Bio/SeqIO/Handler/GenericRichSeqHandler.pm

filter: Statementstmt 79.2% 332 / 419 Branchbran 59.4% 126 / 212 Conditioncond 60.6% 37 / 61 MC/DCmcdc 41.0% 16 / 39 Subroutinesub 95.8% 46 / 48 Podpod 91.6% 11 / 12 totaltotal 71.8% 568 / 791 CC 139 SCAR 41.0
CC
139
Cov
72%
_genbank_dbsource
393.0
_embl_id
36.7
_genbank_locus
33.1
CRAP 60.1
« Bio/Search/HSP/HSPI.pm ↑ Summary Bio/Seq/EncodedSeq.pm »
1 #
2 # BioPerl module for Bio::SeqIO::Handler::GenericRichSeqHandler
3 #
4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
5 #
6 # Cared for by Chris Fields
7 #
8 # Copyright Chris Fields
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::SeqIO::Handler::GenericRichSeqHandler - Bio::HandlerI-based
17 data handler for GenBank/EMBL/UniProt (and other) sequence data
18  
19 =head1 SYNOPSIS
20  
21 # MyHandler is a GenericRichSeqHandler object.
22 # inside a parser (driver) constructor....
23  
24 $self->seq_handler($handler || MyHandler->new(-format => 'genbank'));
25  
26 # in next_seq() in driver...
27  
28 $hobj = $self->seqhandler();
29  
30 # roll data up into hashref chunks, pass off into Handler for processing...
31  
32 $hobj->data_handler($data);
33  
34 # or retrieve Handler methods and pass data directly to Handler methods...
35  
36 my $hmeth = $hobj->handler_methods;
37  
38 if ($hmeth->{ $data->{NAME} }) {
39 my $mth = $hmeth->{ $data->{NAME} };
40 $hobj->$mth($data);
41 }
42  
43 =head1 DESCRIPTION
44  
45 This is an experimental implementation of a sequence-based HandlerBaseI parser
46 and may change over time. It is possible (nay, likely) that the way handler
47 methods are set up will change over development to allow more flexibility.
48 Release pumpkins, please do not add this to a release until the API has settled.
49 It is also likely that write_seq() will not work properly for some data.
50  
51 Standard Developer caveats:
52  
53 Do not use for production purposes.
54 Not responsible for destroying (your data|computer|world).
55 Do not stare directly at GenericRichSeqHandler.
56 If GenericRichSeqHandler glows, back slowly away and call for help.
57  
58 Consider yourself warned!
59  
60 This class acts as a demonstration on how to handle similar data chunks derived
61 from Bio::SeqIO::gbdriver, Bio::SeqIO::embldriver, and Bio::SeqIO::swissdriver
62 using similar (or the same) handler methods.
63  
64 The modules currently pass all previous tests in t/genbank.t, t/embl.t, and
65 t/swiss.t yet all use the same handler methods (the collected tests for handlers
66 can be found in t/Handler.t). Some tweaking of the methods themselves is
67 probably in order over the long run to ensure that data is consistently handled
68 for each parser. Round-trip tests are probably in order here...
69  
70 Though a Bio::Seq::SeqBuilder is employed for building sequence objects no
71 bypassing of data based on builder slots has been implemented (yet); this is
72 planned in the near future.
73  
74 As a reminder: this is the current Annotation data chunk (via Data::Dumper):
75  
76 $VAR1 = {
77 'NAME' => 'REFERENCE',
78 'DATA' => '1 (bases 1 to 10001)'
79 'AUTHORS' => 'International Human Genome Sequencing Consortium.'
80 'TITLE' => 'The DNA sequence of Homo sapiens'
81 'JOURNAL' => 'Unpublished (2003)'
82 };
83 ...
84  
85 This is the current SeqFeature data chunk (again via Data::Dumper):
86  
87 $VAR1 = {
88 'mol_type' => 'genomic DNA',
89 'LOCATION' => '<1..>10001',
90 'NAME' => 'FEATURES',
91 'FEATURE_KEY' => 'source',
92 'note' => 'Accession AL451081 sequenced by The Sanger Centre',
93 'db_xref' => 'taxon:9606',
94 'clone' => 'RP11-302I18',
95 'organism' => 'Homo sapiens'
96 };
97  
98 =head1 FEEDBACK
99  
100 =head2 Mailing Lists
101  
102 User feedback is an integral part of the evolution of this and other
103 Bioperl modules. Send your comments and suggestions preferably to one
104 of the Bioperl mailing lists. Your participation is much appreciated.
105  
106 bioperl-l@bioperl.org - General discussion
107 http://bioperl.org/wiki/Mailing_lists - About the mailing lists
108  
109 =head2 Support
110  
111 Please direct usage questions or support issues to the mailing list:
112  
113 I<bioperl-l@bioperl.org>
114  
115 rather than to the module maintainer directly. Many experienced and
116 reponsive experts will be able look at the problem and quickly
117 address it. Please include a thorough description of the problem
118 with code and data examples if at all possible.
119  
120 =head2 Reporting Bugs
121  
122 Report bugs to the Bioperl bug tracking system to help us keep track
123 the bugs and their resolution. Bug reports can be submitted via the
124 web:
125  
126 https://github.com/bioperl/bioperl-live/issues
127  
128 =head1 AUTHOR - Chris Fields
129  
130 Email cjfields at bioperl dot org
131  
132 =head1 APPENDIX
133  
134 The rest of the documentation details each of the object methods. Internal
135 methods are usually preceded with a _
136  
137 =cut
138  
139 # Let the code begin...
140  
141 package Bio::SeqIO::Handler::GenericRichSeqHandler;
142 5 $Bio::SeqIO::Handler::GenericRichSeqHandler::VERSION = '1.7.8';
143 5 ▶use strict;
Subroutine BEGIN: called CC=1 SCAR=0.0
144 5 ▶use warnings;
Subroutine BEGIN: called CC=1 SCAR=0.0
145  
146 5 ▶use Bio::SeqIO::FTHelper;
Subroutine BEGIN: called CC=1 SCAR=0.0
147 5 ▶use Bio::Annotation::Collection;
Subroutine BEGIN: called CC=1 SCAR=0.0
148 5 ▶use Bio::Annotation::DBLink;
Subroutine BEGIN: called CC=1 SCAR=0.0
149 5 ▶use Bio::Annotation::Comment;
Subroutine BEGIN: called CC=1 SCAR=0.0
150 5 ▶use Bio::Annotation::Reference;
Subroutine BEGIN: called CC=1 SCAR=0.0
151 5 ▶use Bio::Annotation::Collection;
Subroutine BEGIN: called CC=1 SCAR=0.0
152 5 ▶use Bio::Annotation::SimpleValue;
Subroutine BEGIN: called CC=1 SCAR=0.0
153 5 ▶use Bio::Annotation::TagTree;
Subroutine BEGIN: called CC=1 SCAR=0.0
154 5 ▶use Bio::SeqFeature::Generic;
Subroutine BEGIN: called CC=1 SCAR=0.0
155 5 ▶use Bio::Species;
Subroutine BEGIN: called CC=1 SCAR=0.0
156 5 ▶use Bio::Taxon;
Subroutine BEGIN: called CC=1 SCAR=0.0
157 5 ▶use Bio::DB::Taxonomy;
Subroutine BEGIN: called CC=1 SCAR=0.0
158 5 ▶use Bio::Factory::FTLocationFactory;
Subroutine BEGIN: called CC=1 SCAR=0.0
159 5 ▶use Data::Dumper;
Subroutine BEGIN: called CC=1 SCAR=0.0
160  
161 5 ▶use base qw(Bio::Root::Root Bio::HandlerBaseI);
Subroutine BEGIN: called CC=1 SCAR=0.0
162  
163 5 my %HANDLERS = (
164 'genbank' => {
165 'LOCUS' => \&_genbank_locus,
166 'DEFINITION' => \&_generic_description,
167 'ACCESSION' => \&_generic_accession,
168 'VERSION' => \&_generic_version,
169 'KEYWORDS' => \&_generic_keywords,
170 'DBSOURCE' => \&_genbank_dbsource,
171 'DBLINK' => \&_genbank_dbsource,
172 'SOURCE' => \&_generic_species,
173 'REFERENCE' => \&_generic_reference,
174 'COMMENT' => \&_generic_comment,
175 'FEATURES' => \&_generic_seqfeatures,
176 'BASE' => \&noop, # this is generated from scratch
177 'ORIGIN' => \&_generic_seq,
178 # handles anything else (WGS, WGS_SCAFLD, CONTIG, PROJECT)
179 '_DEFAULT_' => \&_generic_simplevalue,
180 },
181 'embl' => {
182 'ID' => \&_embl_id,
183 'DT' => \&_embl_date,
184 'DR' => \&_generic_dbsource,
185 'SV' => \&_generic_version,
186 'RN' => \&_generic_reference,
187 'KW' => \&_generic_keywords,
188 'DE' => \&_generic_description,
189 'AC' => \&_generic_accession,
190 #'AH' => \&noop, # TPA data not dealt with yet...
191 #'AS' => \&noop,
192 'SQ' => \&_generic_seq,
193 'OS' => \&_generic_species,
194 'CC' => \&_generic_comment,
195 'FT' => \&_generic_seqfeatures,
196 # handles anything else (WGS, TPA, ANN...)
197 '_DEFAULT_' => \&_generic_simplevalue,
198 },
199 'swiss' => {
200 'ID' => \&_swiss_id,
201 'DT' => \&_swiss_date,
202 'GN' => \&_swiss_genename,
203 'DR' => \&_generic_dbsource,
204 'RN' => \&_generic_reference,
205 'KW' => \&_generic_keywords,
206 'DE' => \&_generic_description,
207 'AC' => \&_generic_accession,
208 'SQ' => \&_generic_seq,
209 'OS' => \&_generic_species,
210 'CC' => \&_generic_comment,
211 'FT' => \&_generic_seqfeatures,
212 # handles anything else, though I don't know what...
213 '_DEFAULT_' => \&_generic_simplevalue,
214 },
215 );
216  
217 # can we do this generically? Seems like a lot of trouble...
218 5 my %DBSOURCE = map {$_ => 1} qw(
219 EchoBASE IntAct SWISS-2DPAGE ECO2DBASE ECOGENE TIGRFAMs
220 TIGR GO InterPro Pfam PROSITE SGD GermOnline
221 HSSP PhosSite Ensembl RGD AGD ArrayExpress KEGG
222 H-InvDB HGNC LinkHub PANTHER PRINTS SMART SMR
223 MGI MIM RZPD-ProtExp ProDom MEROPS TRANSFAC Reactome
224 UniGene GlycoSuiteDB PIRSF HSC-2DPAGE PHCI-2DPAGE
225 PMMA-2DPAGE Siena-2DPAGE Rat-heart-2DPAGE Aarhus/Ghent-2DPAGE
226 Biocyc MetaCyc Biocyc:Metacyc GenomeReviews FlyBase
227 TMHOBP COMPLUYEAST-2DPAGE OGP DictyBase HAMAP
228 PhotoList Gramene WormBase WormPep Genew ZFIN
229 PeroxiBase MaizeDB TAIR DrugBank REBASE HPA
230 swissprot GenBank GenPept REFSEQ embl PDB UniProtKB);
231  
232 5 my %NOPROCESS = map {$_ => 1} qw(DBSOURCE ORGANISM FEATURES);
233  
234 5 our %VALID_ALPHABET = (
235 'bp' => 'dna',
236 'aa' => 'protein',
237 'rc' => '' # rc = release candidate; file has no sequences
238 );
239  
240 =head2 new
241  
242 Title : new
243 Usage :
244 Function:
245 Returns :
246 Args : -format Sequence format to be mapped for handler methods
247 -builder Bio::Seq::SeqBuilder object (normally defined in
248 SequenceStreamI object implementation constructor)
249 Throws : On undefined '-format' sequence format parameter
250 Note : Still under heavy development
251  
252 =cut
253  
254 42 ▶sub new {
Subroutine new: called CC=3 SCAR=11.1
Pod documented
255 42 my ($class, @args) = @_;
256 42 my $self = $class->SUPER::new(@args);
257 42 $self = {@args};
258 42 bless $self,$class;
259 42 my ($format, $builder) = $self->_rearrange([qw(FORMAT BUILDER)], @args);
260 42 ▶ $self->throw("Must define sequence record format") if !$format;
Branch: 1 branch
BranchTrueFalseTotal
unless $format 0 42 42
261 42 $self->format($format);
262 42 $self->handler_methods();
263 42 ▶ $builder && $self->seqbuilder($builder);
Branch: 1 branch
BranchTrueFalseTotal
$builder and $self->seqbuilder($builder) 42 0 42
264 42 $self->location_factory();
265 42 return $self;
266 }
267  
268 =head1 L<Bio::HandlerBaseI> implementing methods
269  
270 =head2 handler_methods
271  
272 Title : handler_methods
273 Usage : $handler->handler_methods('GenBank')
274 %handlers = $handler->handler_methods();
275 Function: Retrieve the handler methods used for the current format() in
276 the handler. This assumes the handler methods are already
277 described in the HandlerI-implementing class.
278 Returns : a hash reference with the data type handled and the code ref
279 associated with it.
280 Args : [optional] String representing the sequence format. If set here
281 this will also set sequence_format()
282 Throws : On unimplemented sequence format in %HANDLERS
283  
284 =cut
285  
286 75 ▶sub handler_methods {
Subroutine handler_methods: called CC=3 SCAR=11.0
Pod documented
287 75 my $self = shift;
288 75 ▶ if (!($self->{'handlers'})) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($self->{"handlers"}) 42 33 75
289 $self->throw("No handlers defined for seqformat ",$self->format)
290 42 ▶ unless exists $HANDLERS{$self->format};
Branch: 1 branch
BranchTrueFalseTotal
unless exists $HANDLERS{$self->format} 0 42 42
291 42 $self->{'handlers'} = $HANDLERS{$self->format};
292 }
293 75 return ($self->{'handlers'});
294 }
295  
296 =head2 data_handler
297  
298 Title : data_handler
299 Usage : $handler->data_handler($data)
300 Function: Centralized method which accepts all data chunks, then distributes
301 to the appropriate methods for processing based on the chunk name
302 from within the HandlerBaseI object.
303  
304 One can also use
305 Returns : None
306 Args : an hash ref containing a data chunk.
307  
308 =cut
309  
310 1646 ▶sub data_handler {
Subroutine data_handler: called CC=5 SCAR=18.4
Pod documented
311 1646 my ($self, $data) = @_;
312 1646 ▶ my $nm = $data->{NAME} || $self->throw("No name tag defined!");
Condition33%1/3
$data->{'NAME'} || $self->throw('No name tag defined!')
l!l&&r!l&&!r
164600
MC/DC0%0/2
$data->{'NAME'} || $self->throw('No name tag defined!')
$data->{'NAME'} $self->throw('No name tag defined!')
Truth table33%1/3
A || B
A= $data->{'NAME'}B= $self->throw('No name tag defined!')
ABresult
1X1
011
000
313
314 # this should handle data on the fly w/o caching; any caching should be
315 # done in the driver!
316 my $method = (exists $self->{'handlers'}->{$nm}) ? ($self->{'handlers'}->{$nm}) :
317 1646 ▶ (exists $self->{'handlers'}->{'_DEFAULT_'}) ? ($self->{'handlers'}->{'_DEFAULT_'}) :
Branch: 2 branches
BranchTrueFalseTotal
exists $self->{'handlers'}{$nm} ? : 1630 16 1646
exists $self->{'handlers'}{'_DEFAULT_'} ? : 16 0 16
318 undef;
319 1646 ▶ if (!$method) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($method) 0 1646 1646
320 0 $self->debug("No handler defined for $nm\n");
321 0 return;
322 };
323 1646 $self->$method($data);
324 }
325  
326 =head2 reset_parameters
327  
328 Title : reset_parameters
329 Usage : $handler->reset_parameters()
330 Function: Resets the internal cache of data (normally object parameters for
331 a builder or factory)
332 Returns : None
333 Args : None
334  
335 =cut
336  
337 58 ▶sub reset_parameters {
Subroutine reset_parameters: called CC=1 SCAR=0.0
Pod documented
338 58 my $self = shift;
339 58 $self->{'_params'} = undef;
340 }
341  
342 =head2 format
343  
344 Title : format
345 Usage : $handler->format('GenBank')
346 Function: Get/Set the format for the report/record being parsed. This can be
347 used to set handlers in classes which are capable of processing
348 similar data chunks from multiple driver modules.
349 Returns : String with the sequence format
350 Args : [optional] String with the sequence format
351 Note : The format may be used to set the handlers (as in the
352 current GenericRichSeqHandler implementation)
353  
354 =cut
355  
356 1301 ▶sub format {
Subroutine format: called CC=2 SCAR=6.9
Pod documented
357 1301 my $self = shift;
358 1301 ▶ return $self->{'_seqformat'} = lc shift if @_;
Branch: 1 branch
BranchTrueFalseTotal
if @_ 42 1259 1301
359 1259 return $self->{'_seqformat'};
360 }
361  
362 =head2 get_params
363  
364 Title : get_params
365 Usage : $handler->get_params('-species')
366 Function: Convenience method used to retrieve the specified
367 parameters from the internal parameter cache
368 Returns : Hash ref containing parameters requested and data as
369 key-value pairs. Note that some parameter values may be
370 objects, arrays, etc.
371 Args : List (array) representing the parameters requested
372  
373 =cut
374  
375 818 ▶sub get_params {
Subroutine get_params: called CC=4 SCAR=13.9
Pod documented
376 818 my ($self, @ids) = @_;
377 818 my %data;
378 818 for my $id (@ids) {
379 818 ▶ if (!index($id, '-')==0) {
Branch: 1 branch
BranchTrueFalseTotal
if (!index($id, "-") == 0) 818 0 818
380 818 $id = '-'.$id ;
381 }
382 818 ▶ $data{$id} = $self->{'_params'}->{$id} if (exists $self->{'_params'}->{$id});
Branch: 1 branch
BranchTrueFalseTotal
if exists $self->{"_params"}{$id} 814 4 818
383 }
384 818 return \%data;
385 }
386  
387 =head2 set_params
388  
389 Title : set_params
390 Usage : $handler->set_param({'-species')
391 Function: Convenience method used to set specific parameters
392 Returns : None
393 Args : Hash ref containing the data to be passed as key-value pairs
394  
395 =cut
396  
397 0 ▶sub set_params {
Subroutine set_params: not called CC=1 SCAR=6.9
Pod documented
398 0 shift->throw('Not implemented yet!');
399 }
400  
401 =head1 Methods unique to this implementation
402  
403 =head2 seqbuilder
404  
405 Title : seqbuilder
406 Usage :
407 Function:
408 Returns :
409 Args :
410 Throws :
411 Note :
412  
413 =cut
414  
415 104 ▶sub seqbuilder {
Subroutine seqbuilder: called CC=2 SCAR=6.9
Pod documented
416 104 my $self = shift;
417 104 ▶ return $self->{'_seqbuilder'} = shift if @_;
Branch: 1 branch
BranchTrueFalseTotal
if @_ 42 62 104
418 62 return $self->{'_seqbuilder'};
419 }
420  
421 =head2 build_sequence
422  
423 Title : build_sequence
424 Usage :
425 Function:
426 Returns :
427 Args :
428 Throws :
429 Note :
430  
431 =cut
432  
433 62 ▶sub build_sequence {
Subroutine build_sequence: called CC=3 SCAR=11.0
Pod documented
434 62 my $self = shift;
435 62 my $builder = $self->seqbuilder();
436 62 my $seq;
437 62 ▶ if (defined($self->{'_params'})) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $self->{"_params"}) 58 4 62
438 58 $builder->add_slot_value(%{ $self->{'_params'} });
439 58 $seq = $builder->make_object();
440 58 $self->reset_parameters;
441 }
442 62 ▶ return $seq if $seq;
Branch: 1 branch
BranchTrueFalseTotal
if $seq 58 4 62
443 4 return 0;
444 }
445  
446 =head2 location_factory
447  
448 Title : location_factory
449 Usage :
450 Function:
451 Returns :
452 Args :
453 Throws :
454 Note :
455  
456 =cut
457  
458 42 ▶sub location_factory {
Subroutine location_factory: called CC=5 SCAR=23.4
Pod documented
459 42 my ($self, $factory) = @_;
460 42 ▶ if ($factory) {
Branch: 2 branches
BranchTrueFalseTotal
if ($factory) { } 0 42 42
elsif (not defined $self->{'_locfactory'}) { } 42 0 42
461 0 ▶ $self->throw("Must have a Bio::Factory::LocationFactoryI when ".
Branch: 1 branch
BranchTrueFalseTotal
unless ref $factory and $factory->isa("Bio::Factory::LocationFactoryI") 0 0 0
Condition0%0/3
ref $factory and $factory->isa("Bio::Factory::LocationFactoryI")
!ll&&!rl&&r
000
MC/DC0%0/2
ref $factory and $factory->isa("Bio::Factory::LocationFactoryI")
ref $factory $factory->isa("Bio::Factory::LocationFactoryI")
Truth table0%0/3
A and B
A= ref $factoryB= $factory->isa("Bio::Factory::LocationFactoryI")
ABresult
0X0
100
111
462 "explicitly setting factory()") unless
463 (ref($factory) && $factory->isa('Bio::Factory::LocationFactoryI'));
464 0 $self->{'_locfactory'} = $factory;
465 } elsif (!defined($self->{'_locfactory'})) {
466 42 $self->{'_locfactory'} = Bio::Factory::FTLocationFactory->new()
467 }
468 42 return $self->{'_locfactory'};
469 }
470  
471 =head2 annotation_collection
472  
473 Title : annotation_collection
474 Usage :
475 Function:
476 Returns :
477 Args :
478 Throws :
479 Note :
480  
481 =cut
482  
483 746 ▶sub annotation_collection {
Subroutine annotation_collection: called CC=5 SCAR=21.7
Pod documented
484 746 my ($self, $coll) = @_;
485 746 ▶ if ($coll) {
Branch: 2 branches
BranchTrueFalseTotal
if ($coll) { } 0 746 746
elsif (not exists $self->{'_params'}{'-annotation'}) { } 57 689 746
486 0 ▶ $self->throw("Must have Bio::AnnotationCollectionI ".
Branch: 1 branch
BranchTrueFalseTotal
unless ref $coll and $coll->isa("Bio::AnnotationCollectionI") 0 0 0
Condition0%0/3
ref $coll and $coll->isa("Bio::AnnotationCollectionI")
!ll&&!rl&&r
000
MC/DC0%0/2
ref $coll and $coll->isa("Bio::AnnotationCollectionI")
ref $coll $coll->isa("Bio::AnnotationCollectionI")
Truth table0%0/3
A and B
A= ref $collB= $coll->isa("Bio::AnnotationCollectionI")
ABresult
0X0
100
111
487 "when explicitly setting collection()")
488 unless (ref($coll) && $coll->isa('Bio::AnnotationCollectionI'));
489 0 $self->{'_params'}->{'-annotation'} = $coll;
490 } elsif (!exists($self->{'_params'}->{'-annotation'})) {
491 57 $self->{'_params'}->{'-annotation'} = Bio::Annotation::Collection->new()
492 }
493 746 return $self->{'_params'}->{'-annotation'};
494 }
495  
496 ####################### SEQUENCE HANDLERS #######################
497  
498 # any sequence data
499 53 ▶sub _generic_seq {
Subroutine _generic_seq: called CC=1 SCAR=0.0
500 53 my ($self, $data) = @_;
501 53 $self->{'_params'}->{'-seq'} = $data->{DATA};
502 }
503  
504 ####################### RAW DATA HANDLERS #######################
505  
506 # GenBank LOCUS line
507 31 ▶sub _genbank_locus {
Subroutine _genbank_locus: called CC=14 SCAR=35.0
508 31 my ($self, $data) = @_;
509 31 my (@tokens) = split m{\s+}, $data->{DATA};
510 31 my $display_id = shift @tokens;
511 31 $self->{'_params'}->{'-display_id'} = $display_id;
512 31 my $seqlength = shift @tokens;
513 31 ▶ if (exists $VALID_ALPHABET{$seqlength}) {
Branch: 1 branch
BranchTrueFalseTotal
if (exists $Bio::SeqIO::Handler::GenericRichSeqHandler::VALID_ALPHABET{$seqlength}) { } 0 31 31
514 # moved one token too far. No locus name?
515 $self->warn("Bad LOCUS name? Changing [".$self->{'_params'}->{'-display_id'}.
516 0 "] to 'unknown' and length to ".$self->{'_params'}->{'-display_id'});
517 0 $self->{'_params'}->{'-length'} = $self->{'_params'}->{'-display_id'};
518 0 $self->{'_params'}->{'-display_id'} = 'unknown';
519 # add token back...
520 0 unshift @tokens, $seqlength;
521 } else {
522 31 $self->{'_params'}->{'-length'} = $seqlength;
523 }
524 31 my $alphabet = lc(shift @tokens);
525 $self->{'_params'}->{'-alphabet'} =
526 31 ▶ (exists $VALID_ALPHABET{$alphabet}) ? $VALID_ALPHABET{$alphabet} :
Branch: 1 branch
BranchTrueFalseTotal
exists $Bio::SeqIO::Handler::GenericRichSeqHandler::VALID_ALPHABET{$alphabet} ? : 31 0 31
527 $self->warn("Unknown alphabet: $alphabet");
528 31 ▶ if (($self->{'_params'}->{'-alphabet'} eq 'dna') || (@tokens > 2)) {
Branch: 1 branch
BranchTrueFalseTotal
if ($self->{'_params'}{'-alphabet'} eq 'dna' or @tokens > 2) { } 31 0 31
Condition66%2/3
$self->{"_params"}{"-alphabet"} eq "dna" or @tokens > 2
l!l&&r!l&&!r
2920
MC/DC0%0/2
$self->{"_params"}{"-alphabet"} eq "dna" or @tokens > 2
$self->{"_params"}{"-alphabet"} eq "dna" @tokens > 2
Truth table66%2/3
A or B
A= $self->{"_params"}{"-alphabet"} eq "dna"B= @tokens > 2
ABresult
1X1
011
000
529 31 $self->{'_params'}->{'-molecule'} = shift(@tokens);
530 31 my $circ = shift(@tokens);
531 31 ▶ if ($circ eq 'circular') {
Branch: 1 branch
BranchTrueFalseTotal
if ($circ eq 'circular') { } 2 29 31
532 2 $self->{'_params'}->{'-is_circular'} = 1;
533 2 $self->{'_params'}->{'-division'} = shift(@tokens);
534 } else {
535 # 'linear' or 'circular' may actually be omitted altogether
536 29 ▶ $self->{'_params'}->{'-division'} =
Branch: 1 branch
BranchTrueFalseTotal
length $circ == 3 ? : 14 15 29
537 (CORE::length($circ) == 3 ) ? $circ : shift(@tokens);
538 }
539 } else {
540 0 ▶ $self->{'_params'}->{'-molecule'} = 'PRT' if($self->{'_params'}->{'-alphabet'} eq 'aa');
Branch: 1 branch
BranchTrueFalseTotal
if $self->{"_params"}{"-alphabet"} eq "aa" 0 0 0
541 0 $self->{'_params'}->{'-division'} = shift(@tokens);
542 }
543 31 my $date = join(' ', @tokens);
544 # maybe use Date::Time for dates?
545 31 ▶ if($date && $date =~ s{\s*((\d{1,2})-(\w{3})-(\d{2,4})).*}{$1}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($date and $date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/) 30 1 31
Condition66%2/3
$date and $date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/
!ll&&!rl&&r
1030
MC/DC50%1/2
$date and $date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/
$date $date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/
Truth table66%2/3
A and B
A= $dateB= $date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/
ABresult
0X0
100
111
546
547 30 ▶ if( length($date) < 11 ) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $date < 11) { } 0 30 30
548 # improperly formatted date
549 # But we'll be nice and fix it for them
550 0 my ($d,$m,$y) = ($2,$3,$4);
551 0 ▶ if( length($d) == 1 ) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $d == 1) 0 0 0
552 0 $d = "0$d";
553 }
554 # guess the century here
555 0 ▶ if( length($y) == 2 ) {
Branch: 1 branch
BranchTrueFalseTotal
if (length $y == 2) 0 0 0
556 0 ▶ if( $y > 60 ) { # arbitrarily guess that '60' means 1960
Branch: 1 branch
BranchTrueFalseTotal
if ($y > 60) { } 0 0 0
557 0 $y = "19$y";
558 } else {
559 0 $y = "20$y";
560 }
561 0 $self->warn("Date was malformed, guessing the century for $date to be $y\n");
562 }
563 0 $self->{'_params'}->{'-dates'} = [join('-',$d,$m,$y)];
564 } else {
565 30 $self->{'_params'}->{'-dates'} = [$date];
566 }
567 }
568 }
569  
570 # EMBL ID line
571 10 ▶sub _embl_id {
Subroutine _embl_id: called CC=21 SCAR=36.0
572 10 my ($self, $data) = @_;
573 10 my $alphabet;
574 10 my ($name, $sv, $topology, $mol, $div);
575 10 my $line = $data->{DATA};
576 #$self->debug("$line\n");
577 10 my ($idtype) = $line =~ tr/;/;/;
578 10 ▶ if ( $idtype == 6) { # New style headers contain exactly six semicolons.
Branch: 2 branches
BranchTrueFalseTotal
if ($idtype == 6) { } 1 9 10
elsif ($idtype) { } 8 1 9
579 # New style header (EMBL Release >= 87, after June 2006)
580 1 my $topology;
581 my $sv;
582
583 # ID DQ299383; SV 1; linear; mRNA; STD; MAM; 431 BP.
584 # This regexp comes from the new2old.pl conversion script, from EBI
585 1 ▶ if ($line =~ m/^(\w+);\s+SV (\d+); (\w+); ([^;]+); (\w{3}); (\w{3}); (\d+) \w{2}\./) {
Branch: 1 branch
BranchTrueFalseTotal
if ($line =~ /^(\w+);\s+SV (\d+); (\w+); ([^;]+); (\w{3}); (\w{3}); (\d+) \w{2}\./) { } 1 0 1
586 1 ($name, $sv, $topology, $mol, $div) = ($1, $2, $3, $4, $6);
587 } else {
588 0 $self->throw("Unrecognized EMBL ID line:[$line]");
589 }
590 1 ▶ if (defined($sv)) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $sv) 1 0 1
591 1 $self->{'_params'}->{'-seq_version'} = $sv;
592 1 $self->{'_params'}->{'-version'} = $sv;
593 }
594  
595 1 ▶ if ($topology eq "circular") {
Branch: 1 branch
BranchTrueFalseTotal
if ($topology eq "circular") 0 1 1
596 0 $self->{'_params'}->{'-is_circular'} = 1;
597 }
598
599 1 ▶ if (defined $mol ) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $mol) 1 0 1
600 1 ▶ if ($mol =~ /DNA/) {
Branch: 3 branches
BranchTrueFalseTotal
if ($mol =~ /DNA/) { } 0 1 1
elsif ($mol =~ /RNA/) { } 1 0 1
elsif ($mol =~ /AA/) { } 0 0 0
601 0 $alphabet='dna';
602 }
603 elsif ($mol =~ /RNA/) {
604 1 $alphabet='rna';
605 }
606 elsif ($mol =~ /AA/) {
607 0 $alphabet='protein';
608 }
609 }
610 } elsif ($idtype) { # has internal ';'
611 # Old style header (EMBL Release < 87, before June 2006)
612 8 ▶ if ($line =~ m{^(\S+)[^;]*;\s+(\S+)[^;]*;\s+(\S+)[^;]*;}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($line =~ /^(\S+)[^;]*;\s+(\S+)[^;]*;\s+(\S+)[^;]*;/) 8 0 8
613 8 ($name, $mol, $div) = ($1, $2, $3);
614 #$self->debug("[$name][$mol][$div]");
615 }
616  
617 8 ▶ if($mol) {
Branch: 1 branch
BranchTrueFalseTotal
if ($mol) 8 0 8
618 8 ▶ if ( $mol =~ m{circular} ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($mol =~ /circular/) 0 8 8
619 0 $self->{'_params'}->{'-is_circular'} = 1;
620 0 $mol =~ s{circular }{};
621 }
622 8 ▶ if (defined $mol ) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined $mol) 8 0 8
623 8 ▶ if ($mol =~ /DNA/) {
Branch: 3 branches
BranchTrueFalseTotal
if ($mol =~ /DNA/) { } 7 1 8
elsif ($mol =~ /RNA/) { } 1 0 1
elsif ($mol =~ /AA/) { } 0 0 0
624 7 $alphabet='dna';
625 }
626 elsif ($mol =~ /RNA/) {
627 1 $alphabet='rna';
628 }
629 elsif ($mol =~ /AA/) {
630 0 $alphabet='protein';
631 }
632 }
633 }
634 } else {
635 1 $name = $data->{DATA};
636 }
637 10 ▶ unless( defined $name && length($name) ) {
Branch: 1 branch
BranchTrueFalseTotal
unless (defined $name and length $name) 0 10 10
Condition33%1/3
defined $name and length $name
!ll&&!rl&&r
0010
MC/DC0%0/2
defined $name and length $name
defined $name length $name
Truth table33%1/3
A and B
A= defined $nameB= length $name
ABresult
0X0
100
111
638 0 $name = "unknown_id";
639 }
640 10 $self->{'_params'}->{'-display_id'} = $name;
641 10 $self->{'_params'}->{'-alphabet'} = $alphabet;
642 10 ▶ $self->{'_params'}->{'-division'} = $div if $div;
Branch: 1 branch
BranchTrueFalseTotal
if $div 9 1 10
643 10 ▶ $self->{'_params'}->{'-molecule'} = $mol if $mol;
Branch: 1 branch
BranchTrueFalseTotal
if $mol 9 1 10
644 }
645  
646 # UniProt/SwissProt ID line
647 17 ▶sub _swiss_id {
Subroutine _swiss_id: called CC=6 SCAR=18.3
648 17 my ($self, $data) = @_;
649 17 my ($name, $seq_div);
650 17 ▶ if($data->{DATA} =~ m{^
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{'DATA'} =~ /^ (\S+) \s+ # $1 entryname ([^\s;]+); \s+ # $2 DataClass (?:PRT;)? \s+ # Molecule Type (optional) [0-9]+[ ]AA \. # Sequencelength (capture?) $ /ox) { } 17 0 17
651 (\S+) \s+ # $1 entryname
652 ([^\s;]+); \s+ # $2 DataClass
653 (?:PRT;)? \s+ # Molecule Type (optional)
654 [0-9]+[ ]AA \. # Sequencelength (capture?)
655 $
656 }ox ) {
657 17 ($name, $seq_div) = ($1, $2);
658 17 ▶ $self->{'_params'}->{'-namespace'} =
Branch: 2 branches
BranchTrueFalseTotal
$seq_div eq 'Reviewed' || $seq_div eq 'STANDARD' ? : 13 4 17
$seq_div eq 'Unreviewed' || $seq_div eq 'PRELIMINARY' ? : 4 0 4
Condition83%5/6
$seq_div eq "Reviewed" or $seq_div eq "STANDARD"
l!l&&r!l&&!r
3104
$seq_div eq "Unreviewed" or $seq_div eq "PRELIMINARY"
l!l&&r!l&&!r
220
MC/DC100%2/2
$seq_div eq "Reviewed" or $seq_div eq "STANDARD"
$seq_div eq "Reviewed" $seq_div eq "STANDARD"
MC/DC0%0/2
$seq_div eq "Unreviewed" or $seq_div eq "PRELIMINARY"
$seq_div eq "Unreviewed" $seq_div eq "PRELIMINARY"
Truth table100%3/3
A or B
A= $seq_div eq "Reviewed"B= $seq_div eq "STANDARD"
ABresult
1X1
011
000
Truth table66%2/3
A or B
A= $seq_div eq "Unreviewed"B= $seq_div eq "PRELIMINARY"
ABresult
1X1
011
000
659 ($seq_div eq 'Reviewed' || $seq_div eq 'STANDARD') ? 'Swiss-Prot' :
660 ($seq_div eq 'Unreviewed' || $seq_div eq 'PRELIMINARY') ? 'TrEMBL' :
661 $seq_div;
662 # we shouldn't be setting the division, but for now...
663 17 my ($junk, $division) = split q(_), $name;
664 17 $self->{'_params'}->{'-division'} = $division;
665 17 $self->{'_params'}->{'-alphabet'} = 'protein';
666 # this is important to have the id for display in e.g. FTHelper, otherwise
667 # you won't know which entry caused an error
668 17 $self->{'_params'}->{'-display_id'} = $name;
669 } else {
670 0 $self->throw("Unrecognized UniProt/SwissProt ID line:[".$data->{DATA}."]");
671 }
672 }
673  
674 # UniProt/SwissProt GN line
675 17 ▶sub _swiss_genename {
Subroutine _swiss_genename: called CC=8 SCAR=20.8
676 17 my ($self, $data) = @_;
677 #$self->debug(Dumper($data));
678 17 my $genename = $data->{DATA};
679 17 my $gn;
680 17 ▶ if ($genename) {
Branch: 1 branch
BranchTrueFalseTotal
if ($genename) 17 0 17
681 17 my @stags;
682 17 ▶ if ($genename =~ /\w=\w/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($genename =~ /\w=\w/) { } 10 7 17
683 # new format (e.g., Name=RCHY1; Synonyms=ZNF363, CHIMP)
684 10 for my $n (split(m{\s+and\s+},$genename)) {
685 12 my @genenames;
686 12 for my $section (split(m{\s*;\s*},$n)) {
687 15 my ($tag, $rest) = split("=",$section);
688 15 ▶ $rest ||= '';
Condition50%1/2
$rest ||= ""
l!l
150
MC/DC0%0/1
$rest ||= ""
$rest
Truth table50%1/2
A
A= $rest
Aresult
11
00
689 15 for my $val (split(m{\s*,\s*},$rest)) {
690 19 push @genenames, [$tag => $val];
691 }
692 }
693 12 push @stags, ['gene_name' => \@genenames];
694 }
695 } else {
696 # old format
697 7 for my $section (split(/ AND /, $genename)) {
698 9 my @genenames;
699 9 $section =~ s/[\(\)\.]//g;
700 9 my @names = split(m{\s+OR\s+}, $section);
701 9 push @genenames, ['Name' => shift @names];
702 9 push @genenames, map {['Synonyms' => $_]} @names;
703 9 push @stags, ['gene_name' => \@genenames]
704 }
705 } #use Data::Dumper; print Dumper $gn, $genename;# exit;
706 17 my $gn = Bio::Annotation::TagTree->new(-tagname => 'gene_name',
707 -value => ['gene_names' => \@stags]);
708 17 $self->annotation_collection->add_Annotation('gene_name', $gn);
709 }
710 }
711  
712 # GenBank VERSION line
713 # old EMBL SV line (now obsolete)
714 # UniProt/SwissProt?
715 28 ▶sub _generic_version {
Subroutine _generic_version: called CC=4 SCAR=13.9
716 28 my ($self, $data) = @_;
717 28 my ($acc,$gi) = split(' ',$data->{DATA});
718 28 ▶ if($acc =~ m{^\w+\.(\d+)}xmso) {
Branch: 1 branch
BranchTrueFalseTotal
if ($acc =~ /^\w+\.(\d+)/mosx) 27 1 28
719 27 $self->{'_params'}->{'-version'} = $1;
720 27 $self->{'_params'}->{'-seq_version'} = $1;
721 }
722 28 ▶ if($gi && (index($gi,"GI:") == 0)) {
Branch: 1 branch
BranchTrueFalseTotal
if ($gi and index($gi, "GI:") == 0) 24 4 28
Condition66%2/3
$gi and index($gi, "GI:") == 0
!ll&&!rl&&r
4024
MC/DC50%1/2
$gi and index($gi, "GI:") == 0
$gi index($gi, "GI:") == 0
Truth table66%2/3
A and B
A= $giB= index($gi, "GI:") == 0
ABresult
0X0
100
111
723 24 $self->{'_params'}->{'-primary_id'} = substr($gi,3);
724 }
725 }
726  
727 # EMBL DT lines
728 5 ▶sub _embl_date {
Subroutine _embl_date: called CC=4 SCAR=16.5
729 5 my ($self, $data) = @_;
730 5 ▶ while ($data->{DATA} =~ m{(\S+)\s\((.*?)\)}g) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"DATA"} =~ /(\S+)\s\((.*?)\)/g) 10 5 15
731 10 my ($date, $version) = ($1, $2);
732 10 $date =~ tr{,}{}d; # remove comma if new version
733 10 ▶ if ($version =~ m{\(Rel\.\s(\d+),\sCreated\)}xmso ) {
Branch: 2 branches
BranchTrueFalseTotal
if ($version =~ /\(Rel\.\s(\d+),\sCreated\)/mosx) { } 0 10 10
elsif ($version =~ /\(Rel\.\s(\d+),\sLast\supdated,\sVersion\s(\d+)\)/mosx) { } 0 10 10
734 0 my $release = Bio::Annotation::SimpleValue->new(
735 -tagname => 'creation_release',
736 -value => $1
737 );
738 0 $self->annotation_collection->add_Annotation($release);
739 } elsif ($version =~ m{\(Rel\.\s(\d+),\sLast\supdated,\sVersion\s(\d+)\)}xmso ) {
740 0 my $release = Bio::Annotation::SimpleValue->new(
741 -tagname => 'update_release',
742 -value => $1
743 );
744 0 $self->annotation_collection->add_Annotation($release);
745 0 my $update = Bio::Annotation::SimpleValue->new(
746 -tagname => 'update_version',
747 -value => $2
748 );
749 0 $self->annotation_collection->add_Annotation($update);
750 }
751 10 push @{ $self->{'_params'}->{'-dates'} }, $date;
752 }
753 }
754  
755 # UniProt/SwissProt DT lines
756 17 ▶sub _swiss_date {
Subroutine _swiss_date: called CC=6 SCAR=17.9
757 17 my ($self, $data) = @_;
758 # swissprot
759 17 my @dls = split m{\n}, $data->{DATA};
760 17 for my $dl (@dls) {
761 51 my ($date, $version) = split(' ', $dl, 2);
762 51 $date =~ tr{,}{}d; # remove comma if new version
763 51 ▶ if ($version =~ m{\(Rel\. (\d+), Last sequence update\)} || # old
Branch: 2 branches
BranchTrueFalseTotal
if ($version =~ /\(Rel\. (\d+), Last sequence update\)/ or $version =~ /sequence version (\d+)\./) { } 17 34 51
elsif ($version =~ /\(Rel\. (\d+), Last annotation update\)/ or $version =~ /entry version (\d+)\./) { } 17 17 34
Condition100%3/3
$version =~ /\(Rel\. (\d+), Last sequence update\)/ or $version =~ /sequence version (\d+)\./
l!l&&r!l&&!r
8934
MC/DC100%2/2
$version =~ /\(Rel\. (\d+), Last sequence update\)/ or $version =~ /sequence version (\d+)\./
$version =~ /\(Rel\. (\d+), Last sequence update\)/ $version =~ /sequence version (\d+)\./
Truth table100%3/3
A or B
A= $version =~ /\(Rel\. (\d+), Last sequence update\)/B= $version =~ /sequence version (\d+)\./
ABresult
1X1
011
000
764 $version =~ m{sequence version (\d+)\.}) { #new
765 17 my $update = Bio::Annotation::SimpleValue->new(
766 -tagname => 'seq_update',
767 -value => $1
768 );
769 17 $self->annotation_collection->add_Annotation($update);
770 ▶ } elsif ($version =~ m{\(Rel\. (\d+), Last annotation update\)} || #old
Condition100%3/3
$version =~ /\(Rel\. (\d+), Last annotation update\)/ or $version =~ /entry version (\d+)\./
l!l&&r!l&&!r
8917
MC/DC100%2/2
$version =~ /\(Rel\. (\d+), Last annotation update\)/ or $version =~ /entry version (\d+)\./
$version =~ /\(Rel\. (\d+), Last annotation update\)/ $version =~ /entry version (\d+)\./
Truth table100%3/3
A or B
A= $version =~ /\(Rel\. (\d+), Last annotation update\)/B= $version =~ /entry version (\d+)\./
ABresult
1X1
011
000
771 $version =~ m{entry version (\d+)\.}) { #new
772 17 $self->{'_params'}->{'-version'} = $1;
773 17 $self->{'_params'}->{'-seq_version'} = $1;
774 }
775 51 push @{ $self->{'_params'}->{'-dates'} }, $date;
776 }
777 }
778  
779 # GenBank KEYWORDS line
780 # EMBL KW line
781 # UniProt/SwissProt KW line
782 55 ▶sub _generic_keywords {
Subroutine _generic_keywords: called CC=1 SCAR=0.0
783 55 my ($self, $data) = @_;
784 55 $data->{DATA} =~ s{\.$}{};
785 55 my @kw = split m{\s*\;\s*}xo ,$data->{DATA};
786 55 $self->{'_params'}->{'-keywords'} = \@kw;
787 }
788  
789 # GenBank DEFINITION line
790 # EMBL DE line
791 # UniProt/SwissProt DE line
792 57 ▶sub _generic_description {
Subroutine _generic_description: called CC=1 SCAR=0.0
793 57 my ($self, $data) = @_;
794 57 $self->{'_params'}->{'-desc'} = $data->{DATA};
795 }
796  
797 # GenBank ACCESSION line
798 # EMBL AC line
799 # UniProt/SwissProt AC line
800 56 ▶sub _generic_accession {
Subroutine _generic_accession: called CC=2 SCAR=6.9
801 56 my ($self, $data) = @_;
802 56 my @accs = split m{[\s;]+}, $data->{DATA};
803 56 $self->{'_params'}->{'-accession_number'} = shift @accs;
804 56 ▶ $self->{'_params'}->{'-secondary_accessions'} = \@accs if @accs;
Branch: 1 branch
BranchTrueFalseTotal
if @accs 9 47 56
805 }
806  
807 ####################### SPECIES HANDLERS #######################
808  
809 # uses Bio::Species
810 # GenBank SOURCE, ORGANISM lines
811 # EMBL O* lines
812 # UniProt/SwissProt O* lines
813 56 ▶sub _generic_species {
Subroutine _generic_species: called CC=18 SCAR=29.2
814 56 my ($self, $data) = @_;
815
816 56 my $seqformat = $self->format;
817 # if data is coming in from GenBank parser...
818 56 ▶ if ($seqformat eq 'genbank' &&
Branch: 1 branch
BranchTrueFalseTotal
if ($seqformat eq "genbank" and $data->{"ORGANISM"} =~ /(.+?)\s(\S+;[^\n\.]+)/ox) 30 26 56
Condition66%2/3
$seqformat eq "genbank" and $data->{"ORGANISM"} =~ /(.+?)\s(\S+;[^\n\.]+)/ox
!ll&&!rl&&r
26030
MC/DC50%1/2
$seqformat eq "genbank" and $data->{"ORGANISM"} =~ /(.+?)\s(\S+;[^\n\.]+)/ox
$seqformat eq "genbank" $data->{"ORGANISM"} =~ /(.+?)\s(\S+;[^\n\.]+)/ox
Truth table66%2/3
A and B
A= $seqformat eq "genbank"B= $data->{"ORGANISM"} =~ /(.+?)\s(\S+;[^\n\.]+)/ox
ABresult
0X0
100
111
819 $data->{ORGANISM} =~ m{(.+?)\s(\S+;[^\n\.]+)}ox) {
820 30 ($data->{ORGANISM}, $data->{CLASSIFICATION}) = ($1, $2);
821 }
822
823 # SwissProt stuff...
824 # hybrid names in swissprot files are no longer valid per intergration into
825 # UniProt. Files containing these have been split into separate entries, so
826 # it is probably a good idea to update if one has these lingering around...
827  
828 56 my $taxid;
829 56 ▶ if ($seqformat eq 'swiss') {
Branch: 1 branch
BranchTrueFalseTotal
if ($seqformat eq "swiss") 17 39 56
830 17 ▶ if ($data->{DATA} =~ m{^([^,]+)}ox) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"DATA"} =~ /^([^,]+)/ox) 17 0 17
831 17 $data->{DATA} = $1;
832 }
833 17 ▶ if ($data->{CROSSREF} && $data->{CROSSREF} =~ m{NCBI_TaxID=(\d+)}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"CROSSREF"} and $data->{"CROSSREF"} =~ /NCBI_TaxID=(\d+)/) 16 1 17
Condition66%2/3
$data->{"CROSSREF"} and $data->{"CROSSREF"} =~ /NCBI_TaxID=(\d+)/
!ll&&!rl&&r
1016
MC/DC50%1/2
$data->{"CROSSREF"} and $data->{"CROSSREF"} =~ /NCBI_TaxID=(\d+)/
$data->{"CROSSREF"} $data->{"CROSSREF"} =~ /NCBI_TaxID=(\d+)/
Truth table66%2/3
A and B
A= $data->{"CROSSREF"}B= $data->{"CROSSREF"} =~ /NCBI_TaxID=(\d+)/
ABresult
0X0
100
111
834 16 $taxid = $1;
835 }
836 }
837
838 my ($sl, $class, $sci_name) = ($data->{DATA},
839 $data->{CLASSIFICATION},
840 56 ▶ $data->{ORGANISM} || '');
Condition100%2/2
$data->{'ORGANISM'} || ''
l!l
3026
MC/DC100%1/1
$data->{'ORGANISM'} || ''
$data->{'ORGANISM'}
Truth table100%2/2
A
A= $data->{'ORGANISM'}
Aresult
11
00
841 56 my ($organelle,$abbr_name, $common);
842 56 my @class = reverse split m{\s*;\s*}, $class;
843 # have to treat swiss different from everything else...
844 56 ▶ if ($sl =~ m{^(mitochondrion|chloroplast|plastid)? # GenBank format
Branch: 1 branch
BranchTrueFalseTotal
if ($sl =~ /^(mitochondrion|chloroplast|plastid)? # GenBank format \s*(.*?) \s*(?: \( (.*?) \) )?\.?$ /mosx) { } 56 0 56
845 \s*(.*?)
846 \s*(?: \( (.*?) \) )?\.?$
847 }xmso ){
848 56 ($organelle, $abbr_name, $common) = ($1, $2, $3); # optional
849 } else {
850 0 $abbr_name = $sl; # nothing caught; this is a backup!
851 }
852 # there is no 'abbreviated name' for EMBL
853 56 ▶ $sci_name = $abbr_name if $seqformat ne 'genbank';
Branch: 1 branch
BranchTrueFalseTotal
if $seqformat ne "genbank" 26 30 56
854 56 ▶ $organelle ||= '';
Condition100%2/2
$organelle ||= ""
l!l
254
MC/DC100%1/1
$organelle ||= ""
$organelle
Truth table100%2/2
A
A= $organelle
Aresult
11
00
855 56 ▶ $common ||= '';
Condition100%2/2
$common ||= ""
l!l
1640
MC/DC100%1/1
$common ||= ""
$common
Truth table100%2/2
A
A= $common
Aresult
11
00
856 56 ▶ $sci_name || return;
Branch: 1 branch
BranchTrueFalseTotal
$sci_name or return 56 0 56
857 56 unshift @class, $sci_name;
858 # no genus/species parsing here; moving to Bio::Taxon-based taxonomy
859 56 my $make = Bio::Species->new();
860 56 $make->scientific_name($sci_name);
861 56 ▶ $make->classification(@class) if @class > 0;
Branch: 1 branch
BranchTrueFalseTotal
if @class > 0 56 0 56
862 56 ▶ $common && $make->common_name( $common );
Branch: 1 branch
BranchTrueFalseTotal
$common and $make->common_name($common) 16 40 56
863 56 ▶ $abbr_name && $make->name('abbreviated', $abbr_name);
Branch: 1 branch
BranchTrueFalseTotal
$abbr_name and $make->name("abbreviated", $abbr_name) 56 0 56
864 56 ▶ $organelle && $make->organelle($organelle);
Branch: 1 branch
BranchTrueFalseTotal
$organelle and $make->organelle($organelle) 2 54 56
865 56 ▶ $taxid && $make->ncbi_taxid($taxid);
Branch: 1 branch
BranchTrueFalseTotal
$taxid and $make->ncbi_taxid($taxid) 16 40 56
866 56 $self->{'_params'}->{'-species'} = $make;
867 }
868  
869 ####################### ANNOTATION HANDLERS #######################
870  
871 # GenBank DBSOURCE line
872 1 ▶sub _genbank_dbsource {
Subroutine _genbank_dbsource: called CC=23 SCAR=59.7
873 1 my ($self, $data) = @_;
874 1 my $dbsource = $data->{DATA};
875 1 my $annotation = $self->annotation_collection;
876 # deal with swissprot dbsources
877 # we could possibly parcel these out to subhandlers...
878 1 ▶ if( $dbsource =~ s/(UniProt(?:KB)|swissprot):\s+locus\s+(\S+)\,.+\n// ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($dbsource =~ s/(UniProt(?:KB)|swissprot):\s+locus\s+(\S+)\,.+\n//) { } 0 1 1
879 0 $annotation->add_Annotation
880 ('dblink',
881 Bio::Annotation::DBLink->new
882 (-primary_id => $2,
883 -database => $1,
884 -tagname => 'dblink'));
885 0 ▶ if( $dbsource =~ s/\s*created:\s+([^\.]+)\.\n// ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($dbsource =~ s/\s*created:\s+([^\.]+)\.\n//) 0 0 0
886 0 $annotation->add_Annotation
887 ('swissprot_dates',
888 Bio::Annotation::SimpleValue->new
889 (-tagname => 'date_created',
890 -value => $1));
891 }
892 0 ▶ while( $dbsource =~ s/\s*(sequence|annotation)\s+updated:\s+([^\.]+)\.\n//g ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($dbsource =~ s/\s*(sequence|annotation)\s+updated:\s+([^\.]+)\.\n//g) 0 0 0
893 0 $annotation->add_Annotation
894 ('swissprot_dates',
895 Bio::Annotation::SimpleValue->new
896 (-tagname => 'date_updated',
897 -value => $1));
898 }
899 0 $dbsource =~ s/\n/ /g;
900 0 ▶ if( $dbsource =~ s/\s*xrefs:\s+((?:\S+,\s+)+\S+)\s+xrefs/xrefs/ ) {
Branch: 2 branches
BranchTrueFalseTotal
if ($dbsource =~ s/\s*xrefs:\s+((?:\S+,\s+)+\S+)\s+xrefs/xrefs/) { } 0 0 0
elsif ($dbsource =~ s/\s*xrefs:\s+(.+)\s+xrefs/xrefs/i) { } 0 0 0
901 # will use $i to determine even or odd
902 # for swissprot the accessions are paired
903 0 my $i = 0;
904 0 for my $dbsrc ( split(/,\s+/,$1) ) {
905 0 ▶ if( $dbsrc =~ /(\S+)\.(\d+)/ || $dbsrc =~ /(\S+)/ ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($dbsrc =~ /(\S+)\.(\d+)/ or $dbsrc =~ /(\S+)/) 0 0 0
Condition0%0/3
$dbsrc =~ /(\S+)\.(\d+)/ or $dbsrc =~ /(\S+)/
l!l&&r!l&&!r
000
MC/DC0%0/2
$dbsrc =~ /(\S+)\.(\d+)/ or $dbsrc =~ /(\S+)/
$dbsrc =~ /(\S+)\.(\d+)/ $dbsrc =~ /(\S+)/
Truth table0%0/3
A or B
A= $dbsrc =~ /(\S+)\.(\d+)/B= $dbsrc =~ /(\S+)/
ABresult
1X1
011
000
906 0 my ($id,$version) = ($1,$2);
907 0 ▶ $version ='' unless defined $version;
Branch: 1 branch
BranchTrueFalseTotal
unless defined $version 0 0 0
908 0 my $db;
909 0 ▶ if( $id =~ /^\d\S{3}/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($id =~ /^\d\S{3}/) { } 0 0 0
910 0 $db = 'PDB';
911 } else {
912 0 ▶ $db = ($i++ % 2 ) ? 'GenPept' : 'GenBank';
Branch: 1 branch
BranchTrueFalseTotal
$i++ % 2 ? : 0 0 0
913 }
914 0 $annotation->add_Annotation
915 ('dblink',
916 Bio::Annotation::DBLink->new
917 (-primary_id => $id,
918 -version => $version,
919 -database => $db,
920 -tagname => 'dblink'));
921 }
922 }
923 } elsif( $dbsource =~ s/\s*xrefs:\s+(.+)\s+xrefs/xrefs/i ) {
924 # download screwed up and ncbi didn't put acc in for gi numbers
925 0 my $i = 0;
926 0 for my $id ( split(/\,\s+/,$1) ) {
927 0 my ($acc,$db);
928 0 ▶ if( $id =~ /gi:\s+(\d+)/ ) {
Branch: 2 branches
BranchTrueFalseTotal
if ($id =~ /gi:\s+(\d+)/) { } 0 0 0
elsif ($id =~ /pdb\s+accession\s+(\S+)/) { } 0 0 0
929 0 $acc= $1;
930 0 ▶ $db = ($i++ % 2 ) ? 'GenPept' : 'GenBank';
Branch: 1 branch
BranchTrueFalseTotal
$i++ % 2 ? : 0 0 0
931 } elsif( $id =~ /pdb\s+accession\s+(\S+)/ ) {
932 0 $acc= $1;
933 0 $db = 'PDB';
934 } else {
935 0 $acc= $id;
936 0 $db = '';
937 }
938 0 $annotation->add_Annotation
939 ('dblink',
940 Bio::Annotation::DBLink->new
941 (-primary_id => $acc,
942 -database => $db,
943 -tagname => 'dblink'));
944 }
945 } else {
946 0 $self->warn("Cannot match $dbsource\n");
947 }
948 0 ▶ if( $dbsource =~ s/xrefs\s+\(non\-sequence\s+databases\):\s+
Branch: 1 branch
BranchTrueFalseTotal
if ($dbsource =~ s/xrefs\s+\(non\-sequence\s+databases\):\s+ ((?:\S+,\s+)+\S+)//x) 0 0 0
949 ((?:\S+,\s+)+\S+)//x ) {
950 0 for my $id ( split(/\,\s+/,$1) ) {
951 0 my $db;
952 # this is because GenBank dropped the spaces!!!
953 # I'm sure we're not going to get this right
954 ##if( $id =~ s/^://i ) {
955 ## $db = $1;
956 ##}
957 0 $db = substr($id,0,index($id,':'));
958 0 ▶ if (! exists $DBSOURCE{ $db }) {
Branch: 1 branch
BranchTrueFalseTotal
unless (exists $DBSOURCE{$db}) 0 0 0
959 0 $db = ''; # do we want 'GenBank' here?
960 }
961 0 $id = substr($id,index($id,':')+1);
962 0 $annotation->add_Annotation
963 ('dblink',Bio::Annotation::DBLink->new
964 (-primary_id => $id,
965 -database => $db,
966 -tagname => 'dblink'));
967 }
968 }
969 } else {
970 1 ▶ if( $dbsource =~ /^(\S*?):?\s*accession\s+(\S+)\.(\d+)/ ) {
Branch: 2 branches
BranchTrueFalseTotal
if ($dbsource =~ /^(\S*?):?\s*accession\s+(\S+)\.(\d+)/) { } 1 0 1
elsif ($dbsource =~ /(\S+)([\.:])(\d+)/) { } 0 0 0
971 1 my ($db,$id,$version) = ($1,$2,$3);
972 1 ▶ $annotation->add_Annotation
Condition50%1/2
$db || 'GenBank'
l!l
01
MC/DC0%0/1
$db || 'GenBank'
$db
Truth table50%1/2
A
A= $db
Aresult
11
00
973 ('dblink',
974 Bio::Annotation::DBLink->new
975 (-primary_id => $id,
976 -version => $version,
977 -database => $db || 'GenBank',
978 -tagname => 'dblink'));
979 } elsif ( $dbsource =~ /(\S+)([\.:])(\d+)/ ) {
980 0 my ($id, $db, $version);
981 0 ▶ if ($2 eq ':') {
Branch: 1 branch
BranchTrueFalseTotal
if ($2 eq ':') { } 0 0 0
982 0 ($db, $id) = ($1, $3);
983 } else {
984 0 ($db, $id, $version) = ('GenBank', $1, $3);
985 }
986 0 $annotation->add_Annotation('dblink',
987 Bio::Annotation::DBLink->new(
988 -primary_id => $id,
989 -version => $version,
990 -database => $db,
991 -tagname => 'dblink')
992 );
993 } else {
994 0 $self->warn("Unrecognized DBSOURCE data: $dbsource\n");
995 }
996 }
997 }
998  
999 # EMBL DR lines
1000 # UniProt/SwissProt DR lines
1001 20 ▶sub _generic_dbsource {
Subroutine _generic_dbsource: called CC=3 SCAR=11.1
1002 20 my ($self, $data) = @_;
1003 #$self->debug(Dumper($data));
1004 20 ▶ while ($data->{DATA} =~ m{([^\n]+)}og) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"DATA"} =~ /([^\n]+)/go) 351 20 371
1005 351 my $dblink = $1;
1006 351 $dblink =~ s{\.$}{};
1007 351 my $link;
1008 351 my @linkdata = split '; ',$dblink;
1009 351 ▶ if ( $dblink =~ m{([^\s;]+);\s*([^\s;]+);?\s*([^\s;]+)?}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($dblink =~ /([^\s;]+);\s*([^\s;]+);?\s*([^\s;]+)?/) { } 351 0 351
1010 #if ( $dblink =~ m{([^\s;]+);\s*([^\s;]+);?\s*([^\s;]+)?}) {
1011 351 my ($databse, $prim_id, $sec_id) = ($1,$2,$3);
1012 351 $link = Bio::Annotation::DBLink->new(-database => $databse,
1013 -primary_id => $prim_id,
1014 -optional_id => $sec_id);
1015 } else {
1016 0 $self->warn("No match for $dblink");
1017 }
1018 351 $self->annotation_collection->add_Annotation('dblink', $link);
1019 }
1020 }
1021  
1022  
1023 # GenBank REFERENCE and related lines
1024 # EMBL R* lines
1025 # UniProt/SwissProt R* lines
1026 301 ▶sub _generic_reference {
Subroutine _generic_reference: called CC=10 SCAR=23.0
1027 301 my ($self, $data) = @_;
1028 301 my $seqformat = $self->format;
1029 301 my ($start, $end);
1030 # get these in EMBL/Swiss
1031 301 ▶ if ($data->{CROSSREF}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"CROSSREF"}) 128 173 301
1032 128 ▶ while ($data->{CROSSREF} =~ m{(pubmed|doi|medline)(?:=|;\s+)(\S+)}oig) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"CROSSREF"} =~ /(pubmed|doi|medline)(?:=|;\s+)(\S+)/gio) 199 128 327
1033 199 my ($db, $ref) = (uc $1, $2);
1034 199 $ref =~ s{[;.]+$}{};
1035 199 $data->{$db} = $ref;
1036 }
1037 }
1038 # run some cleanup for swissprot
1039 301 ▶ if ($seqformat eq 'swiss') {
Branch: 1 branch
BranchTrueFalseTotal
if ($seqformat eq "swiss") 109 192 301
1040 109 for my $val (values %{ $data }) {
1041 959 $val =~ s{;$}{};
1042 959 $val =~ s{(\w-)\s}{$1};
1043 }
1044 }
1045 301 ▶ if ( $data->{POSITION} ) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"POSITION"}) 127 174 301
1046 127 ▶ if ($seqformat eq 'embl') {
Branch: 2 branches
BranchTrueFalseTotal
if ($seqformat eq 'embl') { } 18 109 127
elsif ($data->{'POSITION'} =~ /.+? OF (\d+)-(\d+).*/) { } 23 86 109
1047 18 ($start, $end) = split '-', $data->{POSITION},2;
1048 } elsif ($data->{POSITION} =~ m{.+? OF (\d+)-(\d+).*}) { #swiss
1049 23 ($start, $end) = ($1, $2);
1050 }
1051 }
1052 301 ▶ if ($data->{DATA} =~ m{^\d+\s+\([a-z]+\s+(\d+)\s+to\s+(\d+)\)}xmso) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"DATA"} =~ /^\d+\s+\([a-z]+\s+(\d+)\s+to\s+(\d+)\)/mosx) 59 242 301
1053 59 ($start, $end) = ($1, $2);
1054 }
1055 my $ref = Bio::Annotation::Reference->new(
1056 -comment => $data->{REMARK},
1057 -location => $data->{JOURNAL},
1058 -pubmed => $data->{PUBMED},
1059 -consortium => $data->{CONSRTM},
1060 -title => $data->{TITLE},
1061 -authors => $data->{AUTHORS},
1062 -medline => $data->{MEDLINE},
1063 -doi => $data->{DOI},
1064 -rp => $data->{POSITION}, # JIC...
1065 301 -start => $start,
1066 -end => $end,
1067 );
1068 301 ▶ if ($data->{DATA} =~ m{^\d+\s+\((.*)\)}xmso) {
Branch: 1 branch
BranchTrueFalseTotal
if ($data->{"DATA"} =~ /^\d+\s+\((.*)\)/mosx) 59 242 301
1069 59 $ref->gb_reference($1);
1070 }
1071 301 $self->annotation_collection->add_Annotation('reference', $ref);
1072 }
1073  
1074 # GenBank COMMENT lines
1075 # EMBL CC lines
1076 # UniProt/SwissProt CC lines
1077 43 ▶sub _generic_comment {
Subroutine _generic_comment: called CC=1 SCAR=0.0
1078 43 my ($self, $data) = @_;
1079 $self->annotation_collection->add_Annotation('comment',
1080 43 Bio::Annotation::Comment->new( -text => $data->{DATA} ));
1081 }
1082  
1083 ####################### SEQFEATURE HANDLER #######################
1084  
1085 # GenBank Feature Table
1086 848 ▶sub _generic_seqfeatures {
Subroutine _generic_seqfeatures: called CC=9 SCAR=22.4
1087 848 my ($self, $data) = @_;
1088 848 ▶ return if $data->{FEATURE_KEY} eq 'FEATURES';
Branch: 1 branch
BranchTrueFalseTotal
if $data->{"FEATURE_KEY"} eq "FEATURES" 30 818 848
1089 818 my $primary_tag = $data->{FEATURE_KEY};
1090
1091 # grab the NCBI taxon ID from the source SF
1092 818 ▶ if ($primary_tag eq 'source' && exists $data->{'db_xref'}) {
Branch: 1 branch
BranchTrueFalseTotal
if ($primary_tag eq "source" and exists $data->{"db_xref"}) 36 782 818
Condition100%3/3
$primary_tag eq "source" and exists $data->{"db_xref"}
!ll&&!rl&&r
777536
MC/DC100%2/2
$primary_tag eq "source" and exists $data->{"db_xref"}
$primary_tag eq "source" exists $data->{"db_xref"}
Truth table100%3/3
A and B
A= $primary_tag eq "source"B= exists $data->{"db_xref"}
ABresult
0X0
100
111
1093 36 ▶ if ( $self->{'_params'}->{'-species'} &&
Branch: 1 branch
BranchTrueFalseTotal
if ($self->{"_params"}{"-species"} and $data->{"db_xref"} =~ /taxon:(\d+)/mosx) 35 1 36
Condition66%2/3
$self->{"_params"}{"-species"} and $data->{"db_xref"} =~ /taxon:(\d+)/mosx
!ll&&!rl&&r
0135
MC/DC50%1/2
$self->{"_params"}{"-species"} and $data->{"db_xref"} =~ /taxon:(\d+)/mosx
$self->{"_params"}{"-species"} $data->{"db_xref"} =~ /taxon:(\d+)/mosx
Truth table66%2/3
A and B
A= $self->{"_params"}{"-species"}B= $data->{"db_xref"} =~ /taxon:(\d+)/mosx
ABresult
0X0
100
111
1094 $data->{'db_xref'} =~ m{taxon:(\d+)}xmso ) {
1095 35 $self->{'_params'}->{'-species'}->ncbi_taxid($1);
1096 }
1097 }
1098 818 my $source = $self->format;
1099
1100 818 my $seqid = ${ $self->get_params('accession_number') }{'accession_number'};
1101
1102 818 my $loc;
1103 818 eval {
1104 818 $loc = $self->{'_locfactory'}->from_string($data->{'LOCATION'});
1105 };
1106 818 ▶ if(! $loc) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($loc) 0 818 818
1107 $self->warn("exception while parsing location line [" .
1108 $data->{'LOCATION'} .
1109 "] in reading $source, ignoring feature " .
1110 0 $data->{'primary_tag'}.
1111 " (seqid=" . $seqid . "): " . $@);
1112 0 return;
1113 }
1114 818 ▶ if($seqid && (! $loc->is_remote())) {
Branch: 1 branch
BranchTrueFalseTotal
if ($seqid and not $loc->is_remote) 0 818 818
Condition33%1/3
$seqid and not $loc->is_remote
!ll&&!rl&&r
81800
MC/DC0%0/2
$seqid and not $loc->is_remote
$seqid not $loc->is_remote
Truth table33%1/3
A and not(B)
A= $seqidB= not $loc->is_remote
ABresult
0X0
100
111
1115 0 $loc->seq_id($seqid); # propagates if it is a split location
1116 }
1117 818 my $sf = Bio::SeqFeature::Generic->direct_new();
1118 818 $sf->location($loc);
1119 818 $sf->primary_tag($primary_tag);
1120 818 $sf->seq_id($seqid);
1121 818 $sf->source_tag($source);
1122 818 delete $data->{'FEATURE_KEY'};
1123 818 delete $data->{'LOCATION'};
1124 818 delete $data->{'NAME'};
1125 818 delete $data->{'DATA'};
1126 818 $sf->set_attributes(-tag => $data);
1127 818 push @{ $self->{'_params'}->{'-features'} }, $sf;
1128 }
1129  
1130 ####################### ODDS AND ENDS #######################
1131  
1132 # Those things that don't fit anywhere else. If a specific name
1133 # maps to the below table, that class and method are used, otherwise
1134 # it goes into a SimpleValue (I think this is a good argument for why
1135 # we need a generic mechanism for storing annotation)
1136  
1137 16 ▶sub _generic_simplevalue {
Subroutine _generic_simplevalue: called CC=1 SCAR=0.0
1138 16 my ($self, $data) = @_;
1139 $self->annotation_collection->add_Annotation(
1140 Bio::Annotation::SimpleValue->new(-tagname => lc($data->{NAME}),
1141 -value => $data->{DATA})
1142 16 );
1143 }
1144  
1145 15 ▶sub noop {}
Subroutine noop: called CC=1 SCAR=0.0
Pod undocumented
1146  
1147 0 ▶sub _debug {
Subroutine _debug: not called CC=1 SCAR=6.9
1148 0 my ($self, $data) = @_;
1149 0 $self->debug(Dumper($data));
1150 }
1151  
1152  
1153 5 1;
« Bio/Search/HSP/HSPI.pm ↑ Summary Bio/Seq/EncodedSeq.pm »