Mercurial > repos > mahtabm > ensembl
comparison variant_effect_predictor/Bio/DB/GFF/Util/Binning.pm @ 0:1f6dce3d34e0
Uploaded
author | mahtabm |
---|---|
date | Thu, 11 Apr 2013 02:01:53 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:1f6dce3d34e0 |
---|---|
1 =head1 NAME | |
2 | |
3 Bio::DB::GFF::Util::Binning - binning utility for Bio::DB::GFF index | |
4 | |
5 =head1 SYNOPSIS | |
6 | |
7 use Bio::DB::GFF::Util::Binning qw(bin bin_bot bin_top); | |
8 my $tier = bin($start,$stop,$min); | |
9 | |
10 =head1 DESCRIPTION | |
11 | |
12 This is a utility module that exports the functions bin(), bin_bot() | |
13 and bin_top(). These functions translate a range on the genome into a | |
14 named bin that is used as an index in the Bio::DB::GFF schema. The | |
15 index makes certain range retrieval queries much faster. | |
16 | |
17 =head1 API | |
18 | |
19 The remainder of the document describes the function calls. No calls | |
20 are exported by default, but must be imported explicitly. | |
21 | |
22 =over 4 | |
23 | |
24 =cut | |
25 | |
26 package Bio::DB::GFF::Util::Binning; | |
27 | |
28 use strict; | |
29 require Exporter; | |
30 use vars qw($VERSION @ISA @EXPORT @EXPORT_OK); | |
31 @ISA = 'Exporter'; | |
32 @EXPORT_OK = qw(bin bin_bot bin_top); | |
33 @EXPORT = @EXPORT_OK; | |
34 | |
35 =item $bin_name = bin($start,$stop,$bin_size) | |
36 | |
37 Given a start, stop and bin size on the genome, translate this | |
38 location into a bin name. In a list context, returns the bin tier | |
39 name and the position that the bin begins. | |
40 | |
41 =cut | |
42 | |
43 sub bin { | |
44 my ($start,$stop,$min) = @_; | |
45 my $tier = $min; | |
46 my ($bin_start,$bin_end); | |
47 while (1) { | |
48 $bin_start = int $start/$tier; | |
49 $bin_end = int $stop/$tier; | |
50 last if $bin_start == $bin_end; | |
51 $tier *= 10; | |
52 } | |
53 return wantarray ? ($tier,$bin_start) : bin_name($tier,$bin_start); | |
54 } | |
55 | |
56 =item $bottom = bin_bot($tier,$start) | |
57 | |
58 Given a tier name and a range start position, returns the lower end of | |
59 the bin range. | |
60 | |
61 =cut | |
62 | |
63 sub bin_bot { | |
64 my $tier = shift; | |
65 my $pos = shift; | |
66 bin_name($tier,int($pos/$tier)); | |
67 } | |
68 | |
69 =item $top = bin_top($tier,$end) | |
70 | |
71 Given a tier name and the end of a range, returns the upper end of the | |
72 bin range. | |
73 | |
74 =cut | |
75 | |
76 *bin_top = \&bin_bot; | |
77 | |
78 sub bin_name { sprintf("%d.%06d",@_) } | |
79 | |
80 sub log10 { | |
81 my $i = shift; | |
82 log($i)/log(10); | |
83 } | |
84 | |
85 1; | |
86 | |
87 =back | |
88 | |
89 =head1 BUGS | |
90 | |
91 None known yet. | |
92 | |
93 =head1 SEE ALSO | |
94 | |
95 L<Bio::DB::GFF>, | |
96 | |
97 =head1 AUTHOR | |
98 | |
99 Lincoln Stein E<lt>lstein@cshl.orgE<gt>. | |
100 | |
101 Copyright (c) 2001 Cold Spring Harbor Laboratory. | |
102 | |
103 This library is free software; you can redistribute it and/or modify | |
104 it under the same terms as Perl itself. | |
105 | |
106 =cut |