Bio/Restriction/IO.pm

   1 #
   2 # BioPerl module for Bio::Restriction::IO
   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 # POD documentation - main docs before the code
  13
  14 =head1 NAME
  15
  16 Bio::Restriction::IO - Handler for sequence variation IO Formats
  17
  18 =head1 SYNOPSIS
  19
  20     use Bio::Restriction::IO;
  21
  22     $in  = Bio::Restriction::IO->new(-file => "inputfilename" ,
  23                                      -format => 'withrefm');
  24     my $res = $in->read; # a Bio::Restriction::EnzymeCollection
  25
  26 =head1 DESCRIPTION
  27
  28 L<Bio::Restriction::IO> is a handler module for the formats in the
  29 Restriction IO set, e.g. C<Bio::Restriction::IO::xxx>. It is the
  30 officially sanctioned way of getting at the format objects, which most
  31 people should use.
  32
  33 The structure, conventions and most of the code is inherited from
  34 L<Bio::SeqIO>. The main difference is that instead of using methods
  35 C<next_seq>, you drop C<_seq> from the method name.
  36
  37 Also, instead of dealing only with individual L<Bio::Restriction::Enzyme>
  38 objects, C<read()> will slurp in all enzymes into a
  39 L<Bio::Restriction::EnzymeCollection> object.
  40
  41 For more details, see documentation in L<Bio::SeqIO>.
  42
  43 =head1 TO DO
  44
  45 At the moment, these can be use mainly to get a custom set if enzymes in
  46 C<withrefm> or C<itype2> formats into L<Bio::Restriction::Enzyme> or
  47 L<Bio::Restriction::EnzymeCollection> objects.  Using C<bairoch> format is
  48 highly experimental and is not recommmended at this time.
  49
  50 This class inherits from L<Bio::SeqIO> for convenience sake, though this should
  51 inherit from L<Bio::Root::Root>.  Get rid of L<Bio::SeqIO> inheritance by
  52 copying relevant methods in.
  53
  54 C<write()> methods are currently not implemented for any format except C<base>.
  55 Using C<write()> even with C<base> format is not recommended as it does not
  56 support multicut/multisite enzyme output.
  57
  58 Should additional formats be supported (such as XML)?
  59
  60 =head1 SEE ALSO
  61
  62 L<Bio::SeqIO>,
  63 L<Bio::Restriction::Enzyme>,
  64 L<Bio::Restriction::EnzymeCollection>
  65
  66 =head1 FEEDBACK
  67
  68 =head2 Mailing Lists
  69
  70 User feedback is an integral part of the evolution of this and other
  71 Bioperl modules. Send your comments and suggestions preferably to the
  72 Bioperl mailing lists Your participation is much appreciated.
  73
  74   bioperl-l@bioperl.org                  - General discussion
  75   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  76
  77 =head2 Support
  78
  79 Please direct usage questions or support issues to the mailing list:
  80
  81 I<bioperl-l@bioperl.org>
  82
  83 rather than to the module maintainer directly. Many experienced and
  84 reponsive experts will be able look at the problem and quickly
  85 address it. Please include a thorough description of the problem
  86 with code and data examples if at all possible.
  87
  88 =head2 Reporting Bugs
  89
  90 report bugs to the Bioperl bug tracking system to help us keep track
  91 the bugs and their resolution.  Bug reports can be submitted via the
  92 web:
  93
  94   https://redmine.open-bio.org/projects/bioperl/
  95
  96 =head1 AUTHOR
  97
  98 Rob Edwards, redwards@utmem.edu
  99
 100 =head1 CONTRIBUTORS
 101
 102 Heikki Lehvaslaiho, heikki-at-bioperl-dot-org
 103
 104 =head1 APPENDIX
 105
 106 The rest of the documentation details each of the object
 107 methods. Internal methods are usually preceded with a _
 108
 109 =cut
 110
 111 # Let the code begin...
 112
 113 package Bio::Restriction::IO;
 114
 115 use strict;
 116 use vars qw(%FORMAT);
 117 use base qw(Bio::SeqIO);
 118
 119 %FORMAT = (
 120             'itype2'    => 'itype2',
 121             '8'         => 'itype2',
 122             'withrefm'  => 'withrefm',
 123             '31'        => 'withrefm',
 124             'base'      => 'base',
 125             '0'         => 'base',
 126             'bairoch'   => 'bairoch',
 127             '19'        => 'bairoch',
 128             'macvector' => 'bairoch',
 129             'vectorNTI' => 'bairoch',
 130             'neo'       => 'prototype',
 131             'prototype' => 'prototype'
 132 );
 133
 134 =head2 new
 135
 136  Title   : new
 137  Usage   : $stream = Bio::Restriction::IO->new(-file => $filename,
 138                                                -format => 'Format')
 139  Function: Returns a new seqstream
 140  Returns : A Bio::Restriction::IO::Handler initialised with
 141            the appropriate format
 142  Args    : -file => $filename
 143            -format => format
 144            -fh => filehandle to attach to
 145
 146 =cut
 147
 148 sub new {
 149    my ($class, %param) = @_;
 150    my ($format);
 151
 152    @param{ map { lc $_ } keys %param } = values %param;  # lowercase keys
 153    $format = $FORMAT{$param{'-format'}} if defined $param{'-format'};
 154    $format ||= $class->_guess_format( $param{-file} || $ARGV[0] )
 155              || 'base';
 156    $format = "\L$format"; # normalize capitalization to lower case
 157
 158    return unless $class->_load_format_module($format);
 159    return "Bio::Restriction::IO::$format"->new(%param);
 160 }
 161
 162
 163 sub _load_format_module {
 164   my ($class, $format) = @_;
 165   my $module = "Bio::Restriction::IO::" . $format;
 166   my $ok;
 167   eval {
 168       $ok = $class->_load_module($module);
 169   };
 170   if ( $@ ) {
 171     print STDERR <<END;
 172 $class: $format cannot be found
 173 Exception $@
 174 For more information about the IO system please see the IO docs.
 175 This includes ways of checking for formats at compile time, not run time
 176 END
 177   ;
 178   }
 179   return $ok;
 180 }
 181
 182 =head2 read
 183
 184  Title   : read
 185  Usage   : $renzs = $stream->read
 186  Function: reads all the restrction enzymes from the stream
 187  Returns : a Bio::Restriction::EnzymeCollection object
 188  Args    :
 189
 190 =cut
 191
 192 sub read {
 193    my ($self, $seq) = @_;
 194    $self->throw_not_implemented();
 195 }
 196
 197 sub next {
 198    my ($self, $seq) = @_;
 199    $self->throw_not_implemented();
 200 }
 201
 202 sub next_seq {
 203    my ($self, $seq) = @_;
 204    $self->throw_not_implemented();
 205 }
 206
 207 =head2 write
 208
 209  Title   : write
 210  Usage   : $stream->write($seq)
 211  Function: writes the $seq object into the stream
 212  Returns : 1 for success and 0 for error
 213  Args    : Bio::Restriction::EnzymeCollection object
 214
 215 =cut
 216
 217 sub write {
 218     my ($self, $seq) = @_;
 219     $self->throw("Sorry, you cannot write to a generic ".
 220                  "Bio::Restricion::IO object.");
 221 }
 222
 223 sub write_seq {
 224    my ($self, $seq) = @_;
 225    $self->warn("These are not sequence objects. ".
 226                "Use method 'write' instead of 'write_seq'.");
 227    $self->write($seq);
 228 }
 229
 230 =head2 _guess_format
 231
 232  Title   : _guess_format
 233  Usage   : $obj->_guess_format($filename)
 234  Function:
 235  Example :
 236  Returns : guessed format of filename (lower case)
 237  Args    :
 238
 239 =cut
 240
 241 sub _guess_format {
 242    my $class = shift;
 243    return  unless $_ = shift;
 244    return 'flat' if /\.dat$/i;
 245    return 'xml'  if /\.xml$/i;
 246 }
 247
 248
 249 1;