annotate variant_effect_predictor/Bio/Tools/Profile.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 # BioPerl module for Bio::Tools::Profile
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
2 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
3 # Cared for by Balamurugan Kumarasamy
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
4 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
5 # You may distribute this module under the same terms as perl itself
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
6 # POD documentation - main docs before the code
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
7
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
8 =head1 NAME
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
9
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
10 Bio::Tools::Profile - parse Profile output
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
11
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
12 =head1 SYNOPSIS
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
13
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
14 use Bio::Tools::Profile;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
15 my $profile_parser = new Bio::Tools::Profile(-fh =>$filehandle );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
16 while( my $profile_feat = $profile_parser->next_result ) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
17 push @profile_feat, $profile_feat;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
18 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
19
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
20 =head1 DESCRIPTION
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
21
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
22 Parser for Profile output
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
23
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
24 =head1 FEEDBACK
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
25
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
26 =head2 Mailing Lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
27
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
28 User feedback is an integral part of the evolution of this and other
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
29 Bioperl modules. Send your comments and suggestions preferably to
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
30 the Bioperl mailing list. Your participation is much appreciated.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
31
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
32 bioperl-l@bioperl.org - General discussion
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
33 http://bioperl.org/MailList.shtml - About the mailing lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
34
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
35 =head2 Reporting Bugs
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
36
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
37 Report bugs to the Bioperl bug tracking system to help us keep track
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
38 of the bugs and their resolution. Bug reports can be submitted via
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
39 email or the web:
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
40
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
41 bioperl-bugs@bioperl.org
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
42 http://bugzilla.bioperl.org/
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
43 =head1 AUTHOR - Balamurugan Kumarasamy
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
44
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
45 Email: fugui@worf.fugu-sg.org
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
46
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
47 =head1 APPENDIX
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
48
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
49 The rest of the documentation details each of the object methods.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
50 Internal methods are usually preceded with a _
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
51
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
52
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
53 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
54
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
55
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
56 package Bio::Tools::Profile;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
57 use vars qw(@ISA);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
58 use strict;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
59
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
60 use Bio::Root::Root;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
61 use Bio::SeqFeature::FeaturePair;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
62 use Bio::Root::IO;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
63 use Bio::SeqFeature::Generic;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
64
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
65 @ISA = qw(Bio::Root::Root Bio::Root::IO );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
66
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
67
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
68
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
69 =head2 new
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
70
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
71 Title : new
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
72 Usage : my $obj = new Bio::Tools::Profile();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
73 Function: Builds a new Bio::Tools::Profile object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
74 Returns : Bio::Tools::Profile
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
75 Args : -filename
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
76 -fh ($filehandle)
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
77
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
78 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
79
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
80 sub new {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
81 my($class,@args) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
82
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
83 my $self = $class->SUPER::new(@args);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
84 $self->_initialize_io(@args);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
85
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
86 return $self;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
87 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
88
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
89 =head2 next_result
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
90
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
91 Title : next_result
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
92 Usage : my $feat = $profile_parser->next_result
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
93 Function: Get the next result set from parser data
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
94 Returns : L<Bio::SeqFeature::FeaturePair>
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
95 Args : none
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
96
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
97
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
98 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
99
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
100 sub next_result {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
101 my ($self) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
102
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
103 my %printsac;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
104 my $line;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
105 my @features;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
106 while ($_=$self->_readline()) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
107 $line = $_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
108 chomp $line;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
109 my ($nscore,$rawscore,$from,$to,$hfrom,$hto,$ac) = $line =~ /(\S+)\s+(\d+)\s*pos.\s+(\d*)\s*-\s+(\d*)\s*\[\s+(\d*),\s+(\S*)\]\s*(\w+)/;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
110 #for example in this output line
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
111 #38.435 2559 pos. 19958 - 20212 [ 1, -1] PS50011|PROTEIN_KINASE_DOM Protein kinase domain profile.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
112 #$nscore = 38.435
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
113 #$rawscore = 2559
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
114 #$from = 19958
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
115 #$end = 20212
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
116 #$hfrom = 1
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
117 #$hto =-1
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
118 #$ac = PS50011
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
119 my $feat = "$ac,$from,$to,$hfrom,$hto,$nscore";
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
120 my $new_feat= $self->create_feature($feat);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
121 return $new_feat
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
122
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
123 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
124 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
125
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
126
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
127 =head2 create_feature
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
128
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
129 Title : create_feature
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
130 Usage : my $feat= $profile_parser->create_feature($feature)
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
131 Function: creates a Bio::SeqFeature::FeaturePair object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
132 Returns : L<Bio::SeqFeature::FeaturePair>
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
133 Args :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
134
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
135
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
136 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
137
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
138 sub create_feature {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
139 my ($self, $feat) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
140
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
141 my @f = split (/,/,$feat);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
142
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
143
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
144 my $hto = $f[4];
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
145
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
146 if ($f[4] =~ /-1/) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
147
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
148 $hto = $f[2] - $f[1] + 1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
149
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
150 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
151
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
152
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
153 my $feat1 = new Bio::SeqFeature::Generic ( -start => $f[1],
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
154 -end => $f[2],
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
155 -score => $f[5],
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
156 -source=>'pfscan',
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
157 -primary=>$f[0]);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
158
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
159 my $feat2 = new Bio::SeqFeature::Generic (-start => $f[3],
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
160 -end => $hto,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
161 );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
162
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
163 my $feature = new Bio::SeqFeature::FeaturePair(-feature1 => $feat1,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
164 -feature2 => $feat2);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
165
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
166 return $feature;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
167
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
168 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
169 1;