annotate variant_effect_predictor/Bio/DB/GFF/Util/Binning.pm @ 3:d30fa12e4cc5 default tip

Merge heads 2:a5976b2dce6f and 1:09613ce8151e which were created as a result of a recently fixed bug.
author devteam <devteam@galaxyproject.org>
date Mon, 13 Jan 2014 10:38:30 -0500
parents 1f6dce3d34e0
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
1 =head1 NAME
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
2
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
3 Bio::DB::GFF::Util::Binning - binning utility for Bio::DB::GFF index
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
4
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
5 =head1 SYNOPSIS
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
6
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
7 use Bio::DB::GFF::Util::Binning qw(bin bin_bot bin_top);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
8 my $tier = bin($start,$stop,$min);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
9
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
10 =head1 DESCRIPTION
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
11
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
12 This is a utility module that exports the functions bin(), bin_bot()
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
13 and bin_top(). These functions translate a range on the genome into a
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
14 named bin that is used as an index in the Bio::DB::GFF schema. The
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
15 index makes certain range retrieval queries much faster.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
16
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
17 =head1 API
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
18
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
19 The remainder of the document describes the function calls. No calls
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
20 are exported by default, but must be imported explicitly.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
21
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
22 =over 4
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
23
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
24 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
25
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
26 package Bio::DB::GFF::Util::Binning;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
27
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
28 use strict;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
29 require Exporter;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
30 use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
31 @ISA = 'Exporter';
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
32 @EXPORT_OK = qw(bin bin_bot bin_top);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
33 @EXPORT = @EXPORT_OK;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
34
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
35 =item $bin_name = bin($start,$stop,$bin_size)
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
36
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
37 Given a start, stop and bin size on the genome, translate this
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
38 location into a bin name. In a list context, returns the bin tier
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
39 name and the position that the bin begins.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
40
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
41 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
42
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
43 sub bin {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
44 my ($start,$stop,$min) = @_;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
45 my $tier = $min;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
46 my ($bin_start,$bin_end);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
47 while (1) {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
48 $bin_start = int $start/$tier;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
49 $bin_end = int $stop/$tier;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
50 last if $bin_start == $bin_end;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
51 $tier *= 10;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
52 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
53 return wantarray ? ($tier,$bin_start) : bin_name($tier,$bin_start);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
54 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
55
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
56 =item $bottom = bin_bot($tier,$start)
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
57
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
58 Given a tier name and a range start position, returns the lower end of
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
59 the bin range.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
60
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
61 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
62
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
63 sub bin_bot {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
64 my $tier = shift;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
65 my $pos = shift;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
66 bin_name($tier,int($pos/$tier));
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
67 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
68
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
69 =item $top = bin_top($tier,$end)
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
70
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
71 Given a tier name and the end of a range, returns the upper end of the
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
72 bin range.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
73
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
74 =cut
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
75
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
76 *bin_top = \&bin_bot;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
77
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
78 sub bin_name { sprintf("%d.%06d",@_) }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
79
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
80 sub log10 {
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
81 my $i = shift;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
82 log($i)/log(10);
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
83 }
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
84
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
85 1;
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
86
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
87 =back
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
88
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
89 =head1 BUGS
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
90
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
91 None known yet.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
92
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
93 =head1 SEE ALSO
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
94
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
95 L<Bio::DB::GFF>,
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
96
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
97 =head1 AUTHOR
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
98
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
99 Lincoln Stein E<lt>lstein@cshl.orgE<gt>.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
100
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
101 Copyright (c) 2001 Cold Spring Harbor Laboratory.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
102
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
103 This library is free software; you can redistribute it and/or modify
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
104 it under the same terms as Perl itself.
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
105
1f6dce3d34e0 Uploaded
mahtabm
parents:
diff changeset
106 =cut