branch-1-6/Bio/Restriction/IO/bairoch.pm

   1 # $Id$
   2 # BioPerl module for Bio::Restriction::IO::withrefm
   3 #
   4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
   5 #
   6 # Cared for by Rob Edwards <redwards@utmem.edu>
   7 #
   8 # Copyright Rob Edwards
   9 #
  10 # You may distribute this module under the same terms as perl itself
  11 #
  12
  13 # POD documentation - main docs before the code
  14
  15 =head1 NAME
  16
  17 Bio::Restriction::IO::bairoch - bairoch enzyme set
  18
  19 =head1 SYNOPSIS
  20
  21 Do not use this module directly.  Use it via the Bio::Restriction::IO class.
  22
  23 =head1 DESCRIPTION
  24
  25 This is the most complete format of the REBASE files, and basically
  26 includes all the data on each of the restriction enzymes.
  27
  28 This parser is for the Bairoch format (aka MacVector, Vector NTI, PC/Gene
  29 (Bairoch) format), REBASE format #19
  30
  31 =head1 FEEDBACK
  32
  33 =head2 Mailing Lists
  34
  35 User feedback is an integral part of the evolution of this and other
  36 Bioperl modules. Send your comments and suggestions preferably to the
  37 Bioperl mailing lists Your participation is much appreciated.
  38
  39   bioperl-l@bioperl.org                  - General discussion
  40   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  41
  42 =head2 Support
  43
  44 Please direct usage questions or support issues to the mailing list:
  45
  46 I<bioperl-l@bioperl.org>
  47
  48 rather than to the module maintainer directly. Many experienced and
  49 reponsive experts will be able look at the problem and quickly
  50 address it. Please include a thorough description of the problem
  51 with code and data examples if at all possible.
  52
  53 =head2 Reporting Bugs
  54
  55 Report bugs to the Bioperl bug tracking system to help us keep track
  56 the bugs and their resolution.  Bug reports can be submitted via the
  57 web:
  58
  59   http://bugzilla.open-bio.org/
  60
  61 =head1 AUTHOR
  62
  63 Rob Edwards, redwards@utmem.edu
  64
  65 =head1 CONTRIBUTORS
  66
  67 Heikki Lehvaslaiho, heikki-at-bioperl-dot-org
  68
  69 =head1 APPENDIX
  70
  71 The rest of the documentation details each of the object
  72 methods. Internal methods are usually preceded with a _
  73
  74 =cut
  75
  76 # Let the code begin...
  77
  78 package Bio::Restriction::IO::bairoch;
  79
  80 use vars qw(%WITH_REFM_FIELD);
  81 use strict;
  82
  83 use Bio::Restriction::Enzyme;
  84 use Bio::Restriction::Enzyme::MultiCut;
  85 use Bio::Restriction::Enzyme::MultiSite;
  86 use Bio::Restriction::EnzymeCollection;
  87
  88 use Data::Dumper;
  89
  90 use base qw(Bio::Restriction::IO::base);
  91
  92 =head2 read
  93
  94  Title   : read
  95  Usage   : $renzs = $stream->read
  96  Function: reads all the restrction enzymes from the stream
  97  Returns : a Bio::Restriction::Restriction object
  98  Args    : none
  99
 100 =cut
 101
 102 sub read {
 103     my $self = shift;
 104
 105     my $renzs = Bio::Restriction::EnzymeCollection->new(-empty => 1);
 106
 107     local $/ = '//';
 108     while (defined(my $entry=$self->_readline()) ) {
 109         $self->debug("|$entry|\n");
 110
 111         #
 112         # Minimal information
 113         #
 114         my ($name) = $entry =~ /ID\s+(\S+)/;
 115         my ($site) = $entry =~ /RS\s+([^\n]+)/;
 116         next unless ($name && $site);
 117
 118         # the standard sequence format for these guys is:
 119         # GATC, 2;
 120         # or, for enzymes that cut more than once
 121         # GATC, 2; GTAC, 2;
 122
 123         # there are a couple of sequences that have multiple
 124         # recognition sites.
 125
 126         my @sequences;
 127         if ($site =~ /\;/) {
 128             @sequences = split /\;/, $site;
 129             $self->debug(@sequences,"\n");
 130             $site=shift @sequences;
 131         }
 132
 133         my ($seq, $cut)=split /,\s+/, $site;
 134         $self->debug("SITE: |$site| GAVE: |$seq| and |$cut|\n");
 135         if ($seq eq '?') {
 136            $self->warn("$name: no site. Skipping") if $self->verbose > 1;
 137            next;
 138         }
 139
 140             # this is mainly an error check to make sure that I am adding what I think I am!
 141         if ($seq !~ /[NGATC]/i) {
 142           $self->throw("Sequence $name has weird sequence: |$seq|");
 143         }
 144         my $re;
 145         if ($cut eq "?") {
 146               $re = Bio::Restriction::Enzyme->new(-name=>$name, -seq => $seq);
 147         }
 148         else {
 149                if ($cut !~ /^-?\d+$/) {
 150              $self->throw("Cut site from $name is weird: |$cut|\n");
 151                }
 152
 153                $re = Bio::Restriction::Enzyme->new(-name=>$name,
 154                                                   -cut => $cut,
 155                                                   -seq => $seq
 156                                                   );
 157         }
 158         $renzs->enzymes($re);
 159
 160         #
 161         # prototype / isoschizomers
 162         #
 163         my ($prototype) = $entry =~ /PT\s+([^\n]+)/;
 164
 165         if ($prototype) {
 166             #$re->isoschizomers(split /\,/, $isoschizomers);
 167             #NOTE: Need to add a method so that we can add isoschosomers to enzymes that may not exist!
 168             $re->is_prototype(0);
 169         } else {
 170             $re->is_prototype(1);
 171         }
 172
 173         #
 174         # methylation
 175         #
 176
 177         my ($meth) = $entry =~ /MS\s+([^\n]+)/;
 178         my @meths;
 179         if ($meth) {
 180             # this can be either X(Y) or X(Y),X2(Y2)
 181             # where X is the base and y is the type of methylation
 182             if ( $meth =~ /(\S+)\((\d+)\),(\S+)\((\d+)\)/ ) { # two msites per site
 183                 #my ($p1, $m1, $p2, $m2) = ($1, $2, $3, $4);
 184                 $re->methylation_sites($self->_meth($re,$1, $2),
 185                                        $self->_meth($re,$3,$4));
 186             }
 187             elsif ($meth =~ /(\S+)\((\d+)\)/ ) { # one msite per site or more sites
 188                 #print Dumper $meth;
 189                 $re->methylation_sites( $self->_meth($re,$1,$2) );
 190                 @meths = split /, /, $meth;
 191                 $meth=shift @meths;
 192             } else {
 193                 $self->warn("Unknown methylation format [$meth]") if $self->verbose >0;
 194             }
 195         }
 196
 197         #
 198         # microbe
 199         #
 200         my ($microbe) = $entry =~ /OS\s+([^\n]+)/;
 201         $re->microbe($microbe) if $microbe;
 202
 203         #
 204         # source
 205         #
 206         #my ($source) = $entry =~ /<6>([^\n]+)/;
 207         #$re->source($source) if $source;
 208
 209         #
 210         # vendors
 211         #
 212         my ($vendors) = $entry =~ /CR\s+([^\n]+)/;
 213         $re->vendors(split /,\s*/, $vendors) if $vendors;
 214
 215         #
 216         # references
 217         #
 218         #my ($refs) = $entry =~ /<8>(.+)/s;
 219         #$re->references(map {split /\n+/} $refs) if $refs;
 220
 221         #
 222         # create special types of Enzymes
 223         #
 224         $self->warn("Current issues with multisite enzymes using bairoch format\n".
 225                     "Recommend using itype2 or withrefm formats for now") if @sequences;
 226         #$self->_make_multisites($renzs, $re, \@sequences, \@meths) if @sequences;
 227
 228     }
 229
 230     return $renzs;
 231 }
 232
 233
 234 =head2 write
 235
 236  Title   : write
 237  Usage   : $stream->write($renzs)
 238  Function: writes restriction enzymes into the stream
 239  Returns : 1 for success and 0 for error
 240  Args    : a Bio::Restriction::Enzyme
 241            or a Bio::Restriction::EnzymeCollection object
 242
 243 =cut
 244
 245 sub write {
 246     my ($self,@h) = @_;
 247     $self->throw_not_implemented;
 248 }
 249
 250 1;