From Code to Community: Sponsoring The Perl and Raku Conference 2025 Learn more

SENDU / bioperl-1.5.2_005-RC / Bio / DB / GFF / Aggregator / alignment.pm 

            

              
—
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
—
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
—
105
106
107
108
109
110
111
112
113
114
115
116
117
—
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138

              
=head1 NAME
Bio::DB::GFF::Aggregator::alignment -- Alignment aggregator
=head1 SYNOPSIS
  use Bio::DB::GFF;
  # Open the sequence database
  my $db      = Bio::DB::GFF->new( -adaptor => 'dbi:mysql',
                                   -dsn     => 'dbi:mysql:elegans42',
                                   -aggregator => ['alignment'],
                                 );
 -----------------------------
 Aggregator method: alignment
 Main method:       (none)
 Sub methods:       nucleotide_match,EST_match,cDNA_match,expressed_sequence_match,
                    translated_nucleotide_match,protein_match,HSP
 -----------------------------
=head1 DESCRIPTION
Bio::DB::GFF::Aggregator::alignment is one of the default aggregators,
and was written to be compatible with the C elegans GFF files.  It
aggregates raw "similarity" features into composite features of type
"alignment".  A better name for this class might be
"gapped_alignment."
This aggregator does not insist that there be a single top-level
feature that spans one end of the alignment to the other.  As a
result, it can produce truncated alignments if the entire alignment is
not contained within the segment of interest.
=cut
package Bio::DB::GFF::Aggregator::alignment;
use strict;
use base qw(Bio::DB::GFF::Aggregator);
=head2 aggregate
 Title   : aggregate
 Usage   : $features = $a->aggregate($features,$factory)
 Function: aggregate a feature list into composite features
 Returns : an array reference containing modified features
 Args    : see L<Bio::DB::GFF::Aggregator>
 Status  : Public
Because of the large number of similarity features, the aggregate()
method is overridden in order to perform some optimizations.
=cut
# we look for features of type Sequence and add them to a pseudotype transcript
sub aggregate {
  my $self = shift;
  my $features = shift;
  my $factory  = shift;
  my $matchsub = $self->match_sub($factory) or return;
  my $passthru = $self->passthru_sub($factory);
  my $method   = $self->get_method;
  my (%alignments,%targets,@result);
  warn "running alignment aggregator" if $factory->debug;
  for my $feature (@$features) {
    if ($matchsub->($feature)) {
      my $group  = $feature->{group};
      my $source = $feature->source;
      unless (exists $alignments{$group,$source}) {
        my $type = Bio::DB::GFF::Typename->new($method,$source);
         
        my $f = $feature->clone;
        # this is a violation of OO encapsulation, but need to do it this way
        # to achieve desired performance
        @{$f}{qw(type score phase)} = ($type,undef,undef);
        $alignments{$group,$source} = $f or next;
      }
      my $main = $alignments{$group,$source};
      $main->add_subfeature($feature);
      push @result,$feature if $passthru && $passthru->($feature);
    } else {
      push @result,$feature;
    }
  }
  warn "running aligner adjuster" if $factory->debug;
  for my $alignment (values %alignments) {
    $alignment->adjust_bounds;
    $alignment->compound(1);
    push @result,$alignment;
  }
  warn "aligner done" if $factory->debug;
  @$features = @result;
}
=head2 method
 Title   : method
 Usage   : $aggregator->method
 Function: return the method for the composite object
 Returns : the string "alignment"
 Args    : none
 Status  : Public
=cut
sub method { 'alignment' }
=head2 part_names
 Title   : part_names
 Usage   : $aggregator->part_names
 Function: return the methods for the sub-parts
 Returns : the full list of aggregated methods
 Args    : none
 Status  : Public
=cut
sub part_names {
  my $self = shift;
 return qw(nucleotide_match EST_match cDNA_match
           expressed_sequence_match
           translated_nucleotide_match
           protein_match HSP);
}
1;