annotate variant_effect_predictor/Bio/AlignIO/bl2seq.pm @ 0:2bc9b66ada89 draft default tip

Uploaded
author mahtabm
date Thu, 11 Apr 2013 06:29:17 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
1 # $Id: bl2seq.pm,v 1.13.2.1 2003/06/18 12:19:52 jason Exp $
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
2 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
3 # BioPerl module for Bio::AlignIO::bl2seq
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
4
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
5 # based on the Bio::SeqIO modules
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
6 # by Ewan Birney <birney@sanger.ac.uk>
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
7 # and Lincoln Stein <lstein@cshl.org>
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
8 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
9 # the Bio::Tools::BPlite modules by
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
10 # Ian Korf (ikorf@sapiens.wustl.edu, http://sapiens.wustl.edu/~ikorf),
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
11 # Lorenz Pollak (lorenz@ist.org, bioperl port)
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
12 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
13 # and the SimpleAlign.pm module of Ewan Birney
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
14 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
15 # Copyright Peter Schattner
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
16 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
17 # You may distribute this module under the same terms as perl itself
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
18 # _history
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
19 # September 5, 2000
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
20 # POD documentation - main docs before the code
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
21
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
22 =head1 NAME
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
23
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
24 Bio::AlignIO::bl2seq - bl2seq sequence input/output stream
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
25
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
26 =head1 SYNOPSIS
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
27
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
28 Do not use this module directly. Use it via the L<Bio::AlignIO> class, as in:
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
29
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
30 use Bio::AlignIO;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
31
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
32 $in = Bio::AlignIO->new(-file => "inputfilename" , '-format' => 'bl2seq');
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
33 $aln = $in->next_aln();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
34
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
35
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
36 =head1 DESCRIPTION
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
37
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
38 This object can create L<Bio::SimpleAlign> sequence alignment objects (of
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
39 2 sequences) from bl2seq BLAST reports.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
40
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
41 A nice feature of this module is that- in combination with
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
42 StandAloneBlast.pm or remote blasting - it can be used to align 2
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
43 sequences and make a SimpleAlign object from them which can then be
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
44 manipulated using any SimpleAlign.pm methods, eg:
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
45
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
46 #Get 2 sequences
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
47 $str = Bio::SeqIO->new(-file=>'t/amino.fa' , '-format' => 'Fasta', );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
48 my $seq3 = $str->next_seq();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
49 my $seq4 = $str->next_seq();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
50
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
51 # Run bl2seq on them
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
52 $factory = Bio::Tools::StandAloneBlast->new('program' => 'blastp',
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
53 'outfile' => 'bl2seq.out');
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
54 my $bl2seq_report = $factory->bl2seq($seq3, $seq4);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
55
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
56 # Use AlignIO.pm to create a SimpleAlign object from the bl2seq report
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
57 $str = Bio::AlignIO->new(-file=> 'bl2seq.out','-format' => 'bl2seq');
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
58 $aln = $str->next_aln();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
59
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
60 Pass in -report_type flag when initializing the object to have this
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
61 pass through to the Bio::Tools::BPbl2seq object. See that object.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
62
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
63 =head1 FEEDBACK
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
64
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
65 =head2 Mailing Lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
66
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
67 User feedback is an integral part of the evolution of this and other
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
68 Bioperl modules. Send your comments and suggestions preferably to one
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
69 of the Bioperl mailing lists. Your participation is much appreciated.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
70
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
71 bioperl-l@bioperl.org - General discussion
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
72 http://bio.perl.org/MailList.html - About the mailing lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
73
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
74 =head2 Reporting Bugs
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
75
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
76 Report bugs to the Bioperl bug tracking system to help us keep track
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
77 the bugs and their resolution.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
78 Bug reports can be submitted via email or the web:
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
79
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
80 bioperl-bugs@bio.perl.org
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
81 http://bugzilla.bioperl.org/
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
82
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
83 =head1 AUTHOR - Peter Schattner
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
84
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
85 Email: schattner@alum.mit.edu
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
86
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
87
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
88 =head1 APPENDIX
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
89
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
90 The rest of the documentation details each of the object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
91 methods. Internal methods are usually preceded with a _
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
92
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
93 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
94
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
95 # Let the code begin...
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
96
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
97 package Bio::AlignIO::bl2seq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
98 use vars qw(@ISA);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
99 use strict;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
100 # Object preamble - inherits from Bio::Root::Object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
101
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
102 use Bio::AlignIO;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
103 use Bio::Tools::BPbl2seq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
104
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
105 @ISA = qw(Bio::AlignIO);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
106
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
107
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
108
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
109 sub _initialize {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
110 my ($self,@args) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
111 $self->SUPER::_initialize(@args);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
112 ($self->{'report_type'}) = $self->_rearrange([qw(REPORT_TYPE)],
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
113 @args);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
114 return 1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
115 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
116
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
117 =head2 next_aln
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
118
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
119 Title : next_aln
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
120 Usage : $aln = $stream->next_aln()
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
121 Function: returns the next alignment in the stream.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
122 Returns : L<Bio::Align::AlignI> object - returns 0 on end of file
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
123 or on error
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
124 Args : NONE
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
125
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
126 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
127
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
128 sub next_aln {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
129 my $self = shift;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
130 my ($start,$end,$name,$seqname,$seq,$seqchar);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
131 my $aln = Bio::SimpleAlign->new(-source => 'bl2seq');
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
132 $self->{'bl2seqobj'} =
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
133 $self->{'bl2seqobj'} || Bio::Tools::BPbl2seq->new(-fh => $self->_fh,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
134 -report_type => $self->{'report_type'});
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
135 my $bl2seqobj = $self->{'bl2seqobj'};
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
136 my $hsp = $bl2seqobj->next_feature;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
137 $seqchar = $hsp->querySeq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
138 $start = $hsp->query->start;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
139 $end = $hsp->query->end;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
140 $seqname = 'Query-sequence'; # Query name not present in bl2seq report
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
141
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
142 # unless ($seqchar && $start && $end && $seqname) {return 0} ;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
143 unless ($seqchar && $start && $end ) {return 0} ;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
144
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
145 $seq = new Bio::LocatableSeq('-seq'=>$seqchar,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
146 '-id'=>$seqname,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
147 '-start'=>$start,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
148 '-end'=>$end,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
149 );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
150
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
151 $aln->add_seq($seq);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
152
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
153 $seqchar = $hsp->sbjctSeq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
154 $start = $hsp->hit->start;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
155 $end = $hsp->hit->end;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
156 $seqname = $bl2seqobj->sbjctName;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
157
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
158 unless ($seqchar && $start && $end && $seqname) {return 0} ;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
159
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
160 $seq = new Bio::LocatableSeq('-seq'=>$seqchar,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
161 '-id'=>$seqname,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
162 '-start'=>$start,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
163 '-end'=>$end,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
164 );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
165
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
166 $aln->add_seq($seq);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
167
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
168 return $aln;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
169
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
170 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
171
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
172
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
173 =head2 write_aln
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
174
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
175 Title : write_aln
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
176 Usage : $stream->write_aln(@aln)
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
177 Function: writes the $aln object into the stream in bl2seq format
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
178 Returns : 1 for success and 0 for error
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
179 Args : L<Bio::Align::AlignI> object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
180
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
181
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
182 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
183
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
184 sub write_aln {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
185 my ($self,@aln) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
186
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
187 $self->throw("Sorry: writing bl2seq output is not available! /n");
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
188 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
189
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
190 1;