Bio/Tools/Seg.pm

   1 #
   2 # BioPerl module for Bio::Tools::Seg
   3 #
   4 # Copyright Balamurugan Kumarasamy
   5 # Totally re-written, added docs and tests -- Torsten Seemann, Sep 2006
   6 #
   7 # Copyright
   8 # You may distribute this module under the same terms as perl itself
   9 #
  10 # POD documentation - main docs before the code
  11
  12 =head1 NAME
  13
  14 Bio::Tools::Seg - parse C<seg> output
  15
  16 =head1 SYNOPSIS
  17
  18   use Bio::Tools::Seg;
  19   my $parser = Bio::Tools::Seg->(-file => 'seg.fasta');
  20   while ( my $f = $parser->next_result ) {
  21     if ($f->score < 1.5) {
  22       print $f->location->to_FTstring, " is low complexity\n";
  23     }
  24   }
  25
  26 =head1 DESCRIPTION
  27
  28 C<seg> identifies low-complexity regions on a protein sequence.
  29 It is usually part of the C<WU-BLAST> and C<InterProScan> packages.
  30
  31 The L<Bio::Tools::Seg> module will only parse the "fasta" output
  32 modes of C<seg>, i.e. C<seg -l> (low complexity regions only),
  33 C<seg -h> (high complexity regions only), or C<seg -a> (both low
  34 and high).
  35
  36 It creates a L<Bio::SeqFeature::Generic> for each FASTA-like entry
  37 found in the input file. It is up to the user to appropriately filter
  38 these using the feature's score.
  39
  40 =head1 FEEDBACK
  41
  42 =head2 Mailing Lists
  43
  44 User feedback is an integral part of the evolution of this and other
  45 Bioperl modules. Send your comments and suggestions preferably to
  46 the Bioperl mailing list.  Your participation is much appreciated.
  47
  48   bioperl-l@bioperl.org                  - General discussion
  49   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  50
  51 =head2 Support
  52
  53 Please direct usage questions or support issues to the mailing list:
  54
  55 I<bioperl-l@bioperl.org>
  56
  57 rather than to the module maintainer directly. Many experienced and
  58 reponsive experts will be able look at the problem and quickly
  59 address it. Please include a thorough description of the problem
  60 with code and data examples if at all possible.
  61
  62 =head2 Reporting Bugs
  63
  64 Report bugs to the Bioperl bug tracking system to help us keep track
  65 of the bugs and their resolution. Bug reports can be submitted via the
  66 web:
  67
  68   https://redmine.open-bio.org/projects/bioperl/
  69
  70 =head1 AUTHOR - Torsten Seemann
  71
  72 Email - torsten.seemann AT infotech.monash.edu.au
  73
  74 =head1 CONTRIBUTOR - Bala
  75
  76 Email - savikalpa@fugu-sg.org
  77
  78 =head1 APPENDIX
  79
  80 The rest of the documentation details each of the object methods.
  81 Internal methods are usually preceded with a _
  82
  83 =cut
  84
  85 package Bio::Tools::Seg;
  86 use strict;
  87
  88 use Bio::SeqFeature::Generic;
  89 use base qw(Bio::Root::Root Bio::Root::IO);
  90
  91 =head2 new
  92
  93  Title   : new
  94  Usage   : my $obj = Bio::Tools::Seg->new();
  95  Function: Builds a new Bio::Tools::Seg object
  96  Returns : Bio::Tools::Seg
  97  Args    : -fh/-file => $val, # for initing input, see Bio::Root::IO
  98
  99 =cut
 100
 101
 102 sub new {
 103         my($class,@args) = @_;
 104         my $self = $class->SUPER::new(@args);
 105         $self->_initialize_io(@args);
 106         return $self;
 107 }
 108
 109 =head2 next_result
 110
 111  Title   : next_result
 112  Usage   : my $feat = $seg->next_result
 113  Function: Get the next result set from parser data
 114  Returns : Bio::SeqFeature::Generic
 115  Args    : none
 116
 117 =cut
 118
 119 sub next_result {
 120         my ($self) = @_;
 121
 122         # For example in this line
 123         # test_prot(214-226) complexity=2.26 (12/2.20/2.50)
 124         # $1 is test_prot
 125         # $2 is 214
 126         # $3 is 226
 127         # $4 is 2.26
 128
 129         while (my $line = $self->_readline) {
 130                 if ($line =~ /^\>\s*?(\S+)?\s*?\((\d+)\-(\d+)\)\s*complexity=(\S+)/) {
 131                         return Bio::SeqFeature::Generic->new(
 132                                 -seq_id     => $1,
 133                                 -start      => $2,
 134                                 -end        => $3,
 135                                 -score      => $4,
 136                                 -source_tag => 'Seg',
 137                                 -primary    => 'low_complexity'
 138                         );
 139                 }
 140         }
 141 }
 142
 143
 144 1;