annotate variant_effect_predictor/Bio/Coordinate/Utils.pm @ 1:d6778b5d8382 draft default tip

Deleted selected files
author willmclaren
date Fri, 03 Aug 2012 10:05:43 -0400
parents 21066c0abaf5
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
1 # $Id: Utils.pm,v 1.1.2.1 2003/02/20 05:11:45 heikki Exp $
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
2 #
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
3 # BioPerl module for Bio::Coordinate::Utils
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
4 #
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
5 # Cared for by Heikki Lehvaslaiho <heikki@ebi.ac.uk>
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
6 #
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
7 # Copyright Heikki Lehvaslaiho
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
8 #
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
9 # You may distribute this module under the same terms as perl itself
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
10
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
11 # POD documentation - main docs before the code
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
12
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
13 =head1 NAME
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
14
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
15 Bio::Coordinate::Utils - Additional methods to create Bio::Coordinate objects
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
16
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
17 =head1 SYNOPSIS
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
18
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
19 use Bio::Coordinate::Utils;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
20 # get a Bio::Align::AlignI compliant object, $aln, somehow
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
21 # it could be a Bio::SimpleAlign
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
22
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
23 $mapper = Bio::Coordinate::Utils->from_align($aln, 1);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
24
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
25 =head1 DESCRIPTION
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
26
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
27 This class is a holder of methods that work on or create
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
28 Bio::Coordinate::MapperI- compliant objects. . These methods are not
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
29 part of the Bio::Coordinate::MapperI interface and should in general
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
30 not be essential to the primary function of sequence objects. If you
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
31 are thinking of adding essential functions, it might be better to
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
32 create your own sequence class. See L<Bio::PrimarySeqI>,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
33 L<Bio::PrimarySeq>, and L<Bio::Seq> for more.
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
34
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
35 =head1 FEEDBACK
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
36
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
37 =head2 Mailing Lists
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
38
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
39 User feedback is an integral part of the evolution of this and other
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
40 Bioperl modules. Send your comments and suggestions preferably to one
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
41 of the Bioperl mailing lists. Your participation is much appreciated.
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
42
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
43 bioperl-l@bioperl.org - General discussion
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
44 http://bio.perl.org/MailList.html - About the mailing lists
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
45
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
46 =head2 Reporting Bugs
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
47
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
48 Report bugs to the Bioperl bug tracking system to help us keep track
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
49 the bugs and their resolution. Bug reports can be submitted via email
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
50 or the web:
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
51
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
52 bioperl-bugs@bio.perl.org
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
53 http://bugzilla.bioperl.org/
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
54
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
55 =head1 AUTHOR - Heikki Lehvaslaiho
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
56
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
57 Email: heikki@ebi.ac.uk
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
58 Address:
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
59
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
60 EMBL Outstation, European Bioinformatics Institute
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
61 Wellcome Trust Genome Campus, Hinxton
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
62 Cambs. CB10 1SD, United Kingdom
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
63
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
64 =head1 APPENDIX
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
65
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
66 The rest of the documentation details each of the object
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
67 methods. Internal methods are usually preceded with a _
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
68
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
69 =cut
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
70
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
71
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
72 # Let the code begin...
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
73
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
74
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
75 package Bio::Coordinate::Utils;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
76 use vars qw(@ISA);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
77
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
78 use Bio::Location::Simple;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
79 use Bio::Coordinate::Pair;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
80 use Bio::Coordinate::Collection;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
81
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
82 use strict;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
83
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
84 @ISA = qw(Bio::Root::Root);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
85 # new inherited from Root
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
86
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
87 =head2 from_align
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
88
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
89 Title : from_align
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
90 Usage : $mapper = Bio::Coordinate::Utils->from_align($aln, 1);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
91 Function:
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
92 Create a mapper out of an alignment.
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
93 The mapper will return a value only when both ends of
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
94 the input range find a match.
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
95
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
96 Note: This implementation works only on pairwise alignments
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
97 and is not yet well tested!
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
98
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
99 Returns : A Bio::Coordinate::MapperI
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
100 Args : Bio::Align::AlignI object
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
101 Id for the reference sequence, optional
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
102
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
103 =cut
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
104
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
105 sub from_align {
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
106 my ($self, $aln, $ref ) = @_;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
107
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
108 $aln->isa('Bio::Align::AlignI') ||
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
109 $self->throw('Not a Bio::Align::AlignI object but ['. ref($self). ']');
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
110
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
111 # default reference sequence to the first sequence
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
112 $ref ||= 1;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
113
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
114 my $collection = Bio::Coordinate::Collection->new(-return_match=>1);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
115
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
116 # this works only for pairs, so split the MSA
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
117 # take the ref
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
118 #foreach remaining seq in aln, do:
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
119
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
120 my $cs = $aln->consensus_string(49);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
121 while ( $cs =~ /([^-]+)/g) {
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
122
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
123 # alignment coordinates
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
124 my $start = pos($cs) - length($1) + 1;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
125 my $end = $start+length($1)-1;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
126
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
127 my $seq1 = $aln->get_seq_by_pos(1);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
128 my $seq2 = $aln->get_seq_by_pos(2);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
129
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
130 my $match1 = Bio::Location::Simple->new
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
131 (-seq_id => $seq1->id,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
132 -start => $seq1->location_from_column($start)->start,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
133 -end => $seq1->location_from_column($end)->start,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
134 -strand => $seq1->strand );
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
135
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
136 my $match2 = Bio::Location::Simple->new
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
137 (-seq_id => $seq2->id,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
138 -start => $seq2->location_from_column($start)->start,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
139 -end => $seq2->location_from_column($end)->start,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
140 -strand => $seq2->strand );
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
141
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
142 my $pair = Bio::Coordinate::Pair->
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
143 new(-in => $match1,
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
144 -out => $match2
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
145 );
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
146
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
147 $collection->add_mapper($pair);
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
148 }
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
149
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
150 return @{$collection->each_mapper}[0] if $collection->each_mapper == 1;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
151 return $collection;
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
152
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
153 }
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
154
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
155
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
156
21066c0abaf5 Uploaded
willmclaren
parents:
diff changeset
157 1;