-
Notifications
You must be signed in to change notification settings - Fork 50
/
DupMasker
executable file
·1372 lines (1214 loc) · 38.2 KB
/
DupMasker
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
#!/usr/bin/perl
##---------------------------------------------------------------------------##
## File:
## @(#) DupMasker
## Author:
## Robert M. Hubley rhubley@systemsbiology.org
## Description:
## Search a sequence against a library of known segmental duplications
##
#******************************************************************************
#* Copyright (C) Institute for Systems Biology 2002-2004 Developed by
#* Robert Hubley, Zhaoshi Jiang, Arian Smit and Evan Eichler.
#*
#* This work is licensed under the Open Source License v2.1. To view a copy
#* of this license, visit http://www.opensource.org/licenses/osl-2.1.php or
#* see the license.txt file contained in this distribution.
#*
###############################################################################
#
# ChangeLog
#
# $Log: DupMasker,v $
# Revision 1.11 2013/11/06 17:48:25 rhubley
# - Fixing dupmasker so that it can use RMBlast
#
# Revision 1.10 2013/02/20 23:44:45 rhubley
# *** empty log message ***
#
# Revision 1.9 2012/09/13 18:17:56 rhubley
# - Another round of perltidy
#
# Revision 1.8 2012/04/12 19:07:36 rhubley
# - Oh boy...lots o changes. Mostly to RepeatMasker script. Cleaning up
# and generalizing the search stages. Removing dead code. Cleaning up
# the old Choose ( now filterRepeats ) routine and trying desperately to
# remove the metadata which is causing grief for HMMER integration.
#
# Revision 1.7 2009/03/26 17:27:20 rhubley
# - Stupid Debian/Ubuntu switched /bin/sh from BASH to DASH thus breaking
# many many scripts in the holy name of POSIX compliance. To quote the
# mormon south park episode: "Dumb dumb dumb dumb dumb".
# I went through and changed all occurances of ">&" to "> file 2>&1"
#
# Revision 1.6 2008/05/29 21:37:40 rhubley
# - Fixed numbering problem in alignments. When there were complete lines
# of gap characters the index would still increment/decrement by one.
#
# - Fixed problem with fragmenting alignments. The "x" cliping boundaries
# were not being honored. This left single "X" characters in the
# alignments.
#
# - Added some more error checking to DupMasker
#
# Revision 1.5 2008/05/14 18:29:15 rhubley
# - Added "-gi" fix to WUBlastSearchEngine.pm
#
# Revision 1.4 2008/04/28 19:50:50 rhubley
# - Added gff option to DupMasker.
# - Fixed WUBlastSearchEngine default temp directory
#
# Revision 1.3 2008/03/24 18:45:59 rhubley
# - Documentation change
#
# Revision 1.2 2008/03/24 18:21:22 rhubley
# - Pretty-fy the wublast missing message
#
# Revision 1.1 2008/03/17 19:03:57 rhubley
# - DupMasker integration
# - Some ALU Work in ProcessRepeats
#
#
###############################################################################
#
# To Do:
#
=head1 NAME
DupMasker - Annotate segmental duplications in a sequence
=head1 SYNOPSIS
DupMasker [-version] [-maxDiv #] [-maxWidth #] [-forceSearch]
[-align] [-gff] [-engine wublast|abblast|ncbi] <myfile.fa>
=head1 DESCRIPTION
Search a file against a library known segmental
duplications. If the file doesn't already have a
RepeatMasker *.out file this script will generate
one. The output is placed in a file named
myfile.fa.duplicons.
The basic program flow is:
- RepeatMask the sequence ( Human libraries )
- Search the masked squence against the duplicon library
- Build realignment regions for each duplicon
- Realign using non-repeat-masked dna
- Join duplicons and output results
The options are:
=over 4
=item -version
Displays the version of the program
=item -engine <abblast|wublast|ncbi>
The name of the search engine we are using. I.e abblast/wublast or
ncbi (rmblast version). If not specified it will attempt to use
the default configured for RepeatMasker.
=item -maxDiv <value>
Filter out duplicon seeds which have a divergence greater than
this value.
=item -maxWidth <value>
The maximum non-repetitive/non-seed realign gaps, default is 300bp
=item -forceSearch
DupMasker uses RepeatMasker .out and previous runs of DupMasker's *.dupout
files by default. Use this option if you would like to rerun these searches.
=item -align
Produce alignments. These are stored in the output file.
=item -gff
Creates an additional Gene Feature Finding (gff) output file.
=item -pa <value>
Spawn this many processes for masking, default is 1
=item -dupout
Stop the program after generating dupout. The second half of the pipeline often fails in snakemake so this way we can split it into two jobs.
=back
=head1 CONFIGURATION OVERRIDES
=head1 SEE ALSO
RepeatMasker
=head1 COPYRIGHT
Copyright 2007-2019 Robert Hubley, Institute for Systems Biology
=head1 AUTHOR
Robert Hubley <rhubley@systemsbiology.org>
=cut
#
# Module Dependence
#
use strict;
use FindBin;
use lib $FindBin::RealBin;
use Pod::Text;
use Getopt::Long;
use Data::Dumper;
# RepeatMasker Libraries
use RepeatMaskerConfig;
use SearchResult;
use SearchResultCollection;
use WUBlastSearchEngine;
use NCBIBlastSearchEngine;
use CrossmatchSearchEngine;
use SeqDBI;
use SimpleBatcher;
use FastaDB;
use File::Basename;
#
# Version
#
my $version = $RepeatMaskerConfig::VERSION;
#
# Option processing
# e.g.
# -t: Single letter binary option
# -t=s: String parameters
# -t=i: Number paramters
#
my @getopt_args = (
'-version', # print out the version and exit
'-maxDiv=i', # maximal duplicon seed divergence
'-maxWidth=i', # realignNonRepMaxWidth zj 5-10-07
'-pa=i',
'-forceSearch',
'-engine=s',
'-dupout',
'-gff',
'-align'
);
# Add configuration parameters as additional command-line options
push @getopt_args, RepeatMaskerConfig::getCommandLineOptions();
#
# Provide the POD text from this file and
# from the config file by merging them
# together. The heading "CONFIGURATION
# OVERRIDES" provides the insertion point
# for the configuration POD.
#
sub usage {
my $p = Pod::Text->new();
$p->output_fh(*STDOUT);
my $pod_str;
open IN,"<$0" or die "Could not open self ($0) for generating documentation!";
while (<IN>){
if ( /^=head1\s+CONFIGURATION OVERRIDES\s*$/ )
{
my $c_pod = RepeatMaskerConfig::getPOD();
if ( $c_pod ) {
$pod_str .= $_ . $c_pod;
}
}else {
$pod_str .= $_;
}
}
close IN;
print "$0 - $version\n";
$p->parse_string_document($pod_str);
exit(1);
}
my %options = ();
Getopt::Long::config( "noignorecase", "bundling_override" );
unless ( GetOptions( \%options, @getopt_args ) )
{
usage();
}
if ( $options{'version'} )
{
print "$version\n";
exit;
}
my $pa=1;
if($options{'pa'})
{
$pa=$options{'pa'};
}
print "Using this many jobs: $pa\n";
#
# Resolve configuration settings using the following precedence:
# command line first, then environment, followed by config
# file.
#
RepeatMaskerConfig::resolveConfiguration(\%options);
my $config = $RepeatMaskerConfig::configuration;
my $LIBDIR = $config->{'LIBDIR'}->{'value'};
#
# Magic numbers/constants here
# ie. my $PI = 3.14159;
#
my $DEBUG = 0;
$DEBUG = 1 if ( $RepeatMaskerConfig::DEBUGALL == 1 );
my $dupliconLib = "$LIBDIR/dupliconlib.fa";
my $REPEATMASKER = "$FindBin::RealBin/RepeatMasker";
die "\n\nThe dupliconlib doesn't appear to be installed in the\n"
. "RepeatMasker libraries directory ( $LIBDIR ). Please download and install\n"
. "this library before proceeding.\n\n"
if ( !-s $dupliconLib );
## Seed clustering parameters
my $maxSeedInsertion = 7000;
my $maxDupliconSeedOverlap = 30;
## Seed realignment boundaries parameters
# realignNonRepMaxWidth: A boundary for realignment ends at the consensus
# boundaries or the first occurance of a
# non-repetitive,non-seed sequence window of
# this size.
my $realignNonRepMaxWidth = 300;
my $ABBLASTN_PRGM = $config->{'ABBLAST_DIR'}->{'value'} . "/blastn";
my $XDFORMAT_PRGM = $config->{'ABBLAST_DIR'}->{'value'} . "/xdformat";
my $RMBLASTN_PRGM = $config->{'RMBLAST_DIR'}->{'value'} . "/rmblastn";
my $NCBIBLASTDB_PRGM = $config->{'RMBLAST_DIR'}->{'value'} . "/makeblastdb";
#
# Setup the search engines
#
my $searchEngineN;
my $engine = $config->{'DEFAULT_SEARCH_ENGINE'}->{'value'};
$engine = $options{'engine'} if ( $options{'engine'} );
my $MATRICES;
if ( $engine )
{
if ( $engine =~ /wublast|abblast/i )
{
$engine = "abblast";
$searchEngineN =
WUBlastSearchEngine->new(
pathToEngine => $ABBLASTN_PRGM );
if ( not defined $searchEngineN )
{
die "Cannot execute $ABBLASTN_PRGM please make "
. "sure you have setup RepeatModeler to use AB/WUBlast "
. "by running the configure script.\n";
}
$MATRICES = "$FindBin::RealBin/Matrices/wublast/nt";
} elsif ( $engine =~ /ncbi/i )
{
$engine = "ncbi";
$searchEngineN =
NCBIBlastSearchEngine->new(
pathToEngine => $RMBLASTN_PRGM );
if ( not defined $searchEngineN )
{
die "Cannot execute $RMBLASTN_PRGM please make "
. "sure you have setup RepeatModeler to use NCBI (RMBlast) by "
. "running the configure script.\n";
}
$MATRICES = "$FindBin::RealBin/Matrices/ncbi/nt";
} else
{
print "\n\nThis program cannot be used with: $engine\n";
print "Please specify -engine wublast|abblast|ncbi and\n";
print "run again.\n\n";
exec "pod2text $0";
die;
}
}else
{
print "\n\nSearch engine was not defined.\n";
print "Please specify -engine wublast|abblast|ncbi and\n";
print "run again.\n\n";
exec "pod2text $0";
die;
}
my $maxDupliconDiv = 0;
if ( $options{'maxDiv'} )
{
$maxDupliconDiv = $options{'maxDiv'};
}
if ( $options{'maxWidth'} )
{ #zj added 5-10-07
$realignNonRepMaxWidth = $options{'maxWidth'};
}
#
# ARGV Processing
#
if ( !defined $ARGV[ 0 ] )
{
usage();
}
my $fastaFile = $ARGV[ 0 ];
die "\nFile does not exist $fastaFile!!!\n\n" if ( !-s $fastaFile );
my $baseFile = basename($fastaFile);
print "\rRunning on this fasta file: $baseFile \n";
#
# Open up the duplicon library
#
my $libDB = FastaDB->new(
fileName => $dupliconLib,
openMode => SeqDBI::ReadOnly,
maxIDLength => 50
);
##
## Create a repeatmasked sequence file if necessary.
##
my $db = FastaDB->new(
fileName => $fastaFile,
openMode => SeqDBI::ReadOnly,
maxIDLength => 50
);
if ( $options{'forceSearch'} || !-e "$fastaFile.out" )
{
print "Searching for repeats...\n";
system( "$REPEATMASKER -pa $pa -engine $engine $fastaFile > /dev/null 2>&1" );
} else
{
print "Using existing repeat annotations in $fastaFile.out\n";
}
# TODO: Make a temporary directory for all the output files.
my $tmpIdx = 1;
my $tmpMaskedFile = "$fastaFile.dup.tmpmask";
if ( -e $tmpMaskedFile )
{
#die "$tmpMaskedFile already exists! Please remove this file and rerun"
# . "the program.\n";
}
&maskSequence(
seqDB => $db,
annotationFile => "$fastaFile.out",
outputFile => $tmpMaskedFile
);
##
## Search for duplicons using RepeatMasker unless already done.
##
if ( $options{'forceSearch'} || !-e "$fastaFile.dupout" )
{
print "Searching for duplicons...\n";
my $cmd = "$REPEATMASKER -pa $pa -engine $engine -nolow -lib $dupliconLib $tmpMaskedFile";
print "$cmd\n" if ( $DEBUG );
system( "$cmd" );
#system( "$cmd > /dev/null 2>&1" );
unless ( $DEBUG )
{
unlink( "$tmpMaskedFile" ) if ( -e "$tmpMaskedFile" );
unlink( "$tmpMaskedFile.cat" ) if ( -e "$tmpMaskedFile.cat" );
unlink( "$tmpMaskedFile.tbl" ) if ( -e "$tmpMaskedFile.tbl" );
unlink( "$tmpMaskedFile.log" ) if ( -e "$tmpMaskedFile.log" );
unlink( "$tmpMaskedFile.ori.out" ) if ( -e "$tmpMaskedFile.ori.out" );
unlink( "$tmpMaskedFile.masked" ) if ( -e "$tmpMaskedFile.masked" );
}
if ( -s "$tmpMaskedFile.out" )
{
print " -Created duplicon seed file $fastaFile.dupout\n";
system( "mv $tmpMaskedFile.out $fastaFile.dupout" );
} else
{
print "No duplicon seeds found in the sequence file!\n";
exit;
}
} else
{
print "Using existing duplicon seeds in $fastaFile.dupout\n";
}
if ( !-e "$fastaFile.dupout" )
{
die "Could not generate $fastaFile.dupout\n";
}
#
# end the pipeline if the goal is to only generate the dupoutfile
#
if($options{'dupout'}){
print "Exiting becasue -dupout specified and dupout has been created\n";
exit;
}
##
## Read in annotations
##
my $repResultsCollection =
CrossmatchSearchEngine::parseOutput( searchOutput => "$fastaFile.out" );
my $dupResultsCollection =
CrossmatchSearchEngine::parseOutput( searchOutput => "$fastaFile.dupout" );
##
## Filter out low scoring duplicons
## Apply divergence filter if required
##
my $dupResIter = $dupResultsCollection->getIterator();
if ( $DEBUG )
{
print "Original Search ( ** denotes removed annots with scores < 300 ";
if ( $maxDupliconDiv )
{
print ", or div >= $maxDupliconDiv ";
}
print "):\n";
print "-------------------------------------------\n";
}
my %queryLengths = ();
while ( $dupResIter->hasNext() )
{
my $annot = $dupResIter->next();
if ( $annot->getScore() < 300
|| ( $maxDupliconDiv && $annot->getPctDiverge() >= $maxDupliconDiv ) )
{ #zj 5-10-07
print "**" . $annot->toStringFormatted() if ( $DEBUG );
$dupResIter->remove();
} else
{
print " " . $annot->toStringFormatted() if ( $DEBUG );
}
if ( !defined $queryLengths{ $annot->getQueryName() } )
{
$queryLengths{ $annot->getQueryName() } =
$annot->getQueryEnd() + $annot->getQueryRemaining();
}
}
undef $dupResIter;
print "\n\n" if ( $DEBUG );
##
## Cluster collinear duplicon hits.
## This creates groups of duplicons that require realignment.
##
$dupResIter = $dupResultsCollection->getIterator();
my %originalSeedBoundaries = ();
my $subElementsString = undef;
if ( $DEBUG )
{
print "Realignment Clusters ( unexpanded )\n";
print "-----------------------------------\n";
}
while ( $dupResIter->hasNext() )
{
my $annot = $dupResIter->next();
my $neighborIter = $dupResIter->getIterator();
my $conRemaining = $annot->getSubjRemaining();
my $annotConGapEnd = -$annot->getSubjEnd();
if ( $annot->getOrientation() eq "C" )
{
$conRemaining = $annot->getSubjStart();
$annotConGapEnd = $annot->getSubjStart();
}
push @{ $originalSeedBoundaries{$annot} },
{
'start' => $annot->getQueryStart(),
'end' => $annot->getQueryEnd(),
'orient' => $annot->getOrientation()
};
$subElementsString = " -> " . $annot->toStringFormatted if ( $DEBUG );
while ( $neighborIter->hasNext() )
{
my $neighbor = $neighborIter->next();
#print "considering:\n Annot: " . $annot->toStringFormatted() .
# "\n Neighbor: " . $neighbor->toStringFormatted() ."\n"
# if ( $DEBUG );
# last if ( too-far-out > consensus + maxInsert );
last
if ( ( $neighbor->getQueryStart() - $annot->getQueryEnd() ) >
( $conRemaining + $maxSeedInsertion ) );
# last if different query sequence
last if ( $annot->getQueryName() ne $neighbor->getQueryName() );
my $neighConGapEnd = $neighbor->getSubjStart();
if ( $neighbor->getOrientation() eq "C" )
{
$neighConGapEnd = -$neighbor->getSubjEnd();
}
# is this element compatible?
if ( $annot->getSubjName() eq $neighbor->getSubjName()
&& $annot->getOrientation eq $neighbor->getOrientation()
&& ( $annotConGapEnd + $neighConGapEnd ) > -$maxDupliconSeedOverlap )
{
# Yes - Remove element and resize range of the parent
$annot->setQueryEnd( $neighbor->getQueryEnd() );
$annot->setQueryRemaining( $neighbor->getQueryRemaining() );
push @{ $originalSeedBoundaries{$annot} },
{
'start' => $neighbor->getQueryStart(),
'end' => $neighbor->getQueryEnd(),
'orient' => $neighbor->getOrientation()
};
$subElementsString .= " -> " . $neighbor->toStringFormatted if ( $DEBUG );
$neighborIter->remove();
}
}
if ( $DEBUG )
{
print "" . $annot->toStringFormatted();
if ( @{ $originalSeedBoundaries{$annot} } > 1 )
{
print "$subElementsString";
}
}
}
undef $dupResIter;
print "\n\n" if ( $DEBUG );
##
## Create a uniq block list from the repeats
## A list of regions/blocks that are neither seed or
## repeat sequence. This is used to determine
## realignment ranges in a subsequent step.
##
my $repResIter = $repResultsCollection->getIterator();
my %uniqBlocks = ();
my $lastRepeat;
while ( $repResIter->hasNext() )
{
my $repeat = $repResIter->next();
if ( defined $lastRepeat
&& $lastRepeat->getQueryName() eq $repeat->getQueryName() )
{
my $gapSize = $repeat->getQueryStart() - $lastRepeat->getQueryEnd() - 1;
if ( $gapSize > 0 )
{
push @{ $uniqBlocks{ $repeat->getQueryName() } },
{
'start' => $lastRepeat->getQueryEnd(),
'end' => $repeat->getQueryStart()
};
}
}
$lastRepeat = $repeat;
}
##
## Expand clusters/singletons to include flanking repeat regions.
## - Place elements which cannot be expanded into an orphan list.
##
my $orphans = SearchResultCollection->new();
$dupResIter = $dupResultsCollection->getIterator();
if ( $DEBUG )
{
print "Realignment Clusters ( expanded )\n";
print "-----------------------------------\n";
}
while ( $dupResIter->hasNext() )
{
my $annot = $dupResIter->next();
my $leftStart = $annot->getQueryStart() - $annot->getSubjStart() + 1;
my $leftEnd = $annot->getQueryStart();
my $rightStart = $annot->getQueryEnd();
my $rightEnd = $annot->getQueryEnd + $annot->getSubjRemaining();
if ( $annot->getOrientation() eq "C" )
{
$leftStart = $annot->getQueryStart() - $annot->getSubjRemaining() + 1;
$rightEnd = $annot->getQueryEnd + $annot->getSubjStart();
}
$leftStart = 1 if ( $leftStart < 1 );
$rightEnd = $annot->getQueryEnd() + $annot->getQueryRemaining()
if (
$rightEnd > ( $annot->getQueryEnd() + $annot->getQueryRemaining() ) );
## Loop over uniq blocks
my $leftBoundry = $leftStart;
my $rightBoundry = $rightEnd;
foreach my $uniqBlock ( @{ $uniqBlocks{ $annot->getQueryName() } } )
{
next if ( $uniqBlock->{'end'} < $leftStart );
last if ( $uniqBlock->{'start'} > $rightEnd );
if (
getOverlapSize(
$uniqBlock->{'start'}, $uniqBlock->{'end'},
$leftStart, $leftEnd
) > $realignNonRepMaxWidth
)
{
$leftBoundry = $uniqBlock->{'end'};
}
if (
getOverlapSize(
$uniqBlock->{'start'}, $uniqBlock->{'end'},
$rightStart, $rightEnd
) > $realignNonRepMaxWidth
)
{
$rightBoundry = $uniqBlock->{'start'};
last;
}
}
$leftBoundry = $annot->getQueryStart()
if ( $leftBoundry > $annot->getQueryStart() );
$rightBoundry = $annot->getQueryEnd()
if ( $rightBoundry < $annot->getQueryEnd() );
if ( $leftBoundry == $annot->getQueryStart()
&& $rightBoundry == $annot->getQueryEnd() )
{
$orphans->add( $annot );
$dupResIter->remove();
print "O " . $annot->toStringFormatted() if ( $DEBUG );
next;
}
$annot->setQueryStart( $leftBoundry );
$annot->setQueryEnd( $rightBoundry );
print " " . $annot->toStringFormatted() if ( $DEBUG );
}
undef $dupResIter;
print "\n\n" if ( $DEBUG );
##
## Group overlapping realignment ranges into one search
##
$dupResultsCollection->sort( \&byNameBeginEndrev );
$dupResIter = $dupResultsCollection->getIterator();
my @ranges = ();
if ( $DEBUG )
{
print "Realignment Blocks:\n";
print "-------------------\n";
}
while ( $dupResIter->hasNext() )
{
my %consensi;
my $annot = $dupResIter->next();
# Look for overlap
my $neighborIter = $dupResIter->getIterator();
my $rangeStart = $annot->getQueryStart();
my $rangeEnd = $annot->getQueryEnd();
push @{ $consensi{ $annot->getSubjName() } },
( @{ $originalSeedBoundaries{$annot} } );
my $lastAnnot = $annot;
# Cluster clusters
print " considering $rangeStart - $rangeEnd\n" if ( $DEBUG );
print " --> " . $annot->toStringFormatted() if ( $DEBUG );
while ( $neighborIter->hasNext() )
{
my $neighbor = $neighborIter->next();
print " vs " . $neighbor->toStringFormatted() if ( $DEBUG );
last if ( $neighbor->getQueryStart() > $lastAnnot->getQueryEnd() );
last if ( $neighbor->getQueryName() ne $lastAnnot->getQueryName() );
$rangeEnd = $neighbor->getQueryEnd()
if ( $neighbor->getQueryEnd() > $rangeEnd );
print " adding: " . $neighbor->getQueryEnd() . "\n" if ( $DEBUG );
push @{ $consensi{ $neighbor->getSubjName() } },
( @{ $originalSeedBoundaries{$neighbor} } );
$lastAnnot = $neighbor;
$neighborIter->remove();
}
# Add orphans which are fully contained inside a realignment range
# and remove from orphan list
my $orphanIter = $orphans->getIterator();
while ( $orphanIter->hasNext() )
{
my $orphan = $orphanIter->next();
next
if ( $orphan->getQueryEnd() < $rangeStart
|| $orphan->getQueryEnd() > $rangeEnd );
last if ( $orphan->getQueryStart() > $rangeEnd );
if ( $orphan->getQueryStart() >= $rangeStart )
{
print "Adding Orphan -> " . $orphan->toStringFormatted() if ( $DEBUG );
print " to range: " . $rangeStart . " - " . $rangeEnd . "\n"
if ( $DEBUG );
push @{ $consensi{ $orphan->getSubjName() } },
( @{ $originalSeedBoundaries{$orphan} } );
my $annot = $orphanIter->remove();
}
}
push @ranges,
{
'id' => $annot->getQueryName(),
'start' => $rangeStart,
'end' => $rangeEnd,
'consensi' => {%consensi}
};
if ( $DEBUG )
{
print " "
. $annot->getQueryName()
. ":$rangeStart-$rangeEnd vs "
. join( ",", keys( %consensi ) ) . "\n";
}
undef $neighborIter;
}
undef $dupResIter;
print "\n\n" if ( $DEBUG );
#
# Setup the search engine
#
$searchEngineN->setMinScore( 180 );
if ( $options{'align'} )
{
$searchEngineN->setGenerateAlignments( 1 );
} else
{
$searchEngineN->setGenerateAlignments( 0 );
}
$searchEngineN->setGapInit( -35 );
$searchEngineN->setBandwidth( 20 );
$searchEngineN->setInsGapExt( -7 );
$searchEngineN->setDelGapExt( -6 );
$searchEngineN->setMaskLevel( 1 );
$searchEngineN->setMinMatch( 9 );
$searchEngineN->setUseDustSeg( 1 );
$searchEngineN->setScoreMode( SearchEngineI::complexityAdjustedScoreMode );
$searchEngineN->setMatrix( "$MATRICES/20p41g.matrix" );
$searchEngineN->setMaskLevel( 90 );
##
## Realign
##
my $totalResultCollection = SearchResultCollection->new();
my $uniqID = 1;
print "Realigning: ";
foreach my $reAlignRange ( @ranges )
{
# Create a temp file name
$tmpIdx = 1;
my $tmpLibFile = "/tmp/tmplibfile-$baseFile-$tmpIdx";
while ( -e $tmpLibFile )
{
$tmpLibFile = "/tmp/tmplibfile-$baseFile-" . $tmpIdx++;
}
#print "Creating tmp lib file: $tmpLibFile \n";
# Extract consensi and save to temp file
open OUT, ">$tmpLibFile" or die "Can't create lib file $tmpLibFile: $?\n";
foreach my $conID ( keys( %{ $reAlignRange->{'consensi'} } ) )
{
my $seq = $libDB->getSequence( $conID );
print OUT ">" . $conID . "\n";
$seq =~ s/(\S{50})/$1\n/g;
$seq .= "\n"
unless ( $seq =~ /.*\n+$/s );
print OUT $seq;
}
close OUT;
# Create a temp file name
$tmpIdx = 1;
my $tmpQueryFile = "/tmp/tmpqueryfile-$baseFile-$tmpIdx";
while ( -e $tmpQueryFile )
{
$tmpQueryFile = "/tmp/tmpqueryfile-$baseFile-" . $tmpIdx++;
}
#print "Creating tmp query file: $tmpQueryFile \n";
# Extract query range and save to a temp file
open OUT, ">$tmpQueryFile" or die "Can't create lib file $tmpQueryFile: $?\n";
print OUT ">"
. $reAlignRange->{'id'} . "_["
. $reAlignRange->{'start'} . "-"
. $reAlignRange->{'end'} . "]\n";
my $seq = $db->getSubstr( $reAlignRange->{'id'},
$reAlignRange->{'start'},
( $reAlignRange->{'end'} - $reAlignRange->{'start'} ) );
$seq =~ s/(\S{50})/$1\n/g;
$seq .= "\n"
unless ( $seq =~ /.*\n+$/s );
print OUT $seq;
close OUT;
$searchEngineN->setSubject( "$tmpLibFile" );
##
##
##
if ( $searchEngineN->isa( "NCBIBlastSearchEngine" ) )
{
system( "$NCBIBLASTDB_PRGM -dbtype nucl "
. "-in $tmpLibFile > /dev/null 2>&1" ) == 0
or die "DupMasker:: Error invoking "
. "$NCBIBLASTDB_PRGM"
. " on file $tmpLibFile.\n";
}else
{
system( "$XDFORMAT_PRGM -n $tmpLibFile > "
. "/dev/null 2>&1" ) == 0
or die "DupMasker: Error invoking xdformat on file "
. "$tmpLibFile. We tried using the xdformat program ( "
. "$XDFORMAT_PRGM ).\n";
}
$searchEngineN->setQuery( "$tmpQueryFile" );
#print "Running: " . $searchEngineN->getParameters() . "\n";
if ( $DEBUG )
{
print "Running a realignment... $tmpQueryFile vs $tmpLibFile\n";
}
print ".";
my ( $status, $searchResultCol ) = $searchEngineN->search();
if ( $status )
{
die "ERROR from search engine (", $? >> 8, ") \n";
}
# Remove temporary files
unless ( $DEBUG )
{
unlink( $tmpQueryFile ) if ( -e $tmpQueryFile );
unlink( $tmpLibFile ) if ( -e $tmpLibFile );
unlink( $tmpLibFile . ".xnd" ) if ( -e $tmpLibFile . ".xnd" );
unlink( $tmpLibFile . ".xns" ) if ( -e $tmpLibFile . ".xns" );
unlink( $tmpLibFile . ".xnt" ) if ( -e $tmpLibFile . ".xnt" );
unlink( $tmpLibFile . ".nhr" ) if ( -e $tmpLibFile . ".nhr" );
unlink( $tmpLibFile . ".nin" ) if ( -e $tmpLibFile . ".nin" );
unlink( $tmpLibFile . ".nsq" ) if ( -e $tmpLibFile . ".nsq" );
}
# Adjust coordinates
my $resIter = $searchResultCol->getIterator();
while ( $resIter->hasNext() )
{
my $annot = $resIter->next();
my $seqID = $annot->getQueryName();
print "Adjusting $seqID\n" if ( $DEBUG );
print $annot->toStringFormatted( SearchResult::NoAlign ) . "\n"
if ( $DEBUG );
if ( $seqID =~ /(.*)_\[(\d+)-(\d+)\]/ )
{
my $startPos = $2;
$annot->setQueryName( $1 );
$annot->setQueryStart( $annot->getQueryStart() + $startPos );
$annot->setQueryEnd( $annot->getQueryEnd() + $startPos );
$annot->setQueryRemaining(
$queryLengths{ $annot->getQueryName() } - $annot->getQueryEnd() );
print $annot->toStringFormatted( SearchResult::NoAlign ) . "\n"
if ( $DEBUG );
} else
{
die "Seqname $seqID is not in the valid format!\n";
}
}
undef $resIter;
#
# New Filter
#
my $searchIter = $searchResultCol->getIterator();
while ( $searchIter->hasNext() )
{
my $searchAnnot = $searchIter->next();
my $searchNeighIter = $searchIter->getIterator();
my $chainSeedScore = 0;
next
if ( defined $searchAnnot->getOverlap()
&& $searchAnnot->getOverlap() eq "u" );
# Determine if this annotation overlaps a previous seed.
if ( defined $reAlignRange->{'consensi'}->{ $searchAnnot->getSubjName() } )
{
foreach my $range (
@{ $reAlignRange->{'consensi'}->{ $searchAnnot->getSubjName() } } )
{
# check range against this annotation -- increasing seed
# score if overlaps and short circuiting foreach
if (
$searchAnnot->getOrientation() eq $range->{'orient'}
&& getOverlapSize(
$range->{'start'},
$range->{'end'},
$searchAnnot->getQueryStart(),
$searchAnnot->getQueryEnd()
) > 0
)
{
$chainSeedScore++;
last;
}
}
if ( $chainSeedScore > 0 )
{
$totalResultCollection->add( $searchAnnot );
$searchAnnot->setOverlap( "u" );
# Go left
my $leftIter = $searchIter->getIterator();
$leftIter->previous();
my $count = 0;
my $lastAnnot = $searchAnnot;
while ( $leftIter->hasPrevious() )
{
my $leftAnnot = $leftIter->previous();
next if ( $leftAnnot->getScore() < 300 );