| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
# |
|
2
|
|
|
|
|
|
|
# BioPerl module for Bio::Tools::EMBOSS::Palindrome |
|
3
|
|
|
|
|
|
|
# |
|
4
|
|
|
|
|
|
|
# Please direct questions and support issues to |
|
5
|
|
|
|
|
|
|
# |
|
6
|
|
|
|
|
|
|
# Cared for by Jason Stajich |
|
7
|
|
|
|
|
|
|
# |
|
8
|
|
|
|
|
|
|
# Copyright Jason Stajich |
|
9
|
|
|
|
|
|
|
# |
|
10
|
|
|
|
|
|
|
# You may distribute this module under the same terms as perl itself |
|
11
|
|
|
|
|
|
|
|
|
12
|
|
|
|
|
|
|
# POD documentation - main docs before the code |
|
13
|
|
|
|
|
|
|
|
|
14
|
|
|
|
|
|
|
=head1 NAME |
|
15
|
|
|
|
|
|
|
|
|
16
|
|
|
|
|
|
|
Bio::Tools::EMBOSS::Palindrome - parse EMBOSS palindrome output |
|
17
|
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
=head1 SYNOPSIS |
|
19
|
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
# a simple script to turn palindrome output into GFF3 |
|
21
|
|
|
|
|
|
|
use Bio::Tools::EMBOSS::Palindrome; |
|
22
|
|
|
|
|
|
|
use Bio::Tools::GFF; |
|
23
|
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
my $parser = Bio::Tools::EMBOSS::Palindrome->new(-file => $filename); |
|
25
|
|
|
|
|
|
|
my $out = Bio::Tools::GFF->new(-gff_version => 3, |
|
26
|
|
|
|
|
|
|
-file => ">$filename.gff"); |
|
27
|
|
|
|
|
|
|
while( my $seq = $parser->next_seq ) { |
|
28
|
|
|
|
|
|
|
for my $feat ( $seq->get_SeqFeatures ) { |
|
29
|
|
|
|
|
|
|
$out->write_feature($feat); |
|
30
|
|
|
|
|
|
|
} |
|
31
|
|
|
|
|
|
|
} |
|
32
|
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
=head1 DESCRIPTION |
|
34
|
|
|
|
|
|
|
|
|
35
|
|
|
|
|
|
|
This is a parser for the EMBOSS tool 'palindrome'. It will produce a |
|
36
|
|
|
|
|
|
|
L object for each sequence analyzed. The sequence will be |
|
37
|
|
|
|
|
|
|
empty (but will be of the correct length) and will have attached to it |
|
38
|
|
|
|
|
|
|
L objects which wil |
|
39
|
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
=head2 FUTURE WORK |
|
42
|
|
|
|
|
|
|
|
|
43
|
|
|
|
|
|
|
It may be consolidated into another framework at a later time, but for |
|
44
|
|
|
|
|
|
|
the time being it will stay a separate modules. |
|
45
|
|
|
|
|
|
|
|
|
46
|
|
|
|
|
|
|
=head1 FEEDBACK |
|
47
|
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
=head2 Mailing Lists |
|
49
|
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
User feedback is an integral part of the evolution of this and other |
|
51
|
|
|
|
|
|
|
Bioperl modules. Send your comments and suggestions preferably to |
|
52
|
|
|
|
|
|
|
the Bioperl mailing list. Your participation is much appreciated. |
|
53
|
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
bioperl-l@bioperl.org - General discussion |
|
55
|
|
|
|
|
|
|
http://bioperl.org/wiki/Mailing_lists - About the mailing lists |
|
56
|
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
=head2 Support |
|
58
|
|
|
|
|
|
|
|
|
59
|
|
|
|
|
|
|
Please direct usage questions or support issues to the mailing list: |
|
60
|
|
|
|
|
|
|
|
|
61
|
|
|
|
|
|
|
I |
|
62
|
|
|
|
|
|
|
|
|
63
|
|
|
|
|
|
|
rather than to the module maintainer directly. Many experienced and |
|
64
|
|
|
|
|
|
|
reponsive experts will be able look at the problem and quickly |
|
65
|
|
|
|
|
|
|
address it. Please include a thorough description of the problem |
|
66
|
|
|
|
|
|
|
with code and data examples if at all possible. |
|
67
|
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
=head2 Reporting Bugs |
|
69
|
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
Report bugs to the Bioperl bug tracking system to help us keep track |
|
71
|
|
|
|
|
|
|
of the bugs and their resolution. Bug reports can be submitted via |
|
72
|
|
|
|
|
|
|
email or the web: |
|
73
|
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
https://github.com/bioperl/bioperl-live/issues |
|
75
|
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
=head1 AUTHOR - Jason Stajich |
|
77
|
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
Email jason-at-bioperl-dot-org |
|
79
|
|
|
|
|
|
|
|
|
80
|
|
|
|
|
|
|
=head1 APPENDIX |
|
81
|
|
|
|
|
|
|
|
|
82
|
|
|
|
|
|
|
The rest of the documentation details each of the object methods. |
|
83
|
|
|
|
|
|
|
Internal methods are usually preceded with a _ |
|
84
|
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
=cut |
|
86
|
|
|
|
|
|
|
|
|
87
|
|
|
|
|
|
|
|
|
88
|
|
|
|
|
|
|
# Let the code begin... |
|
89
|
|
|
|
|
|
|
|
|
90
|
|
|
|
|
|
|
|
|
91
|
|
|
|
|
|
|
package Bio::Tools::EMBOSS::Palindrome; |
|
92
|
1
|
|
|
1
|
|
519
|
use vars qw($DEFAULT_SOURCETAG); |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
36
|
|
|
93
|
1
|
|
|
1
|
|
4
|
use strict; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
17
|
|
|
94
|
|
|
|
|
|
|
|
|
95
|
1
|
|
|
1
|
|
238
|
use Bio::SeqFeature::FeaturePair; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
28
|
|
|
96
|
1
|
|
|
1
|
|
6
|
use Bio::SeqFeature::Generic; |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
18
|
|
|
97
|
|
|
|
|
|
|
|
|
98
|
1
|
|
|
1
|
|
4
|
use base qw(Bio::Root::IO); |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
577
|
|
|
99
|
|
|
|
|
|
|
$DEFAULT_SOURCETAG = 'palindrome'; |
|
100
|
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
=head2 new |
|
102
|
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
Title : new |
|
104
|
|
|
|
|
|
|
Usage : my $obj = Bio::Tools::EMBOSS::Palindrome->new(); |
|
105
|
|
|
|
|
|
|
Function: Builds a new Bio::Tools::EMBOSS::Palindrome object |
|
106
|
|
|
|
|
|
|
Returns : an instance of Bio::Tools::EMBOSS::Palindrome |
|
107
|
|
|
|
|
|
|
Args : -file/-fh => a filename or filehandle for |
|
108
|
|
|
|
|
|
|
initializing the parser |
|
109
|
|
|
|
|
|
|
|
|
110
|
|
|
|
|
|
|
=cut |
|
111
|
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
=head2 next_seq |
|
113
|
|
|
|
|
|
|
|
|
114
|
|
|
|
|
|
|
Title : next_seq |
|
115
|
|
|
|
|
|
|
Usage : my $seq = $parser->next_seq; |
|
116
|
|
|
|
|
|
|
Function: Get the next feature set from the |
|
117
|
|
|
|
|
|
|
Returns : L object |
|
118
|
|
|
|
|
|
|
Args : none |
|
119
|
|
|
|
|
|
|
|
|
120
|
|
|
|
|
|
|
|
|
121
|
|
|
|
|
|
|
=cut |
|
122
|
|
|
|
|
|
|
|
|
123
|
|
|
|
|
|
|
sub next_seq { |
|
124
|
1
|
|
|
1
|
1
|
5
|
my ($self) = @_; |
|
125
|
1
|
|
|
|
|
1
|
my (%searching, $seq,$state); |
|
126
|
1
|
|
|
|
|
3
|
my $source = $self->source_tag; |
|
127
|
1
|
|
|
|
|
2
|
$state = 0; |
|
128
|
1
|
|
|
|
|
4
|
while(defined($_ = $self->_readline)) { |
|
129
|
38
|
100
|
|
|
|
246
|
if( /^\s+$/ ) { |
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
130
|
6
|
|
|
|
|
14
|
next; |
|
131
|
|
|
|
|
|
|
} elsif( /^Palindromes\s+of\s*:\s+(\S+)/o ) { |
|
132
|
1
|
|
|
|
|
3
|
$state = 0; |
|
133
|
1
|
50
|
|
|
|
2
|
if( $seq ) { |
|
134
|
0
|
|
|
|
|
0
|
$self->_pushback($_); |
|
135
|
0
|
|
|
|
|
0
|
return $seq; |
|
136
|
|
|
|
|
|
|
} |
|
137
|
1
|
|
|
|
|
7
|
$seq = Bio::Seq->new(-display_id => $1); |
|
138
|
|
|
|
|
|
|
# now get ready to store for the next record |
|
139
|
1
|
|
|
|
|
4
|
$searching{'-seq_id'} = $1; |
|
140
|
|
|
|
|
|
|
} elsif( /^Sequence\s+length\s+is\s*:\s+(\d+)/o ) { |
|
141
|
1
|
|
|
|
|
4
|
$seq->length($1); |
|
142
|
1
|
|
|
|
|
4
|
$searching{'-tag'}->{'seqlength'} = $1; |
|
143
|
|
|
|
|
|
|
} elsif( /^(Start|End)\s+at\s+position\s*:\s+(\d+)/ ) { |
|
144
|
2
|
|
|
|
|
8
|
$searching{'-tag'}->{lc($1)} = $2; |
|
145
|
|
|
|
|
|
|
} elsif( m/^(Maximum|Minimum)\s+length\s+of\s+Palindromes\s+ |
|
146
|
|
|
|
|
|
|
is\s*:\s+(\d+)/ox) { |
|
147
|
2
|
|
|
|
|
8
|
$searching{'-tag'}->{lc($1).'_length'} = $2; |
|
148
|
|
|
|
|
|
|
} elsif( /^(Maximum\s+gap)\s+between\s+elements\s+is\s*:\s+(\d+)/o ) { |
|
149
|
1
|
|
|
|
|
7
|
$searching{'-tag'}->{lc($1)} = $2; |
|
150
|
|
|
|
|
|
|
} elsif( m/^Number\s+of\s+mismatches\s+allowed\s+ |
|
151
|
|
|
|
|
|
|
in\s+Palindrome\s*:\s+(\d+)/ox ) { |
|
152
|
1
|
|
|
|
|
6
|
$searching{'-tag'}->{'allowed_mismatches'} = $1; |
|
153
|
|
|
|
|
|
|
} elsif( /^Palindromes:/o ) { |
|
154
|
1
|
|
|
|
|
3
|
$state = 1; |
|
155
|
|
|
|
|
|
|
} elsif( $state == 1 ) { |
|
156
|
23
|
|
|
|
|
75
|
my $feature = Bio::SeqFeature::FeaturePair->new |
|
157
|
|
|
|
|
|
|
(-primary_tag => 'similarity', |
|
158
|
|
|
|
|
|
|
-source_tag => $source); |
|
159
|
23
|
|
|
|
|
51
|
for(my $i = 0; $i < 3; $i++ ) { |
|
160
|
69
|
100
|
|
|
|
115
|
if ($i != 1) { |
|
161
|
46
|
50
|
|
|
|
180
|
if( /^(\d+)\s+(\S+)\s+(\d+)/o ) { |
|
162
|
46
|
|
|
|
|
142
|
my ($start,$match,$end) = ($1,$2,$3); |
|
163
|
46
|
100
|
|
|
|
66
|
my $type = $i == 0 ? 'feature1' : 'feature2'; |
|
164
|
46
|
|
|
|
|
133
|
($start,$end) = sort { $a <=> $b } ($start,$end); |
|
|
46
|
|
|
|
|
141
|
|
|
165
|
46
|
100
|
|
|
|
210
|
$feature->$type( |
|
166
|
|
|
|
|
|
|
Bio::SeqFeature::Generic->new |
|
167
|
|
|
|
|
|
|
(%searching, |
|
168
|
|
|
|
|
|
|
-start => $start, |
|
169
|
|
|
|
|
|
|
-end => $end, |
|
170
|
|
|
|
|
|
|
-strand => $i == 0 ? 1 : -1, |
|
171
|
|
|
|
|
|
|
-primary_tag => 'similarity', |
|
172
|
|
|
|
|
|
|
-source_tag => $source) |
|
173
|
|
|
|
|
|
|
); |
|
174
|
|
|
|
|
|
|
} else { |
|
175
|
0
|
|
|
|
|
0
|
chomp; |
|
176
|
0
|
|
|
|
|
0
|
warn("Out of sync, line did not match:'$_'\n"); |
|
177
|
|
|
|
|
|
|
} |
|
178
|
|
|
|
|
|
|
|
|
179
|
|
|
|
|
|
|
} |
|
180
|
69
|
|
|
|
|
176
|
$_ = $self->_readline; |
|
181
|
|
|
|
|
|
|
} |
|
182
|
23
|
|
|
|
|
60
|
$seq->add_SeqFeature($feature); |
|
183
|
|
|
|
|
|
|
} |
|
184
|
|
|
|
|
|
|
} |
|
185
|
1
|
|
|
|
|
6
|
return $seq; |
|
186
|
|
|
|
|
|
|
} |
|
187
|
|
|
|
|
|
|
|
|
188
|
|
|
|
|
|
|
=head2 source_tag |
|
189
|
|
|
|
|
|
|
|
|
190
|
|
|
|
|
|
|
Title : source_tag |
|
191
|
|
|
|
|
|
|
Usage : $obj->source_tag($newval) |
|
192
|
|
|
|
|
|
|
Function: Get/Set Source Tag ('palindrome') by default |
|
193
|
|
|
|
|
|
|
Returns : value of source_tag (a scalar) |
|
194
|
|
|
|
|
|
|
Args : on set, new value (a scalar or undef, optional) |
|
195
|
|
|
|
|
|
|
|
|
196
|
|
|
|
|
|
|
|
|
197
|
|
|
|
|
|
|
=cut |
|
198
|
|
|
|
|
|
|
|
|
199
|
|
|
|
|
|
|
sub source_tag{ |
|
200
|
1
|
|
|
1
|
1
|
2
|
my $self = shift; |
|
201
|
|
|
|
|
|
|
|
|
202
|
1
|
50
|
|
|
|
2
|
return $self->{'source_tag'} = shift if @_; |
|
203
|
1
|
|
33
|
|
|
5
|
return $self->{'source_tag'} || $DEFAULT_SOURCETAG; |
|
204
|
|
|
|
|
|
|
} |
|
205
|
|
|
|
|
|
|
|
|
206
|
|
|
|
|
|
|
1; |