forked from Computational-conSequences/SequenceTools
-
Notifications
You must be signed in to change notification settings - Fork 0
/
getRBH.pl
1521 lines (1474 loc) · 50.2 KB
/
getRBH.pl
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
## a little program to extract orthologs from a homologs file
## using the reciprocal best hits definition
## an example line is printed when no arguments are given
use strict;
use Getopt::Long;
use Pod::Text;
# to make temporary files/directories
use File::Temp qw( tempfile tempdir );
use sigtrap qw(handler signalHandler normal-signals);
my $columns = qx(tput cols);
chomp($columns);
my $width = $columns >= 100 ? 80 : $columns - 3;
my $parser = Pod::Text->new (sentence => 0, width => $width, margin => 1);
my $ownName = $0;
$ownName =~ s{.*/}{};
my $system = qx(uname -s);
chomp($system);
my %url = (
"blastp" => 'ftp://ftp.ncbi.nlm.nih.gov/blast/executables/LATEST/',
"diamond" => 'https://github.com/bbuchfink/diamond/releases',
"mmseqs" => 'https://github.com/soedinglab/MMseqs2/releases',
"lastal" => 'https://gitlab.com/mcfrith/last',
);
my @pwProgs = sort keys %url;
my $matchProg = join("|",@pwProgs);
my ($refavailable,$refmissing,$missMsg) = checkSoftware();
###### defaults, etc
my $cov1 = 30;
my $cov2 = 99;
my $defCov = 60;
my $defAln = "F";
my $defPW = 'diamond';
my $minmmseqs = 1;
my $maxmmseqs = 7;
my $diamondS = 'V';
my $diamondSl = 'very-sensitive';
my $mmseqsS = '5.7';
my $diamonV = "2.0.2";
my $defCPU = 4;
###### assignable:
my @queries = ();
my @against = ();
my $faaDir = '';
my $rbhDir = "RBH";
my $minCov = $defCov;
my $maxOverlap = 0.1; # maximum overlap in fused proteins/genes
my $maxEvalue = 1e-6;
my $alnSeqs = $defAln;
my $pwProg = $defPW;
my $pwDir = "compRuns";
my $sensitive = '';
my $runRBH = "T";
my $keepold = 'T';
my $topMatch = 0;
my $minTop = 1; # 30 was enough for lastal in one example
my $matchRatio = 7;
my $lengthsort = 'F';
my $logtime = 'F';
### check if there's more than one processor or assume there's $defCPU.
my $cpu_count
= qx(getconf _NPROCESSORS_ONLN 2>/dev/null)
=~ m{\s*(\d+)\s*} ? $1
: qx(sysctl -a 2>/dev/null | grep 'cpu.thread_count')
=~ m{\.cpu\.thread_count:\s+(\d+)} ? $1
: qx(sysctl -a 2>/dev/null | grep 'max-threads')
=~ m{\.max-threads\s+=\s+(\d+)} ? $1
: $defCPU;
my $cpus = $cpu_count >= $defCPU ? $defCPU : 2;
my $podUsage
= qq(=pod\n\n)
. qq(=head1 NAME\n\n)
. qq($ownName - compare proteomes and extract reciprocal best hits\n\n)
. qq(=head1 SYNOPSIS\n\n)
. qq($ownName -q [filename1.faa] -t [filename2.faa] [options]\n\n)
. qq(=head1 EXAMPLES\n\n)
. qq($ownName -q Genomes/GCF_000005845.faa.gz -t Genomes/GCF_000009045.faa.gz\n\n)
. qq($ownName -d Genomes -o AllvsAllRBH\n\n)
. qq(=head1 OPTIONS\n\n)
. qq(=over\n\n)
. qq(=item B<-q>\n\n)
. qq(query fasta file(s) or directory with fasta files, required.\n)
. qq(files can be compressed with gzip or bzip2.\n\n)
. qq(=item B<-t>\n\n)
. qq(target fasta file(s) or directory with fasta files, required.\n)
. qq(files can be compressed with gzip or bzip2.\n\n)
. qq(=item B<-d>\n\n)
. qq(directory with fasta files for all-vs-all comparisons, no default.\n)
. qq(If set -q and -t will be ignored.\n\n)
. qq(=item B<-o>\n\n)
. qq(directory for reciprocal best hits, default: RBH.\n\n)
. qq(=item B<-p>\n\n)
. qq(program for pairwise comparisons [$matchProg], default: $defPW\n\n)
. qq(=item B<-s>\n\n)
. qq(sensitivity (only works for diamond and mmseqs):\n\n)
. qq(=over\n\n)
. qq(=item B<F:>\n\nlow sensitivity: diamond: fast, mmseqs: -s 1\n\n)
. qq(=item B<S:>\n\ndiamond: sensitive, mmseqs: -s 2\n\n)
. qq(=item B<M:>\n\ndiamond: more-sensitive, mmseqs: -s 4\n\n)
. qq(=item B<V:>\n\ndiamond: very-sensitive, mmseqs: -s 5.7\n\n)
. qq(=item B<U:>\n\nhighest sensitivity: diamond: ultra-sensitive, mmseqs: -s $maxmmseqs\n\n)
. qq(=back\n\n)
. qq(for mmseqs the option will also accept numbers between $minmmseqs and $maxmmseqs,\n)
. qq(defaults: diamond: $diamondS; mmseqs: $mmseqsS\n\n)
. qq(=item B<-m>\n\n)
. qq(directory for $matchProg results, default compRuns.\n\n)
. qq(=item B<-c>\n\n)
. qq(minimum coverage of shortest sequence [$cov1 - $cov2], default $defCov.\n\n)
. qq(=item B<-f>\n\n)
. qq(maximum overlap between fused sequences [0 - 0.5], default 0.1\n)
. qq((10%) of shortest sequence.\n\n)
. qq(=item B<-e>\n\n)
. qq(maximum e-value, default $maxEvalue\n\n)
. qq(=item B<-l>\n\n)
. qq(sort files so that pairwise comparisons run against largest database [T|F], default $lengthsort\n\n)
. qq(=item B<-a>\n\n)
. qq(include aligned sequences in comparison results [T/F], default $defAln. (not available in lastal)\n\n)
. qq(=item B<-r>\n\n)
. qq(find RBH [T|F], default 'T', if 'F' the program will only run the\n)
. qq($matchProg comparisons\n\n)
. qq(=item B<-k>\n\n)
. qq(keep prior results [T|R|F], default 'T':\n\n)
. qq(=over\n\n)
. qq(=item B<F:>\n\nrepeat both alignments and gathering of RBH\n\n)
. qq(=item B<R:>\n\nonly repeat gathering of RBHs\n\n)
. qq(=item B<T:>\n\nkeep prior alignments and prior RBHs\n\n)
. qq(=back\n\n)
. qq(=item B<-z>\n\nmaximum number of targets to find with $matchProg\n)
. qq(minimum recommended is 50. Defaults to 1/${matchRatio}th of the\n)
. qq(sequences in the target file\n\n)
. qq(=item B<-x>\n\nnumber of CPUs to use, default: $cpus (max: $cpu_count)\n\n)
. qq(=item B<-n>\n\nnote time spent running pairwise comparisons (T|F), default: $logtime\n\n)
. qq(=back\n\n)
. qq(=head1 REQUIREMENTS\n\n)
. qq(This program requires either appropriately formatted\n)
. qq(comparison results for the query/target genomes, or\n)
. qq($matchProg to compare protein sequences\n\n)
. qq(=cut\n\n)
;
if( length($missMsg) > 0 ) {
$podUsage
.= qq(=head1 WARNING\n\n)
. qq(The following software is missing:\n\n)
. $missMsg;
}
GetOptions(
"q=s{,}" => \@queries,
"t=s{,}" => \@against,
"d=s" => \$faaDir,
"p=s" => \$pwProg,
"m=s" => \$pwDir,
"s=s" => \$sensitive,
"o=s" => \$rbhDir,
"c=f" => \$minCov,
"f=f" => \$maxOverlap,
"e=f" => \$maxEvalue,
"a=s" => \$alnSeqs,
"r=s" => \$runRBH,
"k=s" => \$keepold,
"z=i" => \$topMatch,
"x=i" => \$cpus,
"l=s" => \$lengthsort,
"n=s" => \$logtime,
) or podhelp();
if( !$faaDir && ( !$queries[0] || !$against[0] ) ) {
podhelp();
}
### check if the selected program works
if( $refmissing->{"$pwProg"} ) {
podhelp("$pwProg is missing");
}
### sorting by file length?
$lengthsort = $lengthsort =~ m{^(T|F)$}i ? uc($1) : 'F';
print "sorting by file length = $lengthsort\n";
### check if working with all-vs-all directory
my $allvsall = length($faaDir) > 0 ? 1 : 0;
if( $allvsall == 0 ) {
if( !$queries[0] || !$against[0] ) {
podhelp("if not -d I need both query and target files");
}
else {
####### check queries
my %qseen = ();
@queries = grep { not $qseen{"$_"}++ } @queries;
my $qtoFind = @queries;
if( -d $queries[0] && $qtoFind == 1 ) {
@queries = findFaaFiles("$queries[0]","query");
}
else {
@queries = findWorkFiles("query",@queries);
}
###### check targets
my %tseen = ();
@against = grep { not $tseen{"$_"}++ } @against;
my $stoFind = @against;
if( -d $against[0] && $stoFind == 1 ) {
@against = findFaaFiles("$against[0]","target");
}
else {
@against = findWorkFiles("target",@against);
}
}
}
else {
if ( -d "$faaDir" ) {
if( @queries = findFaaFiles("$faaDir","all vs all") ) {
@against = @queries;
}
}
else {
die "$faaDir doesn't exist or is not a directory\n\n";
}
}
my $pwProg = $pwProg =~ m{^($matchProg)$} ? lc($1) : $defPW;
if( $pwProg eq "lastal" && $alnSeqs eq "T" ) {
my $help
= qq($pwProg does not save sequence alignments, if you need\n)
. qq(the aligned sequences choose another program for pairwise\n)
. qq(comparisons, otherwise don't use '-a T'\n\n);
die "$help";
}
print "will compare proteins with $pwProg\n";
my $dmdmode = '';
if( $pwProg eq "diamond" ) {
$sensitive = $sensitive =~ m{^(F|S|M|V|U)$}i ? uc($1) : $diamondS;
$dmdmode
= $sensitive eq 'F' ? "fast"
: $sensitive eq 'S' ? "sensitive"
: $sensitive eq 'M' ? "more-sensitive"
: $sensitive eq 'V' ? "very-sensitive"
: $sensitive eq 'U' ? "ultra-sensitive"
: $diamondSl;
print "will run diamond in '$dmdmode' mode\n";
}
my $msmode = '';
if( $pwProg eq "mmseqs" ) {
$sensitive
= $sensitive =~ m{^(F|S|M|V|U)$}i ? uc($1)
: ( $sensitive >= $minmmseqs ) && ( $sensitive <= $maxmmseqs )
? $sensitive
: $mmseqsS;
print "testing $sensitive<-sensitive\n";
$msmode
= $sensitive eq 'F' ? "-s 1"
: $sensitive eq 'S' ? "-s 2"
: $sensitive eq 'M' ? "-s 4"
: $sensitive eq 'V' ? "-s 5.7"
: $sensitive eq 'U' ? "-s $maxmmseqs"
: ( $sensitive >= $minmmseqs ) && ( $sensitive <= $maxmmseqs )
? "-s $sensitive"
: "-s $mmseqsS";
print "will run mmseqs in '$msmode' mode\n";
}
my $minCov = $minCov >= $cov1 && $minCov <= $cov2 ? $minCov : $defCov;
print "minimum coverage of shortest sequence: $minCov\n";
my $maxOverlap
= $maxOverlap >= 0 && $maxOverlap <= 0.5
? $maxOverlap : 0.1;
print "maximum overlap for fusions: $maxOverlap\n";
my $alnSeqs = $alnSeqs =~ m{^(T|F)$}i ? uc($1) : $defAln;
print "include aligned seqs in $pwProg results: $alnSeqs\n";
my $cpus
= $cpus > 0 && $cpus <= $cpu_count ? $cpus
: $cpu_count >= $defCPU ? $defCPU
: 1;
print "uing $cpus cpu threads\n";
my $runRBH = $runRBH =~ m{^(T|F)$}i ? uc($1) : 'T';
if( $runRBH eq 'F' ) {
print "only pairwise comparisons will be run\n";
}
my $keepold = $keepold =~ m{^(T|F|R)$}i ? uc($1) : 'T';
if( $keepold eq 'T' ) {
print "will keep all previous results\n";
}
else {
if( $keepold eq 'R' ) {
print "will gather RBHs even if a RBH file exists\n";
}
else {
print "will make sequence comparisons and gather RBHs\n"
. " even if prior results exists\n";
}
}
$logtime = $logtime =~ m{^(T|F)$}i ? uc($1) : 'F';
my $time = '';
if( $logtime eq 'T' ) {
$time = $system eq 'Darwin' ? '/usr/bin/time -p' : 'time';
}
#### directories where to find files:
#### temporary working directory:
my $tempFolder = tempdir("/tmp/$ownName.XXXXXXXXXXXX");
##### heading for pairwise comparisons:
my @pwHeading = qw(
Query
Target
eValue
bitScore
pident
qStart
qEnd
qCover
tStart
tEnd
tCover
);
if( $alnSeqs eq "T" ) {
push(@pwHeading,"qSeq","tSeq");
}
my @rbhHeading = qw(
Query
Target
eValue
bitScore
pident
qStart
qEnd
qCover
tStart
tEnd
tCover
Qualifier
);
##### the table format below is more informative than the default
##### works for both blastp and diamond
my @pwTbl = qw(
qseqid
sseqid
evalue
bitscore
pident
qstart
qend
qlen
sstart
send
slen
);
##### add alignments to blast results table?
if( $alnSeqs eq "T" ) {
if( $pwProg eq "diamond" ) {
push(@pwTbl,"qseq","sseq");
}
else {
push(@pwTbl,"qseq","sseq");
}
}
my $pwTbl = join(" ","6",@pwTbl);
my $dmdTbl = $pwTbl;
$dmdTbl =~ s{qlen}{qcovhsp};
$dmdTbl =~ s{slen}{scovhsp};
##### table format for mmseqs:
my @mmfields = qw(
query
target
evalue
bits
pident
qstart
qend
qcov
tstart
tend
tcov
);
##### add alignments to mmseqs results table?
if( $alnSeqs eq "T" ) {
push(@mmfields,"qaln","taln");
}
my $mmfields = join(",",@mmfields);
my $blastOptions
= qq( -evalue $maxEvalue )
. qq( -seg yes )
. qq( -soft_masking true )
. qq( -comp_based_stats 0 )
. qq( -num_threads $cpus )
. qq( -outfmt '$pwTbl' );
# . qq( -parse_deflines )
my $diamondOptions
= qq( --evalue $maxEvalue )
. qq( --masking 0 )
. qq( --comp-based-stats 0 )
. qq( --threads $cpus )
. qq( --tmpdir $tempFolder )
. qq( -c 1 )
. qq( --quiet )
. qq( --outfmt $dmdTbl );
if( $dmdmode =~ m{sensitive} ) {
$diamondOptions = qq( --$dmdmode ) . $diamondOptions;
}
my $mmseqsOptions
= qq( -e $maxEvalue )
. qq( --comp-bias-corr 0 )
. qq( --threads $cpus )
. qq( --format-output "$mmfields" );
if( $msmode =~ m{s\s+\d} ) {
$mmseqsOptions = qq( $msmode ) . $mmseqsOptions;
}
#############################################################
################# running the RBH comparisons ###############
#############################################################
my $saveLog = "$pwDir/Logs/" . nakedName($queries[0]) . ".log";
my $tmpLog = "$tempFolder/log";
open( my $LOG,">","$tmpLog" );
my $maxKeep = 10;
my $kept = 0;
if( $allvsall > 0 ) {
my $totalfiles = @queries;
my $totalpairs = $totalfiles * ( $totalfiles + 1 ) / 2;
my $currentrun = 0;
##### by running these in reverse we ensure that
##### each database is formatted only once
TARGETAVA:
while( my $faaTarget = pop @queries ) {
print " checking target: $faaTarget\n";
my $cntTargets = checkFasta("$faaTarget");
my $maxAlns
= $topMatch >= $minTop ? $topMatch
: sprintf("%.0f",($cntTargets/$matchRatio));
if( $cntTargets < 1 ) {
$currentrun += @queries;
print {$LOG} "jumped empty file: $faaTarget\n";
print " jumping empty file: $faaTarget";
next TARGETAVA;
}
else {
for my $faaQuery ( @queries,$faaTarget ) {
$currentrun++;
print {$LOG}
"running ",
nakedName($faaQuery)," vs ",
nakedName($faaTarget),
" ($currentrun/$totalpairs runs)\n";
if( runPairWise("$faaQuery","$faaTarget","$maxAlns") ) {
if( $runRBH eq 'T' ) {
buildNrunRBH("$faaQuery","$faaTarget","F");
}
}
elsif( $runRBH eq 'T' ) {
buildNrunRBH("$faaQuery","$faaTarget",$keepold);
}
}
$kept++;
if( $kept >= $maxKeep ) {
cleanTMP();
$kept = 0;
}
}
}
print {$LOG} "\ndone comparing $totalfiles files for a total of\n"
."$totalpairs pairwise comparisons ($currentrun counted)\n\n";
}
else {
my $totalQs = @queries;
my $totalTs = @against;
my $totalpairs = $totalQs * $totalTs;
my $currentrun = 0;
##### by running these target-wise to try and ensure that
##### each database is formatted only once
TARGETQVA:
while( my $faaTarget = shift @against ) {
print " checking target: $faaTarget\n";
my $cntTargets = checkFasta("$faaTarget");
my $maxAlns
= $topMatch >= $minTop ? $topMatch
: sprintf("%.0f",($cntTargets/$matchRatio));
if( $cntTargets < 1 ) {
$currentrun += @queries;
print {$LOG} "jumped empty file: $faaTarget\n";
print " jumping empty file: $faaTarget";
next TARGETQVA;
}
else {
for my $faaQuery ( @queries ) {
$currentrun++;
print {$LOG}
"running ",
nakedName($faaQuery)," vs ",
nakedName($faaTarget),
" ($currentrun/$totalpairs runs)\n";
if( runPairWise("$faaQuery","$faaTarget","$maxAlns") ) {
if( $runRBH eq 'T' ) {
buildNrunRBH("$faaQuery","$faaTarget","F");
}
}
elsif( $runRBH eq 'T' ) {
buildNrunRBH("$faaQuery","$faaTarget",$keepold);
}
}
$kept++;
if( $kept >= $maxKeep ) {
cleanTMP();
$kept = 0;
}
}
}
print {$LOG} "\ndone comparing $totalQs vs $totalTs files for a total of\n"
."$totalpairs pairwise comparisons ($currentrun counted)\n\n";
}
close($LOG);
#### save logfile
saveLog();
##############################################################
######### finish
##############################################################
if( -d "$tempFolder" ) {
print " cleaning up\n";
system("rm -r $tempFolder");
}
print " Done with $ownName!\n\n";
#########################################################################
############################ subroutines ################################
#########################################################################
sub runPairWise {
my($faaQuery,$faaTarget,$maxAlns) = @_;
my $queryGnm = nakedName($faaQuery);
my $targetGnm = nakedName($faaTarget);
my $pwDB = $tempFolder . "/$targetGnm";
my $alnFile = $pwDir . "/$queryGnm/$targetGnm." . $pwProg . ".bz2";
my $alnBack = $pwDir . "/$targetGnm/$queryGnm." . $pwProg . ".bz2";
print {$LOG} "working with $queryGnm and $targetGnm\n";
### check if we have pairwise comparison results
### decide if this should run
if( -f "$alnFile" && $keepold =~ m{T|R} ) {
print "we already have an alignment file:\n $alnFile\n";
print {$LOG} "we already have an alignment file:\n $alnFile\n";
return();
}
elsif( -f "$alnBack" && $keepold =~ m{T|R} ) {
print "we already have an alignment file:\n $alnBack\n";
print {$LOG} "we already have an alignment file:\n $alnBack\n";
return();
}
else {
print "comparing sequences with $pwProg\n";
if( $pwProg eq "blastp" ) {
runBlastp("$faaQuery","$faaTarget","$alnFile","$maxAlns");
return(1);
}
elsif( $pwProg eq "diamond" ) {
runDiamond("$faaQuery","$faaTarget","$alnFile","$maxAlns");
return(1);
}
elsif( $pwProg eq "mmseqs" ) {
runMMseqs("$faaQuery","$faaTarget","$alnFile","$maxAlns");
return(1);
}
elsif( $pwProg eq "lastal" ) {
runLastal("$faaQuery","$faaTarget","$alnFile","$maxAlns");
return(1);
}
else {
print "no $pwProg program\n\n";
signalHandler();
}
}
}
sub buildNrunRBH {
my($faaQuery,$faaTarget,$keepold) = @_;
my $queryGnm = nakedName($faaQuery);
my $targetGnm = nakedName($faaTarget);
my $pwDB = $tempFolder . "/$targetGnm";
my $alnFile = $pwDir . "/$queryGnm/$targetGnm." . $pwProg . ".bz2";
my $alnBack = $pwDir . "/$targetGnm/$queryGnm." . $pwProg . ".bz2";
#########################################################################
######### reciprocal best hits
#########################################################################
my $qRBHdir = "$rbhDir/$queryGnm";
my $tRBHdir = "$rbhDir/$targetGnm";
my $qRBHfile = "$qRBHdir/$targetGnm.rbh.bz2";
my $tRBHfile = "$tRBHdir/$queryGnm.rbh.bz2";
if( -f "$qRBHfile" && -f "$tRBHfile" && $keepold eq "T" ) {
print join("\n ","there is RBH files already:"
,$qRBHfile,$tRBHfile),"\n";
}
else {
print "gathering reciprocal best hits\n";
## learn top homologs
print " learning top homologs\n";
##### first learn lines and their scores from query genome:
my (
$pairQuery,$pairTarget,
$pairBitSc,$pairEvalue,
$pairLine,$identStats
) = extractTop("$alnFile","$alnBack");
#### now sort, first bit-score (highest to lowest),
#### then E value (lowest to highest), then query, then target
my @query_lines = ();
my @query_pairs
= sort {
$pairBitSc->{"$b"} <=> $pairBitSc->{"$a"}
|| $pairEvalue->{"$a"} <=> $pairEvalue->{"$b"}
|| $pairQuery->{"$a"} <=> $pairQuery->{"$b"}
|| $pairQuery->{"$a"} cmp $pairQuery->{"$b"}
|| $pairTarget->{"$a"} <=> $pairTarget->{"$b"}
|| $pairTarget->{"$a"} cmp $pairTarget->{"$b"}
} keys %{ $pairQuery };
for my $pair ( @query_pairs ) {
push(@query_lines,$pairLine->{"$pair"});
}
#### now sort reciprocals
my @reciprocal_lines = ();
if( "$queryGnm" eq "$targetGnm" ) {
push(@reciprocal_lines,@query_lines);
}
else {
print " learning reciprocals\n";
my @pretend_reciprocal
= sort {
$pairBitSc->{"$b"} <=> $pairBitSc->{"$a"}
|| $pairEvalue->{"$a"} <=> $pairEvalue->{"$b"}
|| $pairTarget->{"$a"} <=> $pairTarget->{"$b"}
|| $pairTarget->{"$a"} cmp $pairTarget->{"$b"}
|| $pairQuery->{"$a"} <=> $pairQuery->{"$b"}
|| $pairQuery->{"$a"} cmp $pairQuery->{"$b"}
} keys %{ $pairQuery };
for my $pair ( @pretend_reciprocal ) {
my (
$query,$target,
$evalue,$bit_score,$pident,
$q_start,$q_end,$qcov,
$s_start,$s_end,$scov
) = split(/\t/,$pairLine->{"$pair"});
my $oppLine = join("\t",
$target,$query,
$evalue,$bit_score,$pident,
$s_start,$s_end,$scov,
$q_start,$q_end,$qcov
);
push(@reciprocal_lines,$oppLine);
}
}
###### now orthology
print " extracting orthologs\n";
###### making this into a subroutine to allow working both ways:
my $tmpQuery = $tempFolder . "/$queryGnm.$targetGnm.rbh.bz2";
produceRBH($tmpQuery,\@query_lines,\@reciprocal_lines,
$identStats);
if( -s "$tmpQuery" ) {
for my $checkDir ( "$rbhDir","$qRBHdir" ) {
unless( -d "$checkDir" ) {
mkdir("$checkDir");
}
}
system( "mv $tmpQuery $qRBHfile 2>/dev/null" );
}
if( "$queryGnm" ne "$targetGnm" ) {
my $tmpTarget = $tempFolder . "/$targetGnm.$queryGnm.rbh.bz2";
produceRBH($tmpTarget,\@reciprocal_lines,\@query_lines,
$identStats);
if( -s "$tmpTarget" ) {
for my $checkDir ( "$rbhDir","$tRBHdir" ) {
unless( -d "$checkDir" ) {
mkdir("$checkDir");
}
}
system( "mv $tmpTarget $tRBHfile 2>/dev/null" );
}
}
}
}
sub produceRBH {
my ($outFile,$rqLines,$rsLines,$ridentStats) = @_;
my $tmpFile = $outFile . ".tmp";
my %query_best_hits = ();
my %query_bitsc = ();
my %query_E_value = ();
my %init_target = ();
my %end_target = ();
my %print_line = ();
for my $line ( @{$rqLines} ) {
my ( $query,$target,
$evalue,$bit_score,$pident,
$q_start,$q_end,$qcov,
$s_start,$s_end,$scov
) = split(/\s+/,$line);
my $pair = join("\t",$query,$target);
my $print_line = join("\t",
$pair,
$evalue,$bit_score,$pident,
$q_start,$q_end,$qcov,
$s_start,$s_end,$scov
);
if( length($query_best_hits{"$query"}) > 0 ) {
if( $query_bitsc{"$query"} == $bit_score ) {
$query_best_hits{"$query"} .= "," . $target;
$print_line{"$pair"} = $print_line;
$init_target{"$pair"} = $s_start;
$end_target{"$pair"} = $s_end;
}
}
else {
$query_best_hits{"$query"} = $target;
$print_line{"$pair"} = $print_line;
$init_target{"$pair"} = $s_start;
$end_target{"$pair"} = $s_end;
$query_bitsc{"$query"} = $bit_score;
$query_E_value{"$query"} = $evalue;
}
}
#####
my %target_best_hits = ();
my %target_bitsc = ();
my %target_E_value = ();
for my $line ( @{$rsLines} ) {
my ( $query,$target,
$evalue,$bit_score,$pident,
$q_start,$q_end,$qcov,
$s_start,$s_end,$scov
) = split(/\s+/,$line);
my $pair = join("\t",$target,$query);
if( length $target_best_hits{"$query"} > 0 ) {
if( $target_bitsc{"$query"} == $bit_score ) {
$target_best_hits{"$query"} .= "," . $target;
}
}
else {
$target_best_hits{"$query"} = $target;
$target_bitsc{"$query"} = $bit_score;
$target_E_value{"$query"} = $evalue;
}
}
#####
my %orth = ();
my %share_this_hit = ();
##### sort the queries by bit score to automatically sort the
##### best hits by their bit scores (I guess)
my @queries = sort {
$query_bitsc{"$b"} <=> $query_bitsc{"$a"}
|| $query_E_value{"$a"} <=> $query_E_value{"$b"}
|| $a <=> $b
|| $a cmp $b
} keys(%query_best_hits);
##### now do the finding of orthologs
for my $query ( @queries ) {
for my $query_best_hit ( split(/\,/,$query_best_hits{"$query"}) ) {
for my $target_best_hit (
split(/\,/,$target_best_hits{"$query_best_hit"})
) {
## Reciprocal best hits:
if( $target_best_hit eq $query ) {
$orth{"$query"} .= ",$query_best_hit";
$orth{"$query"} =~ s/^\,+//;
}
else {
$share_this_hit{"$query_best_hit"} .= ",$query";
$share_this_hit{"$query_best_hit"} =~ s/^\,+//;
}
}
}
}
##### count printed lines (to ensure content)
my $printedOrths = 0;
open( my $ORTHS,"|-","bzip2 -9 >$tmpFile" );
print {$ORTHS} "#",join("\t",@rbhHeading),"\n";
###### print reciprocal best hits, and fusions:
for my $query ( sort { $a <=> $b || $a cmp $b } keys %orth ) {
ORTH:
for my $orth ( split(/,+/,$orth{"$query"}) ) {
#### print reciprocal best hit ortholog
my $pair = join("\t",$query,$orth);
my $type
= exists $ridentStats->{"$pair"}
? "Identical RBH"
: "RBH";
print {$ORTHS} join("\t",$print_line{"$pair"},$type),"\n";
$printedOrths++;
### find fusions from query to target by testing
### other queries that find the same target as their top
### hit, but not reciprocal
my @share_this_hit = split(/\,/,$share_this_hit{"$orth"});
my $shared = @share_this_hit;
next ORTH unless( $shared > 0 );
my ($i_query,$f_query)
= ($init_target{"$pair"},$end_target{"$pair"});
my $rbh_coords = join(":",$i_query,$f_query);
my @coords = ("$rbh_coords");
PARTNER:
for my $partner ( @share_this_hit ) {
my $fpair = join("\t",$partner,$orth);
#print $print_line{"$fpair"},"\n";
my $q_start = $init_target{"$fpair"};
my $q_end = $end_target{"$fpair"};
##### allowing a bit of overlap for fusions:
my $q_max_o
= sprintf("%.0f",$maxOverlap * ($q_end - $q_start));
COORDS:
for my $coords ( @coords ) {
my($cover_start,$cover_end) = split(/:/,$coords);
##### allowing a bit of overlap:
my $cover_max_o
= sprintf("%.0f",
$maxOverlap*($cover_end - $cover_start));
my $min_overlap
= $cover_max_o > $q_max_o ? ( -1 * $q_max_o )
: ( -1 * $cover_max_o );
my $overlap1 = $q_start - ( $cover_end + 1);
my $overlap2 = $cover_start - ( $q_end + 1);
#print "OVERLAPS: $overlap1, $overlap2, $min_overlap\n";
if( $overlap1 < $min_overlap
&& $overlap2 < $min_overlap ) {
next PARTNER;
}
#print "PASSED\n";
}
my $new_coords = join(":",$q_start,$q_end);
push(@coords,$new_coords);
if( $q_start < $i_query ) {
print {$ORTHS}
$print_line{"$fpair"}
,"\tLEFT of " . $query . "\n";
$printedOrths++;
}
else {
print {$ORTHS}
$print_line{"$fpair"}
,"\tRIGHT of " . $query . "\n";
$printedOrths++;
}
} # for partner
} # for orth
} # for query
close($ORTHS);
### rename resulting file, then check if it has content
### erase otherwise
rename($tmpFile,$outFile);
if( -z "$outFile" || $printedOrths == 0 ) {
print " found no orthologs\n";
unlink("$outFile");
}
}
sub nakedName {
my $inName = $_[0];
my $outName = $inName;
$outName =~ s{^\S+/}{};
$outName =~ s{\.(Z|gz|bz2)$}{};
$outName =~ s{\.faa\S*}{};
$outName =~ s{\.fasta\S*}{};
if( length($outName) > 0 ) {
return("$outName");
}
else {
print "there's a problem with $inName -> $outName\n";
return();
}
}
sub nameDB {
my $inName = $_[0];
my $outName = nakedName("$inName");
if( length($outName) > 0 ) {
return("$tempFolder/$outName");
}
else {
print "there's a problem with $inName -> $outName\n";
return();
}
}
sub signalHandler {
if( length($tempFolder) > 1 && -d "$tempFolder" ) {
saveLog();
print "\n\tcleaning up ...\n";
system "rm -r $tempFolder";
}
else {
print "\n\tquitting $ownName\n";
}
die "\tdone!\n\n";
}
sub how2open {
my $rootName = $_[0];
$rootName =~ s{\.(gz|bz2|Z)$}{};
my $fullName
= ( -f "$rootName.gz" ) ? "$rootName.gz"
: ( -f "$rootName.Z" ) ? "$rootName.Z"
: ( -f "$rootName.bz2" ) ? "$rootName.bz2"
: ( -f "$rootName" ) ? "$rootName"
: "none";
my $catProg
= $fullName =~ m{\.(gz|Z)$} ? "gzip -qdc"
: $fullName =~ m{\.bz2$} ? "bzip2 -qdc"
: "cat";
if( $fullName eq "none" ) {
return();
}
else {
return("$catProg","$fullName");
}
}
sub inflateFile {
my $origfile = $_[0];
my( $opener ) = how2open("$origfile");
my $rootName = nakedName("$origfile");
my $inflated = "$tempFolder/$rootName.faa";
unless( -f "$inflated" ) {
system("$opener $origfile > $inflated");
}
return("$inflated");
}
sub formatDB {
my($file,$dbfile,$dbType) = @_;
my($opener) = how2open("$file");
if( $dbType eq "blastp" ) {
if( -f "$dbfile.psq" ) {
print " the blast DB file is already there\n";
}
else {
print "producing blastDB: $dbfile\n";
my $mkblastdb
= qq($opener $file |)
. qq( makeblastdb )
. qq( -dbtype prot )
. qq( -title $dbfile )
. qq( -out $dbfile );
#. qq( -parse_seqids )
print {$LOG} "building db:\n$mkblastdb\n";
my $outdb = qx($mkblastdb 2>&1);
print {$LOG} "$outdb";
}
}
elsif( $dbType eq "diamond" ) {
if( -f "$dbfile.dmnd" ) {
print " the diamond DB file is already there\n";
}
else {
print "producing diamondDB: $dbfile\n";
my $mkdiamondDB
= qq($opener $file |)
. qq( diamond makedb -d $dbfile --quiet --threads $cpus );
system("$mkdiamondDB &>/dev/null");
print {$LOG} "building db:\n$mkdiamondDB\n";
my $outdb = qx($mkdiamondDB 2>&1);
print {$LOG} "$outdb";
}
}
elsif( $dbType eq "mmseqs" ) {
if( -f "$dbfile.index" ) {
print " the mmseqs DB file is already there\n";
}
else {
print "producing mmseqsDB: $dbfile\n";
#my $mkmmseqsDB
# = qq( mmseqs createdb $file $dbfile );
my $mkmmseqsDB
= qq( $opener $file | mmseqs createdb stdin $dbfile );
print {$LOG} "building db:\n$mkmmseqsDB\n";
my $outdb = qx($mkmmseqsDB 2>&1);
print {$LOG} "$outdb";
#seems like the idx files make mmseqs less sensitive
#print "producing $dbfile mmseqs index\n";
#my $mkIndex = qq( mmseqs createindex $dbfile $tempFolder );
#system("$mkIndex &>/dev/null");
}
}
elsif( $dbType eq "lastal" ) {
if( -f "$dbfile.prj" ) {
print " the lastal DB file is already there\n";
}
else {
print "producing lastalDB: $dbfile\n";
#= qq($opener $file | segmasker -outfmt fasta |)
#. qq( lastdb -p -P $cpus -c $dbfile );
my $mklastalDB
= qq($opener $file |)
. qq( lastdb -p -P $cpus $dbfile );
print {$LOG} "building db:\n$mklastalDB\n";
my $outdb = qx($mklastalDB 2>&1);
print {$LOG} "$outdb";
}