-
Notifications
You must be signed in to change notification settings - Fork 178
/
SimpleAlign.pm
1692 lines (1295 loc) · 33.8 KB
/
SimpleAlign.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 SimpleAlign
#
# Cared for by Ewan Birney <birney@sanger.ac.uk>
#
# Copyright Ewan Birney
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
SimpleAlign - Multiple alignments held as a set of sequences
=head1 SYNOPSIS
$aln = new Bio::SimpleAlign;
$aln->read_MSF(\*STDIN);
$aln->write_fasta(\*STDOUT);
=head1 INSTALLATION
This module is included with the central Bioperl distribution:
http://bio.perl.org/Core/Latest
ftp://bio.perl.org/pub/DIST
Follow the installation instructions included in the README file.
=head1 DESCRIPTION
SimpleAlign handles multiple alignments of sequences. It is very permissive
of types (it wont insist on things being all same length etc): really
it is a SequenceSet explicitly held in memory with a whole series of
built in manipulations and especially file format systems for
read/writing alignments.
SimpleAlign basically views an alignment as an immutable block of text.
SimpleAlign *is not* the object to be using if you want to perform complex
alignment alignment manipulations.
These functions are much better done by UnivAln by Georg Fuellen.
However for lightweight display/formatting and minimal manipulation
(e.g. removiung all-gaps columns) - this is the one to use.
Tricky concepts. SimpleAlign expects name,start,end to be 'unique' in
the alignment, and this is the key for the internal hashes.
(name,start,end is abreviated nse in the code). However, in many cases
people don't want the name/start-end to be displayed: either multiple
names in an alignment or names specific to the alignment
(ROA1_HUMAN_1, ROA1_HUMAN_2 etc). These names are called
'displayname', and generally is what is used to print out the
alignment. They default to name/start-end
The SimpleAlign Module came from Ewan Birney's Align module
=head1 PROGRESS
SimpleAlign is being slowly converted to bioperl coding standards,
mainly by Ewan.
=over
=item Use Bio::Root::Object - done
=item Use proper exceptions - done
=item Use hashed constructor - not done!
=back
=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
bioperl-guts-l@bioperl.org - Automated bug and CVS messages
http://bioperl.org/MailList.shtml - About the mailing lists
=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 email or the web:
bioperl-bugs@bio.perl.org
http://bio.perl.org/bioperl-bugs/
=head1 AUTHOR
Ewan Birney, birney@sanger.ac.uk
=head1 SEE ALSO
Bio::LocatableSeq.pm
http://bio.perl.org/Projects/modules.html - Online module documentation
http://bio.perl.org/Projects/SeqAlign/ - Bioperl sequence alignment project
http://bio.perl.org/ - Bioperl Project Homepage
=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::SimpleAlign;
use vars qw(@ISA);
use strict;
# Object preamble - inheriets from Bio::Root::Object
use Bio::Root::Object;
use Bio::LocatableSeq; # uses Seq's as list
@ISA = qw(Bio::Root::Object);
# new() is inherited from Bio::Root::Object
# _initialize is where the heavy stuff will happen when new is called
sub _initialize {
my($self,@args) = @_;
my $make = $self->SUPER::_initialize;
# we need to set up internal hashs first!
$self->{'seq'} = {};
$self->{'order'} = {};
$self->{'start_end_lists'} = {};
$self->{'dis_name'} = {};
$self->{'id'} = 'NoName';
# maybe we should automatically read in from args. Hmmm...
# set stuff in self from @args
return $make; # success - we hope!
}
=head2 addSeq
Title : addSeq
Usage : $myalign->addSeq($newseq);
:
:
Function : Adds another sequence to the alignment
: *doesn't* align it - just adds it to the
: hashes
:
Returns : nothing
Argument :
=cut
sub addSeq {
my $self = shift;
my $seq = shift;
my $order = shift;
my ($name,$id,$start,$end);
if( !ref $seq || ! $seq->isa('Bio::LocatableSeq') ) {
$self->throw("Unable to process non locatable sequences");
}
$id = $seq->id();
$start = $seq->start();
$end = $seq->end();
if( !defined $order ) {
$order = keys %{$self->{'seq'}};
}
$name = sprintf("%s-%d-%d",$id,$start,$end);
if( $self->{'seq'}->{$name} ) {
$self->warn("Replacing one sequence [$name]\n");
}
else {
$self->{'order'}->{$order} = $name;
if (not exists( $self->{'start_end_lists'}->{$id})) {
$self->{'start_end_lists'}->{$id} = [];
}
push @{$self->{'start_end_lists'}->{$id}}, $seq;
}
$self->{'seq'}->{$name} = $seq;
}
=head2 column_from_residue_number
Title : column_from_residue_number
Usage : $col = $ali->column_from_residue_number( $seqname, $resnumber)
Function:
This function gives the position in the alignment (i.e. column number) of
the given residue number in the sequence with the given name. For example,
for the alignment
Seq1/91-97 AC..DEF.GH
Seq2/24-30 ACGG.RTY..
Seq3/43-51 AC.DDEFGHI
column_from_residue_number( "Seq1", 94 ) returns 5.
column_from_residue_number( "Seq2", 25 ) returns 2.
column_from_residue_number( "Seq3", 50 ) returns 9.
An exception is thrown if the residue number would lie outside the length
of the aligment (e.g. column_from_residue_number( "Seq2", 22 )
Returns :
A column number for the postion in the alignment of the given residue in the given
sequence (1 = first column)
Args :
A sequence name (not a name/start-end)
A residue number in the whole sequence (not just that segment of it in the alignment)
=cut
sub column_from_residue_number {
my ($self, $seqname, $resnumber) = @_;
foreach my $seq ($self->eachSeqWithId($seqname)) {
if ($resnumber >= $seq->start() and $resnumber <= $seq->end()) {
# we have found the correct sequence
my @residues = $seq->ary();
my $count = $seq->start();
my $i;
for ($i=0; $i < @residues; $i++) {
if ($residues[$i] ne '.' and $residues[$i] ne '-') {
$count == $resnumber and last;
$count++;
}
}
# $i now holds the index of the column. The actual colimn number is this index + 1
return $i+1;
}
}
$self->throw("Could not find a sequence segment in $seqname containing residue number $resnumber");
}
=head2 consensus_string
Title : consensus_string
Usage : $str = $ali->consensus_string()
:
:
Function : Makes a consensus
:
:
:
Returns :
Argument :
=cut
sub consensus_string {
my $self = shift;
my $len;
my ($out,$count);
$out = "";
$len = $self->length_aln();
foreach $count ( 0 .. $len ) {
$out .= $self->consensus_aa($count);
}
return $out;
}
sub consensus_aa {
my $self = shift;
my $point = shift;
my ($seq,%hash,$count,$letter,$key);
foreach $seq ( $self->eachSeq() ) {
$letter = substr($seq->seq,$point,1);
($letter =~ /\./) && next;
# print "Looking at $letter\n";
$hash{$letter}++;
}
$count = -1;
$letter = '?';
foreach $key ( keys %hash ) {
# print "Now at $key $hash{$key}\n";
if( $hash{$key} > $count ) {
$letter = $key;
$count = $hash{$key};
}
}
return $letter;
}
=head2 each_alphabetically
Title : each_alphabetically
Usage : foreach $seq ( $ali->each_alphabetically() )
:
:
Function : returns an array of sequence object sorted
: alphabetically by name and then by start point
:
: Does not change the order of the alignment
Returns :
Argument :
=cut
sub each_alphabetically {
my $self = shift;
my ($seq,$nse,@arr,%hash,$count);
foreach $seq ( $self->eachSeq() ) {
$nse = $seq->get_nse("-","-");
$hash{$nse} = $seq;
}
foreach $nse ( sort alpha_startend keys %hash) {
push(@arr,$hash{$nse});
}
return @arr;
}
sub alpha_startend {
my ($aname,$astart,$bname,$bstart);
($aname,$astart) = split (/-/,$a);
($bname,$bstart) = split (/-/,$b);
if( $aname eq $bname ) {
return $astart <=> $bstart;
}
else {
return $aname cmp $bname;
}
}
=head2 eachSeq
Title : eachSeq
Usage : foreach $seq ( $align->eachSeq() )
:
:
Function : gets an array of Seq objects from the
: alignment
:
:
Returns : an array
Argument : nothing
=cut
sub eachSeq {
my $self = shift;
my (@arr,$order);
foreach $order ( sort { $a <=> $b } keys %{$self->{'order'}} ) {
if( exists $self->{'seq'}->{$self->{'order'}->{$order}} ) {
push(@arr,$self->{'seq'}->{$self->{'order'}->{$order}});
}
}
return @arr;
}
=head2 eachSeqWithId
Title : eachSeqWithId
Usage : foreach $seq ( $align->eachSeqWithName() )
:
:
Function : gets an array of Seq objects from the
: alignment, the contents being those sequences
: with the given name (there may be more than one
:
Returns : an array
Argument : nothing
=cut
sub eachSeqWithId {
my $self = shift;
my $id = shift;
my (@arr, $seq);
if (exists($self->{'start_end_lists'}->{$id})) {
@arr = @{$self->{'start_end_lists'}->{$id}};
}
return @arr;
return @arr;
}
sub get_displayname {
my $self = shift;
my $name = shift;
if( defined $self->{dis_name}->{$name} ) {
return $self->{dis_name}->{$name};
} else {
return $name;
}
}
=head2 id
Title : id
Usage : $myalign->id("Ig")
Function : Gets/sets the id field of the alignment
:
Returns : An id string
Argument : An id string (optional)
=cut
sub id {
my ($self, $name) = @_;
if (defined( $name )) {
$self->{'id'} = $name;
}
return $self->{'id'};
}
=head2 is_flush
Title : is_flush
Usage : if( $ali->is_flush() )
:
:
Function : Tells you whether the alignment
: is flush, ie all of the same length
:
:
Returns : 1 or 0
Argument :
=cut
sub is_flush {
my $self = shift;
my $seq;
my $length = (-1);
my $temp;
foreach $seq ( $self->eachSeq() ) {
if( $length == (-1) ) {
$length = length($seq->seq());
next;
}
$temp = length($seq->seq());
if( $temp != $length ) {
return 0;
}
}
return 1;
}
=head2 length_aln
Title : length_aln()
Usage : $len = $ali->length_aln()
:
:
Function : returns the maximum length of the alignment.
: To be sure the alignment is a block, use is_flush
:
:
Returns :
Argument :
=cut
sub length_aln {
my $self = shift;
my $seq;
my $length = (-1);
my ($temp,$len);
foreach $seq ( $self->eachSeq() ) {
$temp = length($seq->seq());
if( $temp > $length ) {
$length = $temp;
}
}
return $length;
}
=head2 map_chars
Title : map_chars
Usage : $ali->map_chars('\.','-')
:
:
Function : does a s/$arg1/$arg2/ on
: the sequences. Useful for
: gap characters
:
: Notice that the from (arg1) is interpretted
: as a regex, so be careful about quoting meta
: characters (eg $ali->map_chars('.','-') wont
: do what you want)
Returns :
Argument :
=cut
sub map_chars {
my $self = shift;
my $from = shift;
my $to = shift;
my ($seq,$temp);
foreach $seq ( $self->eachSeq() ) {
$temp = $seq->str();
$temp =~ s/$from/$to/g;
$seq->setseq($temp);
}
}
sub maxdisplayname_length {
my $self = shift;
my $maxname = (-1);
my ($seq,$len);
foreach $seq ( $self->eachSeq() ) {
$len = length $self->get_displayname($seq->get_nse());
if( $len > $maxname ) {
$maxname = $len;
}
}
return $maxname;
}
sub maxname_length {
my $self = shift;
my $maxname = (-1);
my ($seq,$len);
foreach $seq ( $self->eachSeq() ) {
$len = length $seq->id();
if( $len > $maxname ) {
$maxname = $len;
}
}
return $maxname;
}
sub maxnse_length {
my $self = shift;
my $maxname = (-1);
my ($seq,$len);
foreach $seq ( $self->eachSeq() ) {
$len = length $seq->get_nse();
if( $len > $maxname ) {
$maxname = $len;
}
}
return $maxname;
}
=head2 no_residues
Title : no_residues
Usage : $no = $ali->no_residues
:
:
Function : number of residues in total
: in the alignment
:
:
Returns :
Argument :
=cut
sub no_residues {
my $self = shift;
my $count = 0;
foreach my $seq ($self->eachSeq) {
my $str = $seq->seq();
$count += ($str =~ s/[^A-Za-z]//g);
}
return $count;
}
=head2 no_sequences
Title : no_sequences
Usage : $depth = $ali->no_sequences
:
:
Function : number of sequence in the
: sequence alignment
:
:
Returns :
Argument :
=cut
sub no_sequences {
my $self = shift;
return scalar($self->eachSeq);
}
=head2 percentage_identity
Title : percentage_identity
Usage : $id = $align->percentage_identity
Function:
The function uses a fast method to calculate the average percentage identity of the alignment
Returns : The average percentage identity of the alignment
Args : None
=cut
sub percentage_identity{
my ($self,@args) = @_;
my @alphabet = ('A','B','C','D','E','F','G','H','I','J','K','L','M',
'N','O','P','Q','R','S','T','U','V','W','X','Y','Z');
my ($len, $total, $subtotal, $divisor, $subdivisor, @seqs, @countHashes);
if (! $self->is_flush()) {
$self->throw("All sequences in the alignment must be the same length");
}
@seqs = $self->eachSeq();
$len = $self->length_aln();
# load the each hash with correct keys for existence checks
for( my $index=0; $index < $len; $index++) {
foreach my $letter (@alphabet) {
$countHashes[$index]->{$letter} = 0;
}
}
foreach my $seq (@seqs) {
my @seqChars = $seq->ary();
for( my $column=0; $column < @seqChars; $column++ ) {
my $char = uc($seqChars[$column]);
if (exists $countHashes[$column]->{$char}) {
$countHashes[$column]->{$char}++;
}
}
}
$total = 0;
$divisor = 0;
for(my $column =0; $column < $len; $column++) {
my %hash = %{$countHashes[$column]};
$subdivisor = 0;
foreach my $res (keys %hash) {
$total += $hash{$res}*($hash{$res} - 1);
$subdivisor += $hash{$res};
}
$divisor += $subdivisor * ($subdivisor - 1);
}
return ($total / $divisor )*100.0;
}
=head2 purge
Title : purge
Usage : $aln->purge(0.7);
Function: removes sequences above whatever %id
Example :
Returns : An array of the removed sequences
Arguments
This function will grind on large alignments. Beware!
(perhaps not ideally implemented)
=cut
sub purge{
my ($self,$perc) = @_;
my (@seqs,$seq,%removed,$i,$j,$count,@one,@two,$seq2,$k,$res,$ratio,@ret);
# $self->write_Pfam(\*STDOUT);
@seqs = $self->eachSeq();
#$self->write_Pfam(\*STDOUT);
# foreach $seq ( @seqs ) {
# printf("$seq %s %s\n",$seq->get_nse(),join(' ',$seq->dump()));
# }
for($i=0;$i< @seqs;$i++ ) {
$seq = $seqs[$i];
#printf "%s\n", $seq->out_fasta();
#print "\n\nDone\n\n";
# if it has already been removed, skip
if( $removed{$seq->get_nse()} == 1 ) {
next;
}
# if not ... look at the other sequences
# make the first array once
@one = $seq->seq();
for($j=$i+1;$j < @seqs;$j++) {
$seq2 = $seqs[$j];
if ( $removed{$seq2->get_nse()} == 1 ) {
next;
}
@two = $seq2->seq();
$count = 0;
$res = 0;
for($k=0;$k<@one;$k++) {
if( $one[$k] ne '.' && $one[$k] ne '-' && $one[$k] eq $two[$k]) {
$count++;
}
if( $one[$k] ne '.' && $one[$k] ne '-' && $two[$k] ne '.' && $two[$k] ne '-' ) {
$res++;
}
}
if( $res == 0 ) {
$ratio = 0;
} else {
$ratio = $count/$res;
}
if( $ratio > $perc ) {
$removed{$seq2->get_nse()} = 1;
$self->removeSeq($seq2);
push(@ret,$seq2);
} else {
# could put a comment here!
}
}
}
return @ret;
}
=head2 read_fasta
Title : read_fasta
Usage : $ali->read_fasta(\*INPUT)
:
:
Function : reads in a fasta formatted
: file for an alignment
:
:
Returns :
Argument :
=cut
sub read_fasta {
my $self = shift;
my $in = shift;
my $count = 0;
my ($start,$end,$name,$seqname,$seq,$seqchar,$tempname,%align);
while( <$in> ) {
if( /^>(\S+)/ ) {
$tempname = $1;
if( defined $name ) {
# put away last name and sequence
if( $name =~ /(\S+)\/(\d+)-(\d+)/ ) {
$seqname = $1;
$start = $2;
$end = $3;
} else {
$seqname=$name;
$start = 1;
$end = length($seqchar);
}
$seq = new Bio::LocatableSeq('-seq'=>$seqchar,
'-id'=>$seqname,
'-start'=>$start,
'-end'=>$end,
);
$self->addSeq($seq);
$count++;
}
$name = $tempname;
$seqchar = "";
next;
}
s/[^A-Za-z\.\-]//g;
$seqchar .= $_;
}
# put away last name and sequence
if( $name =~ /(\S+)\/(\d+)-(\d+)/ ) {
$seqname = $1;
$start = $2;
$end = $3;
} else {
$seqname=$name;
$start = 1;
$end = length($seqchar);
}
$seq = new Bio::LocatableSeq('-seq'=>$seqchar,
'-id'=>$seqname,
'-start'=>$start,
'-end'=>$end,
);
$self->addSeq($seq);
$count++;
return $count;
}
=head2 read_mase
Title : read_mase
Usage : $ali->read_mase(\*INPUT)
:
:
Function : reads mase (seaview)
: formatted alignments
:
:
Returns :
Argument :
=cut
sub read_mase {
my $self = shift;
my $in = shift;
my $name;
my $start;
my $end;
my $seq;
my $add;
my $count = 0;
while( <$in> ) {
/^;/ && next;
if( /^(\S+)\/(\d+)-(\d+)/ ) {
$name = $1;
$start = $2;
$end = $3;
} else {
s/\s//g;
$name = $_;
$end = -1;
}
$seq = "";
while( <$in> ) {
/^;/ && last;
s/[^A-Za-z\.\-]//g;
$seq .= $_;
}
if( $end == -1) {
$start = 1;
$end = length($seq);
}
$add = new Bio::LocatableSeq('-seq'=>$seq,
'-id'=>$name,
'-start'=>$start,
'-end'=>$end,
);
$self->addSeq($add);
$count++;
}
return $count;
}
=head2 read_MSF
Title : read_MSF
Usage : $al->read_MSF(\*STDIN);
Function: reads MSF formatted files. Tries to read *all* MSF
It reads all non whitespace characters in the alignment
area. For MSFs with weird gaps (eg ~~~) map them by using
$al->map_chars('~','-');
Example :
Returns :
Args : filehandle
=cut
sub read_MSF{
my ($self,$fh) = @_;
my (%hash,$name,$str,@names,$seqname,$start,$end,$count,$seq);
# read in the name section
while( <$fh> ) {
/\/\// && last; # move to alignment section
/Name:\s+(\S+)/ && do { $name = $1;
$hash{$name} = ""; # blank line
push(@names,$name); # we need it ordered!
};
# otherwise - skip
}
# alignment section
while( <$fh> ) {
/^\s*(\S+)\s+(.*)$/ && do {
$name = $1;
$str = $2;
if( ! exists $hash{$name} ) {
$self->throw("$name exists as an alignment line but not in the header. Not confident of what is going on!");
}
$str =~ s/\s//g;
$hash{$name} .= $str;
};
}
# now got this as a name - sequence hash. Lets make some sequences!
$count = 0;
foreach $name ( @names ) {
if( $name =~ /(\S+)\/(\d+)-(\d+)/ ) {
$seqname = $1;
$start = $2;
$end = $3;
} else {
$seqname=$name;
$start = 1;
$str = $hash{$name};
$str =~ s/[^A-Za-z]//g;
$end = length($str);
}
$seq = new Bio::LocatableSeq('-seq'=>$hash{$name},
'-id'=>$seqname,
'-start'=>$start,
'-end'=>$end,
);
$self->addSeq($seq);
$count++;
}
return $count;