mailing Lists
|
|
|
47
|
|
|
48 User feedback is an integral part of the evolution of this and other
|
|
|
49 Bioperl modules. Send your comments and suggestions preferably to
|
|
|
50 the Bioperl mailing list. Your participation is much appreciated.
|
|
|
51
|
|
|
52 bioperl-l@bioperl.org - General discussion
|
|
|
53 http://bioperl.org/MailList.shtml - About the mailing lists
|
|
|
54
|
|
|
55 =head2 Reporting Bugs
|
|
|
56
|
|
|
57 Report bugs to the Bioperl bug tracking system to help us keep track
|
|
|
58 of the bugs and their resolution. Bug reports can be submitted via
|
|
|
59 email or the web:
|
|
|
60
|
|
|
61 bioperl-bugs@bioperl.org
|
|
|
62 http://bugzilla.bioperl.org/
|
|
|
63
|
|
|
64 =head1 AUTHOR - Jason Stajich
|
|
|
65
|
|
|
66 Email jason@bioperl.org
|
|
|
67
|
|
|
68 Describe contact details here
|
|
|
69
|
|
|
70 =head1 APPENDIX
|
|
|
71
|
|
|
72 The rest of the documentation details each of the object methods.
|
|
|
73 Internal methods are usually preceded with a _
|
|
|
74
|
|
|
75 =cut
|
|
|
76
|
|
|
77
|
|
|
78 # Let the code begin...
|
|
|
79
|
|
|
80
|
|
|
81 package Bio::Tools::EPCR;
|
|
|
82 use vars qw(@ISA);
|
|
|
83 use strict;
|
|
|
84
|
|
|
85 use Bio::Root::Root;
|
|
|
86 use Bio::SeqAnalysisParserI;
|
|
|
87 use Bio::SeqFeature::FeaturePair;
|
|
|
88 use Bio::SeqFeature::Generic;
|
|
|
89
|
|
|
90 @ISA = qw(Bio::Root::Root Bio::SeqAnalysisParserI Bio::Root::IO );
|
|
|
91
|
|
|
92 =head2 new
|
|
|
93
|
|
|
94 Title : new
|
|
|
95 Usage : my $epcr = new Bio::Tools::EPCR(-file => $file);
|
|
|
96 Function: Initializes a new EPCR parser
|
|
|
97 Returns : Bio::Tools::EPCR
|
|
|
98 Args : -fh => filehandle
|
|
|
99 OR
|
|
|
100 -file => filename
|
|
|
101
|
|
|
102 =cut
|
|
|
103
|
|
|
104 sub new {
|
|
|
105 my($class,@args) = @_;
|
|
|
106
|
|
|
107 my $self = $class->SUPER::new(@args);
|
|
|
108 $self->_initialize_io(@args);
|
|
|
109
|
|
|
110 return $self;
|
|
|
111 }
|
|
|
112
|
|
|
113 =head2 next_feature
|
|
|
114
|
|
|
115 Title : next_feature
|
|
|
116 Usage : $seqfeature = $obj->next_feature();
|
|
|
117 Function: Returns the next feature available in the analysis result, or
|
|
|
118 undef if there are no more features.
|
|
|
119 Example :
|
|
|
120 Returns : A Bio::SeqFeatureI implementing object, or undef if there are no
|
|
|
121 more features.
|
|
|
122 Args : none
|
|
|
123
|
|
|
124 =cut
|
|
|
125
|
|
|
126 sub next_feature {
|
|
|
127 my ($self) = @_;
|
|
|
128 my $line = $self->_readline;
|
|
|
129 return undef unless defined($line);
|
|
|
130 chomp($line);
|
|
|
131 my($seqname,$location,$mkrname, $rest) = split(/\s+/,$line,4);
|
|
|
132
|
|
|
133 my ($start,$end) = ($location =~ /(\S+)\.\.(\S+)/);
|
|
|
134
|
|
|
135 # If we require that e-PCR is run with D=1 we can detect a strand
|
|
|
136 # for now hardcoded to 0
|
|
|
137
|
|
|
138 my $strand = 0;
|
|
|
139 my $markerfeature = new Bio::SeqFeature::Generic ( '-start' => $start,
|
|
|
140 '-end' => $end,
|
|
|
141 '-strand' => $strand,
|
|
|
142 '-source' => 'e-PCR',
|
|
|
143 '-primary' => 'sts',
|
|
|
144 '-seq_id' => $seqname,
|
|
|
145 '-tag' => {
|
|
|
146 'name'=> $mkrname,
|
|
|
147 'note'=> $rest,
|
|
|
148 });
|
|
|
149 return $markerfeature;
|
|
|
150 }
|
|
|
151
|
|
|
152 1;
|
