/
genbank.pm
1779 lines (1537 loc) · 52.6 KB
/
genbank.pm
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#
# BioPerl module for Bio::SeqIO::genbank
#
# Please direct questions and support issues to <bioperl-l@bioperl.org>
#
# Cared for by Bioperl project bioperl-l(at)bioperl.org
#
# Copyright Elia Stupka and contributors see AUTHORS section
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
Bio::SeqIO::genbank - GenBank sequence input/output stream
=head1 SYNOPSIS
It is probably best not to use this object directly, but
rather go through the SeqIO handler:
$stream = Bio::SeqIO->new(-file => $filename,
-format => 'GenBank');
while ( my $seq = $stream->next_seq() ) {
# do something with $seq
}
=head1 DESCRIPTION
This object can transform Bio::Seq objects to and from GenBank flat
file databases.
There is some flexibility here about how to write GenBank output
that is not fully documented.
=head2 Optional functions
=over 3
=item _show_dna()
(output only) shows the dna or not
=item _post_sort()
(output only) provides a sorting func which is applied to the FTHelpers
before printing
=item _id_generation_func()
This is function which is called as
print "ID ", $func($seq), "\n";
To generate the ID line. If it is not there, it generates a sensible ID
line using a number of tools.
If you want to output annotations in Genbank format they need to be
stored in a Bio::Annotation::Collection object which is accessible
through the Bio::SeqI interface method L<annotation()|annotation>.
The following are the names of the keys which are pulled from a
L<Bio::Annotation::Collection> object:
reference - Should contain Bio::Annotation::Reference objects
comment - Should contain Bio::Annotation::Comment objects
dblink - Should contain a Bio::Annotation::DBLink object
segment - Should contain a Bio::Annotation::SimpleValue object
origin - Should contain a Bio::Annotation::SimpleValue object
wgs - Should contain a Bio::Annotation::SimpleValue object
=back
=head1 Where does the data go?
Data parsed in Bio::SeqIO::genbank is stored in a variety of data
fields in the sequence object that is returned. Here is a partial list
of fields.
Items listed as RichSeq or Seq or PrimarySeq and then NAME() tell you
the top level object which defines a function called NAME() which
stores this information.
Items listed as Annotation 'NAME' tell you the data is stored the
associated Bio::AnnotationCollectionI object which is associated with
Bio::Seq objects. If it is explicitly requested that no annotations
should be stored when parsing a record of course they will not be
available when you try and get them. If you are having this problem
look at the type of SeqBuilder that is being used to contruct your
sequence object.
Comments Annotation 'comment'
References Annotation 'reference'
Segment Annotation 'segment'
Origin Annotation 'origin'
Dbsource Annotation 'dblink'
Accessions PrimarySeq accession_number()
Secondary accessions RichSeq get_secondary_accessions()
GI number PrimarySeq primary_id()
LOCUS PrimarySeq display_id()
Keywords RichSeq get_keywords()
Dates RichSeq get_dates()
Molecule RichSeq molecule()
Seq Version RichSeq seq_version()
PID RichSeq pid()
Division RichSeq division()
Features Seq get_SeqFeatures()
Alphabet PrimarySeq alphabet()
Definition PrimarySeq description() or desc()
Version PrimarySeq version()
Sequence PrimarySeq seq()
There is more information in the Feature-Annotation HOWTO about each
field and how it is mapped to the Sequence object
L<http://bioperl.open-bio.org/wiki/HOWTO:Feature-Annotation>.
=head1 FEEDBACK
=head2 Mailing Lists
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists. Your participation is much appreciated.
bioperl-l@bioperl.org - General discussion
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
=head2 Support
Please direct usage questions or support issues to the mailing list:
I<bioperl-l@bioperl.org>
rather than to the module maintainer directly. Many experienced and
reponsive experts will be able look at the problem and quickly
address it. Please include a thorough description of the problem
with code and data examples if at all possible.
=head2 Reporting Bugs
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution. Bug reports can be submitted via the web:
https://redmine.open-bio.org/projects/bioperl/
=head1 AUTHOR - Bioperl Project
bioperl-l at bioperl.org
Original author Elia Stupka, elia -at- tigem.it
=head1 CONTRIBUTORS
Ewan Birney birney at ebi.ac.uk
Jason Stajich jason at bioperl.org
Chris Mungall cjm at fruitfly.bdgp.berkeley.edu
Lincoln Stein lstein at cshl.org
Heikki Lehvaslaiho, heikki at ebi.ac.uk
Hilmar Lapp, hlapp at gmx.net
Donald G. Jackson, donald.jackson at bms.com
James Wasmuth, james.wasmuth at ed.ac.uk
Brian Osborne, bosborne at alum.mit.edu
Chris Fields, cjfields at bioperl dot org
=head1 APPENDIX
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
=cut
# Let the code begin...
package Bio::SeqIO::genbank;
use strict;
use Bio::SeqIO::FTHelper;
use Bio::SeqFeature::Generic;
use Bio::Species;
use Bio::Seq::SeqFactory;
use Bio::Annotation::Collection;
use Bio::Annotation::Comment;
use Bio::Annotation::Reference;
use Bio::Annotation::DBLink;
use base qw(Bio::SeqIO);
our %FTQUAL_NO_QUOTE = map {$_ => 1} qw(
anticodon citation
codon codon_start
cons_splice direction
evidence label
mod_base number
rpt_type rpt_unit
transl_except transl_table
usedin
);
our %DBSOURCE = map {$_ => 1} qw(
EchoBASE IntAct SWISS-2DPAGE ECO2DBASE ECOGENE TIGRFAMs
TIGR GO InterPro Pfam PROSITE SGD GermOnline
HSSP PhosSite Ensembl RGD AGD ArrayExpress KEGG
H-InvDB HGNC LinkHub PANTHER PRINTS SMART SMR
MGI MIM RZPD-ProtExp ProDom MEROPS TRANSFAC Reactome
UniGene GlycoSuiteDB PIRSF HSC-2DPAGE PHCI-2DPAGE
PMMA-2DPAGE Siena-2DPAGE Rat-heart-2DPAGE Aarhus/Ghent-2DPAGE
Biocyc MetaCyc Biocyc:Metacyc GenomeReviews FlyBase
TMHOBP COMPLUYEAST-2DPAGE OGP DictyBase HAMAP
PhotoList Gramene WormBase WormPep Genew ZFIN
PeroxiBase MaizeDB TAIR DrugBank REBASE HPA
swissprot GenBank GenPept REFSEQ embl PDB UniProtKB
DIP PeptideAtlas PRIDE CYGD HOGENOME Gene3D
Project);
our %VALID_MOLTYPE = map {$_ => 1} qw(NA DNA RNA tRNA rRNA cDNA cRNA ms-DNA
mRNA uRNA ss-RNA ss-DNA snRNA snoRNA PRT);
our %VALID_ALPHABET = (
'bp' => 'dna',
'aa' => 'protein',
'rc' => '' # rc = release candidate; file has no sequences
);
sub _initialize {
my($self,@args) = @_;
$self->SUPER::_initialize(@args);
# hash for functions for decoding keys.
$self->{'_func_ftunit_hash'} = {};
$self->_show_dna(1); # sets this to one by default. People can change it
if( ! defined $self->sequence_factory ) {
$self->sequence_factory(Bio::Seq::SeqFactory->new
(-verbose => $self->verbose(),
-type => 'Bio::Seq::RichSeq'));
}
}
=head2 next_seq
Title : next_seq
Usage : $seq = $stream->next_seq()
Function: returns the next sequence in the stream
Returns : Bio::Seq object
Args :
=cut
sub next_seq {
my ($self,@args) = @_;
my %args = @args;
my $builder = $self->sequence_builder();
my $seq;
my %params;
RECORDSTART:
while (1) {
my $buffer;
my (@acc, @features);
my ($display_id, $annotation);
my $species;
# initialize; we may come here because of starting over
@features = ();
$annotation = undef;
@acc = ();
$species = undef;
%params = (-verbose => $self->verbose); # reset hash
local($/) = "\n";
while(defined($buffer = $self->_readline())) {
last if index($buffer,'LOCUS ') == 0;
}
return unless defined $buffer; # end of file
$buffer =~ /^LOCUS\s+(\S.*)$/o ||
$self->throw("GenBank stream with bad LOCUS line. Not GenBank in my book. Got '$buffer'");
my @tokens = split(' ', $1);
# this is important to have the id for display in e.g. FTHelper,
# otherwise you won't know which entry caused an error
$display_id = shift(@tokens);
$params{'-display_id'} = $display_id;
# may still be useful if we don't want the seq
my $seqlength = shift(@tokens);
if (exists $VALID_ALPHABET{$seqlength}) {
# moved one token too far. No locus name?
$self->warn("Bad LOCUS name? Changing [$params{'-display_id'}] to 'unknown' and length to $display_id");
$params{'-display_id'} = 'unknown';
$params{'-length'} = $display_id;
# add token back...
unshift @tokens, $seqlength;
} else {
$params{'-length'} = $seqlength;
}
# the alphabet of the entry
# shouldn't assign alphabet unless one is specifically designated (such as for rc files)
my $alphabet = lc(shift @tokens);
$params{'-alphabet'} = (exists $VALID_ALPHABET{$alphabet}) ? $VALID_ALPHABET{$alphabet} :
$self->warn("Unknown alphabet: $alphabet");
# for aa there is usually no 'molecule' (mRNA etc)
if ($params{'-alphabet'} eq 'protein') {
$params{'-molecule'} = 'PRT'
} else {
$params{'-molecule'} = shift(@tokens);
}
# take care of lower case issues
if ($params{'-molecule'} eq 'dna' || $params{'-molecule'} eq 'rna') {
$params{'-molecule'} = uc $params{'-molecule'};
}
$self->debug("Unrecognized molecule type:".$params{'-molecule'}) if
!exists($VALID_MOLTYPE{$params{'-molecule'}});
my $circ = shift(@tokens);
if ($circ eq 'circular') {
$params{'-is_circular'} = 1;
$params{'-division'} = shift(@tokens);
} else {
# 'linear' or 'circular' may actually be omitted altogether
$params{'-division'} =
(CORE::length($circ) == 3 ) ? $circ : shift(@tokens);
}
my $date = join(' ', @tokens); # we lump together the rest
# this is per request bug #1513
# we can handle
# 9-10-2003
# 9-10-03
# 09-10-2003
# 09-10-03
if($date =~ s/\s*((\d{1,2})-(\w{3})-(\d{2,4})).*/$1/) {
if( length($date) < 11 ) {
# improperly formatted date
# But we'll be nice and fix it for them
my ($d,$m,$y) = ($2,$3,$4);
if( length($d) == 1 ) {
$d = "0$d";
}
# guess the century here
if( length($y) == 2 ) {
if( $y > 60 ) { # arbitrarily guess that '60' means 1960
$y = "19$y";
} else {
$y = "20$y";
}
$self->warn("Date was malformed, guessing the century for $date to be $y\n");
}
$params{'-dates'} = [join('-',$d,$m,$y)];
} else {
$params{'-dates'} = [$date];
}
}
# set them all at once
$builder->add_slot_value(%params);
%params = ();
# parse the rest if desired, otherwise start over
if(! $builder->want_object()) {
$builder->make_object();
next RECORDSTART;
}
# set up annotation depending on what the builder wants
if($builder->want_slot('annotation')) {
$annotation = Bio::Annotation::Collection->new();
}
$buffer = $self->_readline();
until( !defined ($buffer) ) {
$_ = $buffer;
# Description line(s)
if (/^DEFINITION\s+(\S.*\S)/) {
my @desc = ($1);
while ( defined($_ = $self->_readline) ) {
if( /^\s+(.*)/ ) { push (@desc, $1); next };
last;
}
$builder->add_slot_value(-desc => join(' ', @desc));
# we'll continue right here because DEFINITION always comes
# at the top of the entry
$buffer= $_;
}
# accession number (there can be multiple accessions)
if( /^ACCESSION\s+(\S.*\S)/ ) {
push(@acc, split(/\s+/,$1));
while( defined($_ = $self->_readline) ) {
/^\s+(.*)/ && do { push (@acc, split(/\s+/,$1)); next };
last;
}
$buffer = $_;
next;
}
# PID
elsif( /^PID\s+(\S+)/ ) {
$params{'-pid'} = $1;
}
# Version number
elsif( /^VERSION\s+(\S.+)$/ ) {
my ($acc,$gi) = split(' ',$1);
if($acc =~ /^\w+\.(\d+)/) {
$params{'-version'} = $1;
$params{'-seq_version'} = $1;
}
if($gi && (index($gi,"GI:") == 0)) {
$params{'-primary_id'} = substr($gi,3);
}
}
# Keywords
elsif( /^KEYWORDS\s+(\S.*)/ ) {
my @kw = split(/\s*\;\s*/,$1);
while( defined($_ = $self->_readline) ) {
chomp;
/^\s+(.*)/ && do { push (@kw, split(/\s*\;\s*/,$1)); next };
last;
}
@kw && $kw[-1] =~ s/\.$//;
$params{'-keywords'} = \@kw;
$buffer = $_;
next;
}
# Organism name and phylogenetic information
elsif (/^SOURCE\s+\S/) {
if($builder->want_slot('species')) {
$species = $self->_read_GenBank_Species(\$buffer);
$builder->add_slot_value(-species => $species);
} else {
while(defined($buffer = $self->_readline())) {
last if substr($buffer,0,1) ne ' ';
}
}
next;
}
# References
elsif (/^REFERENCE\s+\S/) {
if($annotation) {
my @refs = $self->_read_GenBank_References(\$buffer);
foreach my $ref ( @refs ) {
$annotation->add_Annotation('reference',$ref);
}
} else {
while(defined($buffer = $self->_readline())) {
last if substr($buffer,0,1) ne ' ';
}
}
next;
}
# Project
elsif (/^PROJECT\s+(\S.*)/) {
if ($annotation) {
my $project = new Bio::Annotation::SimpleValue->new(-value => $1);
$annotation->add_Annotation('project',$project);
}
}
# Comments
elsif (/^COMMENT\s+(\S.*)/) {
if($annotation) {
my $comment = $1;
while (defined($_ = $self->_readline)) {
last if (/^\S/);
$comment .= $_;
}
$comment =~ s/\n/ /g;
$comment =~ s/ +/ /g;
$annotation->add_Annotation('comment',
Bio::Annotation::Comment->new(-text => $comment,
-tagname => 'comment'));
$buffer = $_;
} else {
while(defined($buffer = $self->_readline())) {
last if substr($buffer,0,1) ne ' ';
}
}
next;
}
# Corresponding Genbank nucleotide id, Genpept only
elsif( /^DB(?:SOURCE|LINK)\s+(\S.+)/ ) {
if ($annotation) {
my $dbsource = $1;
while (defined($_ = $self->_readline)) {
last if (/^\S/);
$dbsource .= $_;
}
# deal with UniProKB dbsources
if( $dbsource =~ s/(UniProt(?:KB)?|swissprot):\s+locus\s+(\S+)\,.+\n// ) {
$annotation->add_Annotation
('dblink',
Bio::Annotation::DBLink->new
(-primary_id => $2,
-database => $1,
-tagname => 'dblink'));
if( $dbsource =~ s/\s+created:\s+([^\.]+)\.\n// ) {
$annotation->add_Annotation
('swissprot_dates',
Bio::Annotation::SimpleValue->new
(-tagname => 'date_created',
-value => $1));
}
while( $dbsource =~ s/\s+(sequence|annotation)\s+updated:\s+([^\.]+)\.\n//g ) {
$annotation->add_Annotation
('swissprot_dates',
Bio::Annotation::SimpleValue->new
(-tagname => 'date_updated',
-value => $2));
}
$dbsource =~ s/\n/ /g;
if( $dbsource =~ s/\s+xrefs:\s+((?:\S+,\s+)+\S+)\s+xrefs/xrefs/ ) {
# will use $i to determine even or odd
# for swissprot the accessions are paired
my $i = 0;
for my $dbsrc ( split(/,\s+/,$1) ) {
if( $dbsrc =~ /(\S+)\.(\d+)/ ||
$dbsrc =~ /(\S+)/ ) {
my ($id,$version) = ($1,$2);
$version ='' unless defined $version;
my $db;
if( $id =~ /^\d\S{3}/) {
$db = 'PDB';
} else {
$db = ($i++ % 2 ) ? 'GenPept' : 'GenBank';
}
$annotation->add_Annotation
('dblink',
Bio::Annotation::DBLink->new
(-primary_id => $id,
-version => $version,
-database => $db,
-tagname => 'dblink'));
}
}
} elsif( $dbsource =~ s/\s+xrefs:\s+(.+)\s+xrefs/xrefs/i ) {
# download screwed up and ncbi didn't put acc in for gi numbers
my $i = 0;
for my $id ( split(/\,\s+/,$1) ) {
my ($acc,$db);
if( $id =~ /gi:\s+(\d+)/ ) {
$acc= $1;
$db = ($i++ % 2 ) ? 'GenPept' : 'GenBank';
} elsif( $id =~ /pdb\s+accession\s+(\S+)/ ) {
$acc= $1;
$db = 'PDB';
} else {
$acc= $id;
$db = '';
}
$annotation->add_Annotation
('dblink',
Bio::Annotation::DBLink->new
(-primary_id => $acc,
-database => $db,
-tagname => 'dblink'));
}
} else {
$self->debug("Cannot match $dbsource\n");
}
if( $dbsource =~ s/xrefs\s+\(non\-sequence\s+databases\):\s+
((?:\S+,\s+)+\S+)//x ) {
for my $id ( split(/\,\s+/,$1) ) {
my $db;
# this is because GenBank dropped the spaces!!!
# I'm sure we're not going to get this right
##if( $id =~ s/^://i ) {
## $db = $1;
##}
$db = substr($id,0,index($id,':'));
if (! exists $DBSOURCE{ $db }) {
$db = ''; # do we want 'GenBank' here?
}
$id = substr($id,index($id,':')+1);
$annotation->add_Annotation
('dblink',
Bio::Annotation::DBLink->new
(-primary_id => $id,
-database => $db,
-tagname => 'dblink'));
}
}
} else {
if( $dbsource =~ /^(\S*?):?\s*accession\s+(\S+)\.(\d+)/ ) {
my ($db,$id,$version) = ($1,$2,$3);
$annotation->add_Annotation
('dblink',
Bio::Annotation::DBLink->new
(-primary_id => $id,
-version => $version,
-database => $db || 'GenBank',
-tagname => 'dblink'));
} elsif ( $dbsource =~ /(\S+)([\.:])\s*(\S+)/ ) {
my ($db, $version);
my @ids = ();
if ($2 eq ':') {
$db = $1;
# Genbank 192 release notes say this: "The second field can consist of
# multiple comma-separated identifiers, if a sequence record has
# multiple DBLINK cross-references of a given type."
# For example: DBLINK Project:100,200,300"
@ids = split (/,/, $3);
} else {
($db, $version) = ('GenBank', $3);
$ids[0] = $1;
}
foreach my $id (@ids) {
$annotation->add_Annotation('dblink',
Bio::Annotation::DBLink->new(
-primary_id => $id,
-version => $version,
-database => $db,
-tagname => 'dblink')
);
}
} else {
$self->warn("Unrecognized DBSOURCE data: $dbsource\n");
}
}
$buffer = $_;
} else {
while(defined($buffer = $self->_readline())) {
last if substr($buffer,0,1) ne ' ';
}
}
next;
}
# Exit at start of Feature table, or start of sequence
last if( /^(FEATURES|ORIGIN)/ );
# Get next line and loop again
$buffer = $self->_readline;
}
return unless defined $buffer;
# add them all at once for efficiency
$builder->add_slot_value(-accession_number => shift(@acc),
-secondary_accessions => \@acc,
%params);
$builder->add_slot_value(-annotation => $annotation) if $annotation;
%params = (); # reset before possible re-use to avoid setting twice
# start over if we don't want to continue with this entry
if(! $builder->want_object()) {
$builder->make_object();
next RECORDSTART;
}
# some "minimal" formats may not necessarily have a feature table
if($builder->want_slot('features') && defined($_) && /^FEATURES/o) {
# need to read the first line of the feature table
$buffer = $self->_readline;
# DO NOT read lines in the while condition -- this is done as a side
# effect in _read_FTHelper_GenBank!
# part of new circular spec:
# commented out for now until kinks worked out
#my $sourceEnd = 0;
#$sourceEnd = $2 if ($buffer =~ /(\d+?)\.\.(\d+?)$/);
while( defined($buffer) ) {
# check immediately -- not at the end of the loop
# note: GenPept entries obviously do not have a BASE line
last if( $buffer =~ /^BASE|ORIGIN|CONTIG|WGS/o);
# slurp in one feature at a time -- at return, the start of
# the next feature will have been read already, so we need
# to pass a reference, and the called method must set this
# to the last line read before returning
my $ftunit = $self->_read_FTHelper_GenBank(\$buffer);
# implement new circular spec: features that cross the origin are now
# seamless instead of being 2 separate joined features
# commented out until kinks get worked out
#if ((! $args{'-nojoin'}) && $ftunit->{'loc'} =~ /^join\((\d+?)\.\.(\d+?),(\d+?)..(\d+?)\)$/
#&& $sourceEnd == $2 && $3 == 1) {
#my $start = $1;
#my $end = $2 + $4;
#$ftunit->{'loc'} = "$start..$end";
#}
# fix suggested by James Diggans
if( !defined $ftunit ) {
# GRRRR. We have fallen over. Try to recover
$self->warn("Unexpected error in feature table for ".$params{'-display_id'}." Skipping feature, attempting to recover");
unless( ($buffer =~ /^\s{5,5}\S+/o) or
($buffer =~ /^\S+/o)) {
$buffer = $self->_readline();
}
next; # back to reading FTHelpers
}
# process ftunit
my $feat =
$ftunit->_generic_seqfeature($self->location_factory(),
$display_id);
# add taxon_id from source if available
if($species && ($feat->primary_tag eq 'source') &&
$feat->has_tag('db_xref') && (! $species->ncbi_taxid() ||
($species->ncbi_taxid && $species->ncbi_taxid =~ /^list/))) {
foreach my $tagval ($feat->get_tag_values('db_xref')) {
if(index($tagval,"taxon:") == 0) {
$species->ncbi_taxid(substr($tagval,6));
last;
}
}
}
# add feature to list of features
push(@features, $feat);
}
$builder->add_slot_value(-features => \@features);
$_ = $buffer;
}
if( defined ($_) ) {
if( /^CONTIG/o ) {
my @contig;
my $ctg = '';
while($_ !~ m{^//}) { # end of file
$_ =~ /^(?:CONTIG)?\s+(.*)/;
$ctg .= $1;
$_ = $self->_readline;
}
if ($ctg) {
$annotation->add_Annotation(
Bio::Annotation::SimpleValue->new(-tagname => 'contig',
-value => $ctg )
);
}
$self->_pushback($_);
} elsif( /^WGS|WGS_SCAFLD\s+/o ) { # catch WGS/WGS_SCAFLD lines
while($_ =~ s/(^WGS|WGS_SCAFLD)\s+//){ # gulp lines
chomp;
$annotation->add_Annotation(
Bio::Annotation::SimpleValue->new(-value => $_,
-tagname => lc($1)));
$_ = $self->_readline;
}
} elsif(! m{^(ORIGIN|//)} ) { # advance to the sequence, if any
while (defined( $_ = $self->_readline) ) {
last if m{^(ORIGIN|//)};
}
}
}
if(! $builder->want_object()) {
$builder->make_object(); # implicit end-of-object
next RECORDSTART;
}
if($builder->want_slot('seq')) {
# the fact that we want a sequence does not necessarily mean that
# there also is a sequence ...
if(defined($_) && s/^ORIGIN\s+//) {
chomp;
if( $annotation && length($_) > 0 ) {
$annotation->add_Annotation('origin',
Bio::Annotation::SimpleValue->new(-tagname => 'origin',
-value => $_));
}
my $seqc = '';
while( defined($_ = $self->_readline) ) {
m{^//} && last;
$_ = uc($_);
s/[^A-Za-z]//g;
$seqc .= $_;
}
#$self->debug("sequence length is ". length($seqc) ."\n");
$builder->add_slot_value(-seq => $seqc);
}
} elsif ( defined($_) && (substr($_,0,2) ne '//')) {
# advance to the end of the record
while( defined($_ = $self->_readline) ) {
last if substr($_,0,2) eq '//';
}
}
# Unlikely, but maybe the sequence is so weird that we don't want it
# anymore. We don't want to return undef if the stream's not exhausted
# yet.
$seq = $builder->make_object();
next RECORDSTART unless $seq;
last RECORDSTART;
} # end while RECORDSTART
return $seq;
}
=head2 write_seq
Title : write_seq
Usage : $stream->write_seq($seq)
Function: writes the $seq object (must be seq) to the stream
Returns : 1 for success and 0 for error
Args : array of 1 to n Bio::SeqI objects
=cut
sub write_seq {
my ($self,@seqs) = @_;
foreach my $seq ( @seqs ) {
$self->throw("Attempting to write with no seq!") unless defined $seq;
if( ! ref $seq || ! $seq->isa('Bio::SeqI') ) {
$self->warn(" $seq is not a SeqI compliant module. Attempting to dump, but may fail!");
}
my $str = $seq->seq;
my ($div, $mol);
my $len = $seq->length();
if ( $seq->can('division') ) {
$div = $seq->division;
}
if( !defined $div || ! $div ) { $div = 'UNK'; }
my $alpha = $seq->alphabet;
if( !$seq->can('molecule') || ! defined ($mol = $seq->molecule()) ) {
$mol = $alpha || 'DNA';
}
my $circular = 'linear ';
$circular = 'circular' if $seq->is_circular;
local($^W) = 0; # supressing warnings about uninitialized fields.
my $temp_line;
if( $self->_id_generation_func ) {
$temp_line = &{$self->_id_generation_func}($seq);
} else {
my $date = '';
if( $seq->can('get_dates') ) {
($date) = $seq->get_dates();
}
$self->warn("No whitespace allowed in GenBank display id [". $seq->display_id. "]")
if $seq->display_id =~ /\s/;
$temp_line = sprintf ("%-12s%-15s%13s %s%4s%-8s%-8s %3s %-s\n",
'LOCUS', $seq->id(),$len,
(lc($alpha) eq 'protein') ? ('aa','', '') :
('bp', '',$mol),$circular,$div,$date);
}
$self->_print($temp_line);
$self->_write_line_GenBank_regex("DEFINITION ", " ",
$seq->desc(),"\\s\+\|\$",80);
# if there, write the accession line
if( $self->_ac_generation_func ) {
$temp_line = &{$self->_ac_generation_func}($seq);
$self->_print("ACCESSION $temp_line\n");
} else {
my @acc = ();
push(@acc, $seq->accession_number());
if( $seq->isa('Bio::Seq::RichSeqI') ) {
push(@acc, $seq->get_secondary_accessions());
}
$self->_print("ACCESSION ", join(" ", @acc), "\n");
# otherwise - cannot print <sigh>
}
# if PID defined, print it
if($seq->isa('Bio::Seq::RichSeqI') && $seq->pid()) {
$self->_print("PID ", $seq->pid(), "\n");
}
# if there, write the version line
if( defined $self->_sv_generation_func() ) {
$temp_line = &{$self->_sv_generation_func}($seq);
if( $temp_line ) {
$self->_print("VERSION $temp_line\n");
}
} else {
if($seq->isa('Bio::Seq::RichSeqI') && defined($seq->seq_version)) {
my $id = $seq->primary_id(); # this may be a GI number
$self->_print("VERSION ",
$seq->accession_number(), ".", $seq->seq_version,
($id && ($id =~ /^\d+$/) ? " GI:".$id : ""),
"\n");
}
}
# if there, write the PROJECT line
for my $proj ( $seq->annotation->get_Annotations('project') ) {
$self->_print("PROJECT ".$proj->value."\n");
}
# if there, write the DBSOURCE line
foreach my $ref ( $seq->annotation->get_Annotations('dblink') ) {
my ($db, $id) = ($ref->database, $ref->primary_id);
my $prefix = $db eq 'Project' ? 'DBLINK' : 'DBSOURCE';
my $text = $db eq 'GenBank' ? '' :
$db eq 'Project' ? "$db:$id" : "$db accession $id";
$self->_print(sprintf ("%-11s %s\n",$prefix, $text));
}
# if there, write the keywords line
if( defined $self->_kw_generation_func() ) {
$temp_line = &{$self->_kw_generation_func}($seq);
$self->_print("KEYWORDS $temp_line\n");
} else {
if( $seq->can('keywords') ) {
my $kw = $seq->keywords;
$kw .= '.' if( $kw !~ /\.$/ );
$self->_print("KEYWORDS $kw\n");
}
}
# SEGMENT if it exists
foreach my $ref ( $seq->annotation->get_Annotations('segment') ) {
$self->_print(sprintf ("%-11s %s\n",'SEGMENT',
$ref->value));
}
# Organism lines
if (my $spec = $seq->species) {
my ($on, $sn, $cn) = ($spec->can('organelle') ? $spec->organelle : '',
$spec->scientific_name,
$spec->common_name);
my @classification;
if ($spec->isa('Bio::Species')) {
@classification = $spec->classification;
shift(@classification);
} else {
# Bio::Taxon should have a DB handle of some type attached, so
# derive the classification from that
my $node = $spec;
while ($node) {
$node = $node->ancestor || last;
unshift(@classification, $node->node_name);
#$node eq $root && last;
}
@classification = reverse @classification;
}
my $abname = $spec->name('abbreviated') ? # from genbank file
$spec->name('abbreviated')->[0] : $sn;
my $sl = $on ? "$on " : '';
$sl .= $cn ? $abname." ($cn)" : "$abname";
$self->_write_line_GenBank_regex("SOURCE ", ' 'x12, $sl, "\\s\+\|\$",80);
$self->_print(" ORGANISM ", $spec->scientific_name, "\n");
my $OC = join('; ', (reverse(@classification))) .'.';
$self->_write_line_GenBank_regex(' 'x12,' 'x12,
$OC,"\\s\+\|\$",80);
}
# Reference lines
my $count = 1;
foreach my $ref ( $seq->annotation->get_Annotations('reference') ) {
$temp_line = "REFERENCE $count";
if ($ref->start) {
$temp_line .= sprintf (" (%s %d to %d)",
($seq->alphabet() eq "protein" ?
"residues" : "bases"),
$ref->start,$ref->end);
} elsif ($ref->gb_reference) {
$temp_line .= sprintf (" (%s)", $ref->gb_reference);
}
$self->_print("$temp_line\n");
$self->_write_line_GenBank_regex(" AUTHORS ",' 'x12,
$ref->authors,"\\s\+\|\$",80);
$self->_write_line_GenBank_regex(" CONSRTM ",' 'x12,
$ref->consortium,"\\s\+\|\$",80) if $ref->consortium;
$self->_write_line_GenBank_regex(" TITLE "," "x12,
$ref->title,"\\s\+\|\$",80);
$self->_write_line_GenBank_regex(" JOURNAL "," "x12,
$ref->location,"\\s\+\|\$",80);
if( $ref->medline) {
$self->_write_line_GenBank_regex(" MEDLINE "," "x12,
$ref->medline, "\\s\+\|\$",80);
# I am assuming that pubmed entries only exist when there
# are also MEDLINE entries due to the indentation
}
# This could be a wrong assumption
if( $ref->pubmed ) {
$self->_write_line_GenBank_regex(" PUBMED "," "x12,
$ref->pubmed, "\\s\+\|\$",
80);
}
# put remark at the end
if ($ref->comment) {
$self->_write_line_GenBank_regex(" REMARK "," "x12,
$ref->comment,"\\s\+\|\$",80);
}
$count++;
}
# Comment lines
foreach my $comment ( $seq->annotation->get_Annotations('comment') ) {
$self->_write_line_GenBank_regex("COMMENT "," "x12,
$comment->text,"\\s\+\|\$",80);
}
$self->_print("FEATURES Location/Qualifiers\n");
if( defined $self->_post_sort ) {
# we need to read things into an array. Process. Sort them. Print 'em
my $post_sort_func = $self->_post_sort();
my @fth;