File Coverage

Bio/AlignIO/selex.pm
Criterion Covered Total %
statement 35 43 81.4
branch 10 16 62.5
condition 1 3 33.3
subroutine 4 4 100.0
pod 2 2 100.0
total 52 68 76.4


line stmt bran cond sub pod time code
1             #
2             # BioPerl module for Bio::AlignIO::selex
3              
4             # based on the Bio::SeqIO::selex module
5             # by Ewan Birney
6             # and Lincoln Stein
7             #
8             # and the SimpleAlign.pm module of Ewan Birney
9             #
10             # Copyright Peter Schattner
11             #
12             # You may distribute this module under the same terms as perl itself
13             # _history
14             # September 5, 2000
15             # POD documentation - main docs before the code
16              
17             =head1 NAME
18              
19             Bio::AlignIO::selex - selex sequence input/output stream
20              
21             =head1 SYNOPSIS
22              
23             # Do not use this module directly. Use it via the L class.
24              
25             use Bio::AlignIO;
26             use strict;
27              
28             my $in = Bio::AlignIO->new(-format => 'selex',
29             -file => 't/data/testaln.selex');
30             while( my $aln = $in->next_aln ) {
31              
32             }
33              
34             =head1 DESCRIPTION
35              
36             This object can transform L objects to and from selex flat
37             file databases.
38              
39             =head1 FEEDBACK
40              
41             =head2 Support
42              
43             Please direct usage questions or support issues to the mailing list:
44              
45             I
46              
47             rather than to the module maintainer directly. Many experienced and
48             reponsive experts will be able look at the problem and quickly
49             address it. Please include a thorough description of the problem
50             with code and data examples if at all possible.
51              
52             =head2 Reporting Bugs
53              
54             Report bugs to the Bioperl bug tracking system to help us keep track
55             the bugs and their resolution. Bug reports can be submitted via the
56             web:
57              
58             https://github.com/bioperl/bioperl-live/issues
59              
60             =head1 AUTHORS - Peter Schattner
61              
62             Email: schattner@alum.mit.edu
63              
64             =head1 CONTRIBUTORS
65              
66             Jason Stajich, jason-at-bioperl.org
67              
68             =head1 APPENDIX
69              
70             The rest of the documentation details each of the object
71             methods. Internal methods are usually preceded with a _
72              
73             =cut
74              
75             # Let the code begin...
76              
77             package Bio::AlignIO::selex;
78 3     3   443 use strict;
  3         4  
  3         80  
79              
80 3     3   9 use base qw(Bio::AlignIO);
  3         5  
  3         1165  
81              
82             =head2 next_aln
83              
84             Title : next_aln
85             Usage : $aln = $stream->next_aln()
86             Function: returns the next alignment in the stream. Tries to read *all* selex
87             It reads all non whitespace characters in the alignment
88             area. For selexs with weird gaps (eg ~~~) map them by using
89             $al->map_chars('~','-')
90             Returns : L object
91             Args : NONE
92              
93             =cut
94              
95             sub next_aln {
96 3     3 1 11 my $self = shift;
97 3         5 my $entry;
98 3         5 my ($start,$end,%align,$name,$seqname,%hash,@c2name, %accession,%desc);
99 3         22 my $aln = Bio::SimpleAlign->new(-source => 'selex');
100              
101             # in selex format, every non-blank line that does not start
102             # with '#=' is an alignment segment; the '#=' lines are mark up lines.
103             # Of particular interest are the '#=GF AC '
104             # lines, which give accession numbers for each segment
105 3         24 while( $entry = $self->_readline) {
106 375 50       1376 if( $entry =~ /^\#=GS\s+(\S+)\s+AC\s+(\S+)/ ) {
    50          
    100          
107 0         0 $accession{ $1 } = $2;
108 0         0 next;
109             } elsif( $entry =~ /^\#=GS\s+(\S+)\s+DE\s+(.+)\s*$/ ) {
110 0         0 $desc{$1} .= $2;
111             } elsif ( $entry =~ /^([^\#]\S+)\s+([A-Za-z\.\-\*]+)\s*/ ) {
112 156         214 my ($name,$seq) = ($1,$2);
113              
114 156 100       197 if( ! defined $align{$name} ) {
115 6         10 push @c2name, $name;
116             }
117 156         303 $align{$name} .= $seq;
118             }
119             }
120             # ok... now we can make the sequences
121              
122 3         8 foreach my $name ( @c2name ) {
123              
124 6 50       18 if( $name =~ /(\S+)\/(\d+)-(\d+)/ ) {
125 0         0 $seqname = $1;
126 0         0 $start = $2;
127 0         0 $end = $3;
128             } else {
129 6         8 $seqname=$name;
130 6         8 $start = 1;
131 6         8 $end = length($align{$name});
132             }
133             my $seq = Bio::LocatableSeq->new
134             ('-seq' => $align{$name},
135             '-display_id' => $seqname,
136             '-start' => $start,
137             '-end' => $end,
138             '-description' => $desc{$name},
139 6         26 '-accession_number' => $accession{$name},
140             '-alphabet' => $self->alphabet,
141             );
142              
143 6         22 $aln->add_seq($seq);
144             }
145              
146 3 50       10 return $aln if $aln->num_sequences;
147 0         0 return;
148             }
149              
150              
151             =head2 write_aln
152              
153             Title : write_aln
154             Usage : $stream->write_aln(@aln)
155             Function: writes the $aln object into the stream in selex format
156             Returns : 1 for success and 0 for error
157             Args : L object
158              
159              
160             =cut
161              
162             sub write_aln {
163 2     2 1 8 my ($self,@aln) = @_;
164 2         4 my ($namestr,$seq,$add);
165 0         0 my ($maxn);
166 2         5 foreach my $aln (@aln) {
167 2         9 $maxn = $aln->maxdisplayname_length();
168 2         6 foreach $seq ( $aln->each_seq() ) {
169 8         17 $namestr = $aln->displayname($seq->get_nse());
170 8         12 $add = $maxn - length($namestr) + 2;
171 8         13 $namestr .= " " x $add;
172 8 50       14 $self->_print (sprintf("%s %s\n",$namestr,$seq->seq())) or return;
173             }
174             }
175 2 50 33     7 $self->flush if $self->_flush_on_write && defined $self->_fh;
176 2         6 return 1;
177             }
178              
179             1;