annotate variant_effect_predictor/Bio/Coordinate/Utils.pm @ 2:a5976b2dce6f

changing defualt values for ensembl database
author mahtabm
date Thu, 11 Apr 2013 17:15:42 +1000
parents 1f6dce3d34e0
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
1 # $Id: Utils.pm,v 1.1.2.1 2003/02/20 05:11:45 heikki Exp $
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
2 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
3 # BioPerl module for Bio::Coordinate::Utils
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
4 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
5 # Cared for by Heikki Lehvaslaiho <heikki@ebi.ac.uk>
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
6 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
7 # Copyright Heikki Lehvaslaiho
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
8 #
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
9 # You may distribute this module under the same terms as perl itself
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
10
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
11 # POD documentation - main docs before the code
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
12
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
13 =head1 NAME
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
14
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
15 Bio::Coordinate::Utils - Additional methods to create Bio::Coordinate objects
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
16
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
17 =head1 SYNOPSIS
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
18
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
19 use Bio::Coordinate::Utils;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
20 # get a Bio::Align::AlignI compliant object, $aln, somehow
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
21 # it could be a Bio::SimpleAlign
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
22
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
23 $mapper = Bio::Coordinate::Utils->from_align($aln, 1);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
24
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
25 =head1 DESCRIPTION
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
26
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
27 This class is a holder of methods that work on or create
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
28 Bio::Coordinate::MapperI- compliant objects. . These methods are not
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
29 part of the Bio::Coordinate::MapperI interface and should in general
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
30 not be essential to the primary function of sequence objects. If you
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
31 are thinking of adding essential functions, it might be better to
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
32 create your own sequence class. See L<Bio::PrimarySeqI>,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
33 L<Bio::PrimarySeq>, and L<Bio::Seq> for more.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
34
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
35 =head1 FEEDBACK
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
36
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
37 =head2 Mailing Lists
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
38
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
39 User feedback is an integral part of the evolution of this and other
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
40 Bioperl modules. Send your comments and suggestions preferably to one
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
41 of the Bioperl mailing lists. Your participation is much appreciated.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
42
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
43 bioperl-l@bioperl.org - General discussion
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
44 http://bio.perl.org/MailList.html - About the mailing lists
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
45
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
46 =head2 Reporting Bugs
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
47
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
48 Report bugs to the Bioperl bug tracking system to help us keep track
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
49 the bugs and their resolution. Bug reports can be submitted via email
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
50 or the web:
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
51
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
52 bioperl-bugs@bio.perl.org
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
53 http://bugzilla.bioperl.org/
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
54
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
55 =head1 AUTHOR - Heikki Lehvaslaiho
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
56
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
57 Email: heikki@ebi.ac.uk
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
58 Address:
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
59
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
60 EMBL Outstation, European Bioinformatics Institute
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
61 Wellcome Trust Genome Campus, Hinxton
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
62 Cambs. CB10 1SD, United Kingdom
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
63
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
64 =head1 APPENDIX
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
65
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
66 The rest of the documentation details each of the object
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
67 methods. Internal methods are usually preceded with a _
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
68
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
69 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
70
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
71
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
72 # Let the code begin...
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
73
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
74
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
75 package Bio::Coordinate::Utils;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
76 use vars qw(@ISA);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
77
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
78 use Bio::Location::Simple;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
79 use Bio::Coordinate::Pair;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
80 use Bio::Coordinate::Collection;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
81
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
82 use strict;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
83
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
84 @ISA = qw(Bio::Root::Root);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
85 # new inherited from Root
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
86
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
87 =head2 from_align
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
88
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
89 Title : from_align
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
90 Usage : $mapper = Bio::Coordinate::Utils->from_align($aln, 1);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
91 Function:
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
92 Create a mapper out of an alignment.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
93 The mapper will return a value only when both ends of
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
94 the input range find a match.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
95
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
96 Note: This implementation works only on pairwise alignments
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
97 and is not yet well tested!
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
98
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
99 Returns : A Bio::Coordinate::MapperI
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
100 Args : Bio::Align::AlignI object
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
101 Id for the reference sequence, optional
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
102
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
103 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
104
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
105 sub from_align {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
106 my ($self, $aln, $ref ) = @_;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
107
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
108 $aln->isa('Bio::Align::AlignI') ||
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
109 $self->throw('Not a Bio::Align::AlignI object but ['. ref($self). ']');
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
110
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
111 # default reference sequence to the first sequence
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
112 $ref ||= 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
113
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
114 my $collection = Bio::Coordinate::Collection->new(-return_match=>1);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
115
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
116 # this works only for pairs, so split the MSA
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
117 # take the ref
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
118 #foreach remaining seq in aln, do:
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
119
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
120 my $cs = $aln->consensus_string(49);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
121 while ( $cs =~ /([^-]+)/g) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
122
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
123 # alignment coordinates
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
124 my $start = pos($cs) - length($1) + 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
125 my $end = $start+length($1)-1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
126
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
127 my $seq1 = $aln->get_seq_by_pos(1);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
128 my $seq2 = $aln->get_seq_by_pos(2);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
129
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
130 my $match1 = Bio::Location::Simple->new
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
131 (-seq_id => $seq1->id,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
132 -start => $seq1->location_from_column($start)->start,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
133 -end => $seq1->location_from_column($end)->start,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
134 -strand => $seq1->strand );
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
135
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
136 my $match2 = Bio::Location::Simple->new
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
137 (-seq_id => $seq2->id,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
138 -start => $seq2->location_from_column($start)->start,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
139 -end => $seq2->location_from_column($end)->start,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
140 -strand => $seq2->strand );
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
141
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
142 my $pair = Bio::Coordinate::Pair->
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
143 new(-in => $match1,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
144 -out => $match2
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
145 );
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
146
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
147 $collection->add_mapper($pair);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
148 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
149
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
150 return @{$collection->each_mapper}[0] if $collection->each_mapper == 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
151 return $collection;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
152
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
153 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
154
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
155
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
156
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
157 1;