Bio/SeqFeature/Tools/TypeMapper.pm

filter: Statementstmt 15.6% 8 / 51 Branchbran 0.0% 0 / 30 Conditioncond 0.0% 0 / 9 MC/DCmcdc 0.0% 0 / 6 Subroutinesub 25.0% 2 / 8 Podpod 83.3% 5 / 6 totaltotal 13.6% 15 / 110 CC 20 SCAR 47.5
CC
20
Cov
9%
map_types
210.0
get_relationship_type_by_parent_child
30.0
new
6.0
CRAP 115.6
« Bio/Tools/GFF.pm ↑ Summary Bio/Root/HTTPget.pm »
1 #
2 # bioperl module for Bio::SeqFeature::Tools::TypeMapper
3 #
4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
5 #
6 # Cared for by Chris Mungall <cjm@fruitfly.org>
7 #
8 # Copyright Chris Mungall
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::SeqFeature::Tools::TypeMapper - maps $seq_feature-E<gt>primary_tag
17  
18 =head1 SYNOPSIS
19  
20 use Bio::SeqIO;
21 use Bio::SeqFeature::Tools::TypeMapper;
22  
23 # first fetch a genbank SeqI object
24 $seqio =
25 Bio::SeqIO->new(-file=>'AE003644.gbk',
26 -format=>'GenBank');
27 $seq = $seqio->next_seq();
28  
29 $tm = Bio::SeqFeature::Tools::TypeMapper->new;
30  
31 # map all the types in the sequence
32 $tm->map_types(-seq=>$seq,
33 {CDS=>'ORF',
34 variation=>sub {
35 my $f = shift;
36 $f->length > 1 ?
37 'variation' : 'SNP'
38 },
39 });
40  
41 # alternatively, use the hardcoded SO mapping
42 $tm->map_types_to_SO(-seq=>$seq);
43  
44 =head1 DESCRIPTION
45  
46 This class implements an object for mapping between types; for
47 example, the types in a genbank feature table, and the types specified
48 in the Sequence Ontology.
49  
50 You can specify your own mapping, either as a simple hash index, or by
51 providing your own subroutines.
52  
53 =head1 FEEDBACK
54  
55 =head2 Mailing Lists
56  
57 User feedback is an integral part of the evolution of this and other
58 Bioperl modules. Send your comments and suggestions preferably to the
59 Bioperl mailing lists Your participation is much appreciated.
60  
61 bioperl-l@bioperl.org - General discussion
62 http://bioperl.org/wiki/Mailing_lists - About the mailing lists
63  
64 =head2 Support
65  
66 Please direct usage questions or support issues to the mailing list:
67  
68 I<bioperl-l@bioperl.org>
69  
70 rather than to the module maintainer directly. Many experienced and
71 reponsive experts will be able look at the problem and quickly
72 address it. Please include a thorough description of the problem
73 with code and data examples if at all possible.
74  
75 =head2 Reporting Bugs
76  
77 report bugs to the Bioperl bug tracking system to help us keep track
78 the bugs and their resolution. Bug reports can be submitted via the
79 web:
80  
81 https://github.com/bioperl/bioperl-live/issues
82  
83 =head1 AUTHOR - Chris Mungall
84  
85 Email: cjm@fruitfly.org
86  
87 =head1 APPENDIX
88  
89 The rest of the documentation details each of the object
90 methods. Internal methods are usually preceded with a _
91  
92 =cut
93  
94  
95 # Let the code begin...
96  
97 package Bio::SeqFeature::Tools::TypeMapper;
98 1 $Bio::SeqFeature::Tools::TypeMapper::VERSION = '1.7.8';
99 1 ▶use strict;
Subroutine BEGIN: called CC=1 SCAR=0.0
100  
101 # Object preamble - inherits from Bio::Root::Root
102  
103 1 ▶use base qw(Bio::Root::Root);
Subroutine BEGIN: called CC=1 SCAR=0.0
104  
105 =head2 new
106  
107 Title : new
108 Usage : $unflattener = Bio::SeqFeature::Tools::TypeMapper->new();
109 Function: constructor
110 Example :
111 Returns : a new Bio::SeqFeature::Tools::TypeMapper
112 Args : see below
113  
114  
115 =cut
116  
117 0 ▶sub new {
Subroutine new: not called CC=2 SCAR=17.9
Pod documented
118 0 my($class,@args) = @_;
119 0 my $self = $class->SUPER::new(@args);
120  
121 0 my($typemap) =
122 $self->_rearrange([qw(TYPEMAP
123 )],
124 @args);
125  
126 0 ▶ $typemap && $self->typemap($typemap);
Branch: 1 branch
BranchTrueFalseTotal
$typemap and $self->typemap($typemap) 0 0 0
127 0 return $self; # success - we hope!
128 }
129  
130 =head2 typemap
131  
132 Title : typemap
133 Usage : $obj->typemap($newval)
134 Function:
135 Example :
136 Returns : value of typemap (a scalar)
137 Args : on set, new value (a scalar or undef, optional)
138  
139  
140 =cut
141  
142 0 ▶sub typemap{
Subroutine typemap: not called CC=2 SCAR=17.9
Pod documented
143 0 my $self = shift;
144  
145 0 ▶ return $self->{'typemap'} = shift if @_;
Branch: 1 branch
BranchTrueFalseTotal
if @_ 0 0 0
146 0 return $self->{'typemap'};
147 }
148  
149 =head2 map_types
150  
151 Title : map_types
152 Usage :
153 Function:
154 Example :
155 Returns :
156 Args :
157  
158 dgg: added -undefined => "region" option to produce all valid SO mappings.
159  
160 =cut
161  
162 0 ▶sub map_types{
Subroutine map_types: not called CC=14 SCAR=53.5
Pod documented
163 0 my ($self,@args) = @_;
164  
165 0 my($sf, $seq, $type_map, $undefmap) =
166 $self->_rearrange([qw(FEATURE
167 SEQ
168 TYPE_MAP
169 UNDEFINED
170 )],
171 @args);
172 0 ▶ if (!$sf && !$seq) {
Branch: 1 branch
BranchTrueFalseTotal
unless ($sf or $seq) 0 0 0
Condition0%0/3
$sf or $seq
l!l&&r!l&&!r
000
MC/DC0%0/2
$sf or $seq
$sf $seq
Truth table0%0/3
A or B
A= $sfB= $seq
ABresult
1X1
011
000
173 0 $self->throw("you need to pass in either -feature or -seq");
174 }
175  
176 0 my @sfs = ($sf);
177 0 ▶ if ($seq) {
Branch: 1 branch
BranchTrueFalseTotal
if ($seq) 0 0 0
178 0 ▶ $seq->isa("Bio::SeqI") || $self->throw("$seq NOT A SeqI");
Branch: 1 branch
BranchTrueFalseTotal
$seq->isa("Bio::SeqI") or $self->throw("$seq NOT A SeqI") 0 0 0
179 0 @sfs = $seq->get_all_SeqFeatures;
180 }
181 0 ▶ $type_map = $type_map || $self->typemap; # dgg: was type_map;
Condition0%0/3
$type_map || $self->typemap
l!l&&r!l&&!r
000
MC/DC0%0/2
$type_map || $self->typemap
$type_map $self->typemap
Truth table0%0/3
A || B
A= $type_mapB= $self->typemap
ABresult
1X1
011
000
182 0 foreach my $sf (@sfs) {
183  
184 0 ▶ $sf->isa("Bio::SeqFeatureI") || $self->throw("$sf NOT A SeqFeatureI");
Branch: 1 branch
BranchTrueFalseTotal
$sf->isa("Bio::SeqFeatureI") or $self->throw("$sf NOT A SeqFeatureI") 0 0 0
185 0 ▶ $sf->isa("Bio::FeatureHolderI") || $self->throw("$sf NOT A FeatureHolderI");
Branch: 1 branch
BranchTrueFalseTotal
$sf->isa("Bio::FeatureHolderI") or $self->throw("$sf NOT A FeatureHolderI") 0 0 0
186  
187 0 my $type = $sf->primary_tag;
188 0 my $mtype = $type_map->{$type};
189 0 ▶ if ($mtype) {
Branch: 1 branch
BranchTrueFalseTotal
if ($mtype) 0 0 0
190 0 ▶ if (ref($mtype)) {
Branch: 2 branches
BranchTrueFalseTotal
if (ref $mtype) { } 0 0 0
elsif ($undefmap and $mtype eq 'undefined') { } 0 0 0
191 0 ▶ if (ref($mtype) eq 'CODE') {
Branch: 1 branch
BranchTrueFalseTotal
if (ref $mtype eq 'CODE') { } 0 0 0
192 0 $mtype = $mtype->($sf);
193 }
194 else {
195 0 $self->throw('type_map values must be scalar or CODE ref. You said: '.$mtype.' for type: '.$type);
196 }
197 }
198 ▶ elsif ($undefmap && $mtype eq 'undefined') { # dgg
Condition0%0/3
$undefmap and $mtype eq "undefined"
!ll&&!rl&&r
000
MC/DC0%0/2
$undefmap and $mtype eq "undefined"
$undefmap $mtype eq "undefined"
Truth table0%0/3
A and B
A= $undefmapB= $mtype eq "undefined"
ABresult
0X0
100
111
199 0 $mtype= $undefmap;
200 }
201 0 $sf->primary_tag($mtype);
202 }
203 }
204 0 return;
205 }
206  
207 =head2 map_types_to_SO
208  
209 Title : map_types_to_SO
210 Usage :
211 Function:
212 Example :
213 Returns :
214 Args :
215  
216 hardcodes the genbank to SO mapping
217  
218 Based on revision 1.22 of SO
219  
220 Please see the actual code for the mappings
221  
222 Taken from
223  
224 L<http://sequenceontology.org/resources/mapping/FT_SO.txt>
225  
226 dgg: separated out FT_SO_map for caller changes. Update with:
227  
228 open(FTSO,"curl -s http://sequenceontology.org/resources/mapping/FT_SO.txt|");
229 while(<FTSO>){
230 chomp; ($ft,$so,$sid,$ftdef,$sodef)= split"\t";
231 print " '$ft' => '$so',\n" if($ft && $so && $ftdef);
232 }
233  
234 =cut
235  
236 0 ▶sub FT_SO_map {
Subroutine FT_SO_map: not called CC=1 SCAR=6.9
Pod undocumented
237 # $self= shift;
238 # note : some of the ft_so mappings are commented out and overriden...
239 return {
240 0 "-" => ["located_sequence_feature", "so:0000110"],
241 "-10_signal" => ["minus_10_signal", "so:0000175"],
242 "-35_signal" => ["minus_35_signal", "so:0000176"],
243 "3'utr" => ["three_prime_utr", "so:0000205"],
244 "3'clip" => ["three_prime_clip", "so:0000557"],
245 "5'utr" => ["five_prime_utr", "so:0000204"],
246 "5'clip" => ["five_prime_clip", "so:0000555"],
247 "caat_signal" => ["caat_signal", "so:0000172"],
248 "cds" => ["cds", "so:0000316"],
249 "c_region" => ["undefined", ""],
250 "d-loop" => ["d_loop", "so:0000297"],
251 "d_segment" => ["d_gene", "so:0000458"],
252 "gc_signal" => ["gc_rich_region", "so:0000173"],
253 "j_segment" => ["undefined", ""],
254 "ltr" => ["long_terminal_repeat", "so:0000286"],
255 "n_region" => ["undefined", ""],
256 "rbs" => ["ribosome_entry_site", "so:0000139"],
257 "sts" => ["sts", "so:0000331"],
258 "s_region" => ["undefined", ""],
259 "tata_signal" => ["tata_box", "so:0000174"],
260 "v_region" => ["undefined", ""],
261 "v_segment" => ["undefined", ""],
262 "attenuator" => ["attenuator", "so:0000140"],
263 "conflict" => ["undefined", ""],
264 "enhancer" => ["enhancer", "so:0000165"],
265 "exon" => ["exon", "so:0000147"],
266 "gap" => ["gap", "so:0000730"],
267 "gene" => ["gene", "so:0000704"],
268 "idna" => ["idna", "so:0000723"],
269 "intron" => ["intron", "so:0000188"],
270 "mRNA" => ["mRNA", "so:0000234"],
271 "mat_peptide" => ["mature_protein_region", "so:0000419"],
272 "mature_peptide" => ["mature_protein_region", "so:0000419"],
273 #"misc_RNA" => ["transcript", "so:0000673"],
274 "misc_binding" => ["binding_site", "so:0000409"],
275 "misc_difference" => ["sequence_difference", "so:0000413"],
276 "misc_feature" => ["region", undef],
277 "misc_recomb" => ["recombination_feature", "so:0000298"],
278 "misc_signal" => ["regulatory_region", "so:0005836"],
279 "misc_structure" => ["sequence_secondary_structure", "so:0000002"],
280 "modified_base" => ["modified_base_site", "so:0000305"],
281 "old_sequence" => ["undefined", ""],
282 "operon" => ["operon", "so:0000178"],
283 "oriT" => ["origin_of_transfer", "so:0000724"],
284 "polya_signal" => ["polyA_signal_sequence", "so:0000551"],
285 "polya_site" => ["polyA_site", "so:0000553"],
286 "precursor_RNA" => ["primary_transcript", "so:0000185"],
287 "prim_transcript" => ["primary_transcript", "so:0000185"],
288 "primer_bind" => ["primer_binding_site", "so:0005850"],
289 "promoter" => ["promoter", "so:0000167"],
290 "protein_bind" => ["protein_binding_site", "so:0000410"],
291 "rRNA" => ["rRNA", "so:0000252"],
292 "repeat_region" => ["repeat_region", "so:0000657"],
293 "repeat_unit" => ["repeat_unit", "so:0000726"],
294 "satellite" => ["satellite_dna", "so:0000005"],
295 "scRNA" => ["scRNA", "so:0000013"],
296 "sig_peptide" => ["signal_peptide", "so:0000418"],
297 "snRNA" => ["snRNA", "so:0000274"],
298 "snoRNA" => ["snoRNA", "so:0000275"],
299 #"source" => ["databank_entry", "so:2000061"],
300 "stem_loop" => ["stem_loop", "so:0000313"],
301 "tRNA" => ["tRNA", "so:0000253"],
302 "terminator" => ["terminator", "so:0000141"],
303 "transit_peptide" => ["transit_peptide", "so:0000725"],
304 "unsure" => "undefined",
305 "variation" => ["sequence_variant", "so:0000109"],
306  
307 # manually added
308 ## has parent = pseudogene ; dgg
309 "pseudomRNA" => ["pseudogenic_transcript", "so:0000516"],
310 ## from unflattener misc_rna ; dgg
311 "pseudotranscript" => ["pseudogenic_transcript", "so:0000516"],
312 "pseudoexon" => ["pseudogenic_exon", "so:0000507"],
313 "pseudoCDS" => ["pseudogenic_exon", "so:0000507"],
314 "pseudomisc_feature" => ["pseudogenic_region", "so:0000462"],
315 "pseudointron" => ["pseudogenic_region", "so:0000462"],
316  
317  
318 ## "undefined" => "region",
319  
320 # this is the most generic form for rnas;
321 # we always represent the processed form of
322 # the transcript
323 misc_RNA => ['mature_transcript',"so:0000233"],
324  
325 # not sure about this one...
326 source=>['contig', "SO:0000149"],
327  
328 rep_origin=>['origin_of_replication',"SO:0000296"],
329  
330 Protein=>['polypeptide',"SO:0000104"],
331 };
332 # return {
333 #"FT term" => "SO term",
334 #"-" => "located_sequence_feature",
335 #"-10_signal" => "minus_10_signal",
336 #"-35_signal" => "minus_35_signal",
337 #"3'UTR" => "three_prime_UTR",
338 #"3'clip" => "three_prime_clip",
339 #"5'UTR" => "five_prime_UTR",
340 #"5'clip" => "five_prime_clip",
341 #"CAAT_signal" => "CAAT_signal",
342 #"CDS" => "CDS",
343 #"C_region" => "undefined",
344 #"D-loop" => "D_loop",
345 #"D_segment" => "D_gene",
346 #"GC_signal" => "GC_rich_region",
347 #"J_segment" => "undefined",
348 #"LTR" => "long_terminal_repeat",
349 #"N_region" => "undefined",
350 #"RBS" => "ribosome_entry_site",
351 #"STS" => "STS",
352 #"S_region" => "undefined",
353 #"TATA_signal" => "TATA_box",
354 #"V_region" => "undefined",
355 #"V_segment" => "undefined",
356 #"attenuator" => "attenuator",
357 #"conflict" => "undefined",
358 #"enhancer" => "enhancer",
359 #"exon" => "exon",
360 #"gap" => "gap",
361 #"gene" => "gene",
362 #"iDNA" => "iDNA",
363 #"intron" => "intron",
364 #"mRNA" => "mRNA",
365 #"mat_peptide" => "mature_protein_region",
366 #"mature_peptide" => "mature_protein_region",
367 ## "misc_RNA" => "transcript",
368 #"misc_binding" => "binding_site",
369 #"misc_difference" => "sequence_difference",
370 #"misc_feature" => "region",
371 #"misc_recomb" => "recombination_feature",
372 #"misc_signal" => "regulatory_region",
373 #"misc_structure" => "sequence_secondary_structure",
374 #"modified_base" => "modified_base_site",
375 #"old_sequence" => "undefined",
376 #"operon" => "operon",
377 #"oriT" => "origin_of_transfer",
378 #"polyA_signal" => "polyA_signal_sequence",
379 #"polyA_site" => "polyA_site",
380 #"precursor_RNA" => "primary_transcript",
381 #"prim_transcript" => "primary_transcript",
382 #"primer_bind" => "primer_binding_site",
383 #"promoter" => "promoter",
384 #"protein_bind" => "protein_binding_site",
385 #"rRNA" => "rRNA",
386 #"repeat_region" => "repeat_region",
387 #"repeat_unit" => "repeat_unit",
388 #"satellite" => "satellite_DNA",
389 #"scRNA" => "scRNA",
390 #"sig_peptide" => "signal_peptide",
391 #"snRNA" => "snRNA",
392 #"snoRNA" => "snoRNA",
393 ## "source" => "databank_entry",
394 #"stem_loop" => "stem_loop",
395 #"tRNA" => "tRNA",
396 #"terminator" => "terminator",
397 #"transit_peptide" => "transit_peptide",
398 #"unsure" => "undefined",
399 #"variation" => "sequence_variant",
400  
401 #"pseudomRNA" => "pseudogenic_transcript", ## has parent = pseudogene ; dgg
402 #"pseudotranscript" => "pseudogenic_transcript", ## from Unflattener misc_RNA ; dgg
403 #"pseudoexon" => "pseudogenic_exon",
404 #"pseudoCDS" => "pseudogenic_exon",
405 #"pseudomisc_feature" => "pseudogenic_region",
406 #"pseudointron" => "pseudogenic_region",
407
408 ### "undefined" => "region",
409  
410 ## this is the most generic form for RNAs;
411 ## we always represent the processed form of
412 ## the transcript
413 #misc_RNA=>'processed_transcript',
414
415 ## not sure about this one...
416 #source=>'contig',
417
418 #rep_origin=>'origin_of_replication',
419
420 #Protein=>'protein',
421 #};
422 }
423  
424 0 ▶sub map_types_to_SO{
Subroutine map_types_to_SO: not called CC=1 SCAR=6.9
Pod documented
425 0 my ($self,@args) = @_;
426  
427 0 push(@args, (-type_map=> $self->FT_SO_map() ) );
428 0 return $self->map_types(@args);
429 }
430  
431 =head2 get_relationship_type_by_parent_child
432  
433 Title : get_relationship_type_by_parent_child
434 Usage : $type = $tm->get_relationship_type_by_parent_child($parent_sf, $child_sf);
435 Usage : $type = $tm->get_relationship_type_by_parent_child('mRNA', 'protein');
436 Function: given two features where the parent contains the child,
437 will determine what the relationship between them in
438 Example :
439 Returns :
440 Args : parent SeqFeature, child SeqFeature OR
441 parent type string, child type string OR
442  
443 bioperl Seq::FeatureHolderI hierarchies are equivalent to unlabeled
444 graphs (where parent nodes are the containers, and child nodes are the
445 features being contained). For example, a feature of type mRNA can
446 contain features of type exon.
447  
448 Some external representations (eg chadoxml or chaosxml) require that
449 the edges in the feature relationship graph are labeled. For example,
450 the type between mRNA and exon would be B<part_of>. Although it
451 stretches the bioperl notion of containment, we could have a CDS
452 contained by an mRNA (for example, the
453 L<Bio::SeqFeature::Tools::Unflattener> module takes genbank records
454 and makes these kind of links. The relationship here would be
455 B<produced_by>
456  
457 In chado speak, the child is the B<subject> feature and the parent is
458 the B<object> feature
459  
460 =cut
461  
462 0 ▶sub get_relationship_type_by_parent_child {
Subroutine get_relationship_type_by_parent_child: not called CC=5 SCAR=34.0
Pod documented
463 0 my ($self,$parent,$child) = @_;
464 0 ▶ $parent = ref($parent) ? $parent->primary_tag : $parent;
Branch: 1 branch
BranchTrueFalseTotal
ref $parent ? : 0 0 0
465 0 ▶ $child = ref($child) ? $child->primary_tag : $child;
Branch: 1 branch
BranchTrueFalseTotal
ref $child ? : 0 0 0
466  
467 0 my $type = 'part_of'; # default
468  
469 # TODO - do this with metadata, or infer via SO itself
470  
471 0 ▶ if (lc($child) eq 'protein') {
Branch: 1 branch
BranchTrueFalseTotal
if (lc $child eq "protein") 0 0 0
472 0 $type = 'derives_from';
473 }
474 0 ▶ if (lc($child) eq 'polypeptide') {
Branch: 1 branch
BranchTrueFalseTotal
if (lc $child eq "polypeptide") 0 0 0
475 0 $type = 'derives_from';
476 }
477 0 return $type;
478 }
479  
480  
481 1 1;
« Bio/Tools/GFF.pm ↑ Summary Bio/Root/HTTPget.pm »