[bug 3148] switch default to "expasy" until we can work out REST service interface
[bioperl-live.git] / Bio / DB / CUTG.pm
blobdbf1abe63f840843ea2ede0da355290c5e889c1e
2 # BioPerl module for Bio::DB::CUTG
4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
6 # Cared for by Richard Adams (richard.adams@ed.ac.uk)
8 # Copyright Richard Adams
10 # You may distribute this module under the same terms as perl itself
12 # POD documentation - main docs before the code
14 =head1 NAME
16 Bio::DB::CUTG - for access to the Codon usage Database
17 at http://www.kazusa.or.jp/codon.
19 =head1 SYNOPSIS
21 use Bio::CodonUsage::Table;
22 use Bio::DB::CUTG;
24 my $db = Bio::DB::CUTG->new(-sp =>'Pan troglodytes');
25 my $CUT = $db->get_request();
28 =head1 DESCRIPTION
30 This class retrieves and objectifies codon usage tables either from the
31 CUTG web database . The idea is that you can initially retrieve a CUT from
32 the web database, and write it to file in a way that can be read in
33 later, using the Bio::CodonUsage::IO module.
35 For a web query, two parameters need to be specified: species(sp) and
36 genetic code id (gc). The database is searched using regular
37 expressions, therefore the full latin name must be given to specify
38 the organism. If the species name is ambiguous the first CUT in the
39 list is retrieved. Defaults are Homo sapiens and 1(standard genetic
40 code). If you are retrieving CUTs from organisms using other genetic
41 codes this needs to be put in as a parameter. Parameters can be
42 entered in the constructor or in the get_web_request
43 ()method. Allowable parameters are listed in the $QUERY_KEYS hash
44 reference variable.
46 I intend at a later date to allow retrieval of multiple codon tables
47 e.g., from a wildcard search.
49 =head1 SEE ALSO
51 L<Bio::Tools::CodonTable>,
52 L<Bio::WebAgent>,
53 L<Bio::CodonUsage::Table>,
54 L<Bio::CodonUsage::IO>
56 =head1 FEEDBACK
58 =head2 Mailing Lists
61 User feedback is an integral part of the evolution of this and other
62 Bioperl modules. Send your comments and suggestions preferably to one
63 of the Bioperl mailing lists. Your participation is much appreciated.
65 bioperl-l@bioperl.org - General discussion
66 http://bioperl.org/wiki/Mailing_lists - About the mailing lists
68 =head2 Support
70 Please direct usage questions or support issues to the mailing list:
72 I<bioperl-l@bioperl.org>
74 rather than to the module maintainer directly. Many experienced and
75 reponsive experts will be able look at the problem and quickly
76 address it. Please include a thorough description of the problem
77 with code and data examples if at all possible.
79 =head2 Reporting Bugs
81 Report bugs to the Bioperl bug tracking system to help us keep track
82 the bugs and their resolution. Bug reports can be submitted via the web:
84 http://bugzilla.open-bio.org/
86 =head1 AUTHORS
88 Richard Adams, Richard.Adams@ed.ac.uk
90 =head1 APPENDIX
92 The rest of the documentation details each of the object
93 methods. Internal methods are usually preceded with a _
95 =cut
98 # Let the code begin...
102 package Bio::DB::CUTG;
103 use Bio::CodonUsage::IO;
104 use IO::String;
105 use URI::Escape;
106 use vars qw($URL $QUERY_KEYS);
108 use base qw(Bio::WebAgent);
110 $QUERY_KEYS = {
111 sp => 'full Latin species name',
112 gc => 'genetic code id'
115 BEGIN {
116 $URL = "http://www.kazusa.or.jp"
120 =head2 new
122 Title : new
123 Usage : my $db = Bio::DB::CUTG->new()
124 Returns : a reference to a new Bio::DB::CUTG
125 Args : hash of optional values for db query
127 =cut
129 sub new {
130 my ($class, @args ) =@_;
131 _check_args(@args);
132 my $self = $class->SUPER::new(@args);
133 return $self;
136 =head2 query_keys
138 Title : query_keys
139 Usage : $db->query_keys()
140 Purpose : To determine valid keys for parameters for db query.
141 Returns : a reference to a hash describing valid query keys
142 Args : none
144 =cut
146 sub query_keys {
147 return $QUERY_KEYS;
150 =head2 sp
152 Title : sp
153 Usage : my $sp = $db->sp();
154 Purpose: Get/set method for species name
155 Returns: void or species name string
156 Args : None or species name string
158 =cut
160 sub sp {
161 my $self = shift;
162 if (@_) {
163 my $name = shift;
164 $self->{'_sp'} = $name;
166 return $self->{'_sp'}|| "Homo sapiens";
170 =head2 gc
172 Title : gc
173 Usage : my $gc = $db->gc();
174 Purpose: Get/set method for genetic code id
175 Returns: void or genetic code integer
176 Args : None or genetic code integer
178 =cut
180 sub gc {
181 #### genetic code id for translations ####
182 my $self = shift;
183 if (@_) {
184 if($_[0] =~ /^\d+$/ && $_[0] >= 1 && $_[0] <=15 && $_[0] != 7
185 && $_[0] != 8) {
186 $self->{'_gc'} = shift;
188 else {
189 $self->warn("invalid genetic code index - setting to standard default (1)");
190 $self->{'_gc'} = 1;
193 return $self->{'_gc'} || 1; #return 1 if not defined
198 =head2 get_request
200 Title : get_request
201 Usage : my $cut = $db->get_request();
202 Purpose: To query remote CUT with a species name
203 Returns: a new codon usage table object
204 Args : species name(mandatory), genetic code id(optional)
206 =cut
208 sub get_request {
209 my ($self, @args) = @_;
210 _check_args(@args);
211 shift;
212 ### can put in parameters here as well
213 while( @_ ) {
214 my $key = shift;
215 $key =~ s/^-//;
216 $self->$key(shift);
218 $self->url($URL);
220 ###1st of all search DB to check species exists and is unique
221 my $nameparts = join "+", $self->sp =~ /(\S+)/g;
222 my $search_url = $self->url . "/codon/cgi-bin/spsearch.cgi?species="
223 . $nameparts . "&c=s";
224 my $rq = HTTP::Request->new(GET=>$search_url);
225 my $reply = $self->request($rq);
226 if ($reply->is_error) {
227 $self->throw($reply->as_string()."\nError getting for url $search_url!\n");
229 my $content = $reply->content;
230 return 0 unless $content;
231 $self->debug (" reply from query is \n $content");
232 ##### if no matches, assign defaults - or can throw here? ######
233 if ($content =~ /not found/i) {
234 $self->warn("organism not found -selecting human [9606] as default");
235 $self->sp("9606");
236 $self->_db("gbpri");
239 else {
240 my @names = $content =~ /species=([^"]+)/g;
241 ### get 1st species data from report ####
242 my @dbs = $content =~ /\[([^\]]+)\]:\s+\d+/g;
243 ## warn if more than 1 matching species ##
244 ## if multiple species retrieved, choose first one by default ##
245 $self->throw("No names returned for $nameparts") unless @names;
246 if (@names >1 ){
247 $self->warn ("too many species - not a unique species id\n".
248 "selecting $names[0] using database [$dbs[0]]");
250 ### now assign species and database value
251 $self->sp($names[0]);
252 $self->_db($dbs[0]);
256 ######## now get codon table , all defaults established now
258 ##construct URL##
259 $nameparts = $self->sp;
261 my $CT_url = $self->url . "/codon/cgi-bin/showcodon.cgi?species="
262 . $nameparts . "&aa=" . $self->gc . "&style=GCG";
263 $self->debug("URL : $CT_url\n");
264 ## retrieve data in html##
265 my $rq2 = HTTP::Request->new(GET => $CT_url);
266 $reply = $self->request($rq2);
267 if ($reply->is_error) {
268 $self->throw($reply->as_string()."\nError getting for url $CT_url!\n");
270 my $content2 = $reply->content;
272 ## strip html tags, basic but works here
273 $content2 =~ s/<[^>]+>//sg;
274 $content2 =~ s/Format.*//sg;
275 $self->debug ("raw DDB table is :\n $content2");
277 ### and pass to Bio::CodonUsage::IO for parsing
278 my $iostr = IO::String->new($content2);
279 my $io = Bio::CodonUsage::IO->new (-fh=>$iostr);
281 ##return object ##
282 return $io->next_data;
285 sub _check_args {
287 ###checks parameters for matching $QUERYKEYS
288 my @args = @_;
289 while (my $key = shift @args) {
290 $key = lc($key);
291 $key =~ s/\-//;
293 if (!exists ($QUERY_KEYS->{$key})) {
294 Bio::Root::Root->throw("invalid parameter - must be one of [" .
295 (join "] [", keys %$QUERY_KEYS) . "]");
297 shift @args;
301 #### internal URL parameter not specifiable ######
302 sub _db {
303 my $self = shift;
304 if (@_) {
305 $self->{'_db'} = shift;
307 return $self->{'_db'};