-
Notifications
You must be signed in to change notification settings - Fork 2
/
bb.motif
executable file
·750 lines (653 loc) · 23.8 KB
/
bb.motif
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
#!/usr/bin/perl
#----------------------------------------------------------#
# Author: Douglas Senalik [email protected] #
#----------------------------------------------------------#
# "Black Box" program series
=bb
Find a motif in one or more fasta sequences, and create
a summary report
=cut bb
# Version 1.0 - June 14, 2010
use strict;
use Getopt::Long; # for getting command line parameters
############################################################
# configuration variables
############################################################
my $defaulttempdir = "/tmp/";
my $bl2seq = "/usr/local/bin/blast-2.2.22/bin/bl2seq";
my $blastprogram = "blastn";
my $charmatch = "|";
my $charmismatch = "*";
my $charoutofmotif = " ";
my $charnomotif = "-";
my @validchars = ( 'A', 'C', 'G', 'T' );
my $dividerline = "----------\n\n";
############################################################
# global variables
############################################################
my $keeptempfiles = 0;
my @sequences = (); # array with each fasta sequence from input file as an element
my $tmpmotiffile = "";
my $tmpseqfile = "";
my $tmpblastfile = "";
my @startmotif = (); # flag for base 1 of motif in subject
my @stopmotif = (); # flag for last base of motif in subject
my $charmatchmeta = quotemeta($charmatch);
my $charmismatchmeta = quotemeta($charmismatch);
my @motifstats = (); # array of hashes for each letter seen
############################################################
# get command line parameters
############################################################
my $motif = "";
my $infile = ();
my $outfile = "";
my $tbl2asnfile = "";
my $tempdir = "";
my $expect = "10.0";
my $help = 0;
my $debug = 0;
# get command line options
GetOptions ("motif=s" => \$motif, # string
"infile=s" => \$infile, # string
"outfile=s" => \$outfile, # string
"tbl2asn=s" => \$tbl2asnfile, # string
"tempdir=s" => \$tempdir, # string
"expect=s" => \$expect, # string
"help" => \$help, # flag
"debug" => \$debug); # flag
############################################################
# print help screen
############################################################
unless ( ( $infile ) and ( $outfile ) and ( $motif ) ) { $help = 1; }
if ( $help )
{
print "This program will take one or more sequences in a FASTA
file, and look for your specified motif sequence in them.
Required parameters:
--motif=xxx nucleotide sequence of the motif to find
--infile=xxx name of input FASTA file, multiple allowed
--outfile=xxx name of summary file to create
Optional parameters:
--tbl2asnfile=xxx create a feature table for tbl2asn import
--tempdir=xxx save intermediate files in this directory.
If not specified, temporary files are not kept
--expect=xxx expect value for blast, default = $expect
--debug debugging mode=extra info printed, keep temp files
--help print this screen\n";
exit 1;
} # if ( $help )
############################################################
# initialize some variables
############################################################
print "Starting at ", timestr(), "\n";
if ( $tempdir )
{
# make sure trailing slash is present
unless ( $tempdir =~ m/\/$/ )
{ $tempdir .= "/"; }
unless ( -d $tempdir )
{ die "Error, temporary directory \"$tempdir\" does not exist or is not a directory"; }
$keeptempfiles = 1;
}
else
{ $tempdir = $defaulttempdir; }
if ( $debug ) { $keeptempfiles = 1; }
my $tmpprefix = $tempdir . "bb.motiffinder";
my $tmplog = $tmpprefix . ".log";
$tmpmotiffile = $tmpprefix . ".motif.tmp";
$tmpseqfile = $tmpprefix . ".subject.tmp";
$tmpblastfile = $tmpprefix . ".blastoutput.tmp";
############################################################
# read input file into memory
############################################################
my $numseq = 0;
open INP,"<$infile" or die "Error opening input file \"$infile\": $!\n";
while ( my $aline = <INP> )
{
$aline =~ s/[\r\n]//g;
if ( $aline =~ m/^>/ )
{
$numseq++;
$aline .= "\n";
}
$sequences[$numseq-1] .= $aline;
} # while <INP>
close INP;
if ( $numseq )
{ print "Loaded $numseq sequences from input file \"$infile\"\n"; }
else
{ die "Error, no sequences found in \"$infile\"\n"; }
############################################################
# create temporary file for motif
############################################################
$motif =~ s/[^ABCDGHKMNRSTVWYabcdghkmnrstvwy]//g; # remove all non-DNA characters
my $motiflen = length ( $motif );
print "Motif length is $motiflen\n";
my @motifarr = split ( //, "!" . $motif ); # we don't use array index [0]
( my $motifC = $motif ) =~ tr/AaCcTtGgMmRrYyKkVvHhDdBb/TtGgAaCcKkYyRrMmBbDdHhVv/;;
my @motifarrC = split ( //, "!" . $motifC );
unless ( $motif ) { die "Error, no motif has been defined\n"; }
open TMP,">$tmpmotiffile" or die "Error creating temporary motif file \"$tmpmotiffile\": $!\n";
print TMP ">Motif\n";
print TMP "$motif\n";
close TMP;
############################################################
# open output files
############################################################
open OUT,">$outfile" or die "Error creating output file \"$outfile\": $!\n";
print OUT "MotifFinder analysis using motif \"$motif\", length=$motiflen\n";
print OUT "Numbers after each motif represent\n";
print OUT "Number of matches to this motif ; Number of gaps on motif side ; Number of gaps on subject side / Length of motif found\n";
print OUT $dividerline;
if ( $tbl2asnfile )
{ open SEQ,">$tbl2asnfile" or die "Error creating tbl2asn output file \"$tbl2asnfile\": $!\n"; }
############################################################
# loop for each sequence in input file
############################################################
foreach my $inseq ( @sequences )
{
@startmotif = ();
@stopmotif = ();
my $foundany = 0;
my ( $header, $seq ) = split ( /\n/, $inseq ); # all other returns were already stripped
$header =~ s/^>//;
$seq =~ s/[^ABCDGHKMNRSTVWYabcdghkmnrstvwy]//g; # remove all non-DNA characters
my @seqarr = split ( //, "!" . $seq ); # we won't use array index [0]
my @matcharr = ( "!" );
# create temporary input file with sequence
open TMP,">$tmpseqfile" or die "Error creating temporary sequence file \"$tmpseqfile\": $!\n";
print TMP ">", $header, "\n";
print TMP $seq, "\n";
close TMP;
# run blast2seq
my $cmd = $bl2seq;
$cmd .= " -i \"$tmpmotiffile\"";
$cmd .= " -j \"$tmpseqfile\"";
$cmd .= " -p \"$blastprogram\"";
$cmd .= " -o \"$tmpblastfile\"";
$cmd .= " -e \"$expect\"";
$cmd .= " -D 0"; # output format traditional
$cmd .= " -F F"; # filter off
$cmd .= " -G -1"; # gap open penalty
$cmd .= " -E -1"; # gap extension penalty
$cmd .= " -q -3"; # penalty for mismatch default -3
$cmd .= " -r 2"; # reward for match default 1
my $result = system ( $cmd );
if ( $result ) { die "Error $result running \"$cmd\"\n"; }
# print header in output file for this sequence
print OUT "Analysis of \"$header\"\n";
# parse results
my $qpos1 = 0;
my $qpos2 = 0;
my $qseq = "";
my $qseqlen = 0;
my @qarr = ();
my @qgaps = ();
my $qdirection = 0;
my $spos1 = 0;
my $spos2 = 0;
my @sarr = ();
my @sgaps = ();
my $sseq = "";
my $sseqlen = 0;
my $sdirection = 0;
my @midx = (); # motif index
my @mor = (); # motif orientation, 1 forward, -1 reverse
my $linenum = 0;
open TMP,"<$tmpblastfile" or die "Error opening blast output file \"$tmpblastfile\": $!\n";
while ( my $aline = <TMP> )
{
if ( $debug ) { print $aline; }
$linenum++;
$aline =~ s/[\r\n]//g;
# parse Query: line
if ( $aline =~ m/^Query:\s+(\d+)\s+(.+)\s+(\d+)/ )
{
$qpos1 = $1;
$qpos2 = $3;
$qseq = $2;
$qseqlen = length( $qseq );
if ( $qpos2 < $qpos1 )
{ $qdirection = -1; }
else
{ $qdirection = 1; }
$foundany = 1;
} # if ( $aline =~ m/^Query/ )
# parse Sbjct: line
if ( $aline =~ m/^Sbjct:\s+(\d+)\s+(.+)\s+(\d+)/ )
{
$spos1 = $1;
$spos2 = $3;
$sseq = $2;
$sseqlen = length( $sseq );
if ( $spos2 < $spos1 )
{ $sdirection = -1; }
else
{ $sdirection = 1; }
if ( $qdirection == -1 ) { print "query is RC\n"; }
if ( $sdirection == -1 ) { print "sbjct is RC\n"; }
# look at each character and either store base or store a gap
my $qindex = $qpos1; # storage location index
my $sindex = $spos1; # storage location index
for ( my $i=0; $i<$sseqlen; $i++ )
{
# motifindex
$midx[$sindex] = $qindex;
##print "Motif index for $sindex set to $qindex\n";
# QUERY ( = motif )
my $qletter = substr ( $qseq, $i, 1 );
if ( $qletter =~ m/[A-Za-z]/ )
{
##print "store q $qletter at $sindex\n";
$qarr[$sindex] = $qletter; # note use of $sindex here
$qindex += $qdirection;
}
elsif ( $qletter eq "-" )
{
##print "Query gap at $i\n";
if ( $qdirection > 0 )
{ $qgaps[$qindex-1]++; }
else
{ $qgaps[$qindex]++; }
}
else
{ die "Invalid query letter \"$qletter\" line $linenum:\"$aline\"\n"; }
# SBJCT ( = sequence being analyzed )
my $sletter = substr ( $sseq, $i, 1 );
if ( $sletter =~ m/[A-Za-z]/ )
{
##print "store s $sletter at $sindex\n";
$sarr[$sindex] = $sletter;
$sindex += $sdirection;
}
elsif ( $sletter eq "-" )
{
if ( $sdirection > 0 )
{ $sgaps[$sindex-1]++; }
else
{ $sgaps[$sindex]++; }
}
else
{ die "Invalid sbjct letter \"$sletter\" line $linenum:\"$aline\"\n"; }
# save orientation
$mor[$sindex] = ( $qdirection * $sdirection );
} # for
} # if ( $aline =~ m/^Sbjct/ )
} # while <TMP>
close TMP;
# extrapolate motif index on each end.
# first do lower numbers, then on a second pass do higher numbers
my $prevval = 0;
my $prevor = 0;
for ( my $i=$#seqarr; $i>=1; $i-- )
{
if ( ( $prevval > 1 ) and ( $prevval < $motiflen ) and ( ! $midx[$i] ) )
{
my $tmp = ( $prevval - $prevor );
if ( $midx[$i-1] != $tmp ) { $midx[$i] = $tmp; }
$mor[$i] = $prevor;
if ( $debug ) { print "Extrapolating motif down, $midx[$i] at $i orient=$prevor\n"; }
}
$prevval = $midx[$i];
if ( $mor[$i] != 0 ) { $prevor = $mor[$i]; }
} # for $i
$prevval = 0;
for ( my $i=1; $i<=$#seqarr; $i++ )
{
if ( ( $prevval > 1 ) and ( $prevval < $motiflen ) and ( ! $midx[$i] ) )
{
my $tmp = ( $prevval + $prevor );
if ( $midx[$i+1] != $tmp ) { $midx[$i] = $tmp; }
$mor[$i] = $prevor;
if ( $debug ) { print "Extrapolating motif up, $midx[$i] at $i orient=$prevor\n"; }
}
$prevval = $midx[$i];
if ( $mor[$i] != 0 ) { $prevor = $mor[$i]; }
} # for $i
# find elements
if ( $tbl2asnfile )
{
my @left = ();
my @right = ();
my $inelement = 0;
my $previdx = 0;
for ( my $i=1; $i<=$#seqarr; $i++ )
{
if ( $inelement )
{
if ( $midx[$i] )
{
# only do anything at border
if ( abs ( $previdx - $midx[$i] ) > 3 )
{
push ( @right, $i-1 );
push ( @left, $i );
}
$previdx = $midx[$i];
}
else
{
$inelement = 0;
push ( @right, $i-1 );
}
}
else
{
if ( $midx[$i] )
{
$inelement = 1;
$previdx = $midx[$i];
push ( @left, $i );
}
}
} # for $i
if ( $inelement ) { push ( @right, $#seqarr ); }
if ( scalar @left )
{
# header must only be identifier, right trim after first space
my $tmphdr = $header;
$tmphdr =~ s/ .*$//;
print SEQ ">Feature ", $tmphdr, "\n";
for ( my $i=0; $i<=$#left; $i++ )
{
print SEQ "$left[$i]\t$right[$i]\trepeat_region\t\t\n";
print SEQ "\t\t\tnote\tCent-Dc repeat element\n";
}
}
} # if ( $tbl2asnfile )
if ( $foundany )
{
# print the output, in 3-line format when motif present, 1-line when absent
my $o1 = " 1 ";
my $o2 = " ";
my $o3 = " ";
my $linelen = 0;
my $inmotif = 0;
my $motifmatch = 0;
my $motifmismatch = 0;
my $motiforient = 0; # +1 for forward (same as sbjct), -1 for reverse, 0 for no motif here
my $prevmotiforient = 0;
my $prevmidx; # for finding orientation in $motiforient
for ( my $i=1; $i<=$#seqarr; $i++ )
{
if ( $debug and 0 )
{ print "\$i=$i \$seqarr[$i]=\"$seqarr[$i]\" ",
"\$sarr[$i]=\"$sarr[$i]\" ",
"\$qarr[$i]=\"$qarr[$i]\" ",
"\$sgaps[$i]=\"$sgaps[$i]\" ",
"\$qgaps[$i]=\"$qgaps[$i]\" ",
"\$midx[$i]=\"$midx[$i]\"\n"; }
# determine motif orientation
$motiforient = $mor[$i];
# summary statistics for motif letters observed
if ( $midx[$i] )
{
##print "Store at index $i letter $seqarr[$i] motif index $midx[$i]\n";
$motifstats[$midx[$i]]->{$seqarr[$i]}++;
}
$o1 .= $seqarr[$i];
my $tmp = " ";
if ( $midx[$i] )
{
if ( $mor[$i] < 0 )
{ $tmp = $motifarrC[$midx[$i]]; }
else
{ $tmp = $motifarr[$midx[$i]]; }
}
$o3 .= $tmp;
# show matches between motif and sequence
if ( $seqarr[$i] =~ m/^$tmp$/i )
{ $o2 .= $charmatch; $motifmatch++; }
elsif ( $midx[$i] )
{ $o2 .= $charmismatch; $motifmismatch++; }
else
{ $o2 .= $charoutofmotif; }
$linelen++;
# add gaps in sequence
if ( $sgaps[$i] )
{
if ( $debug ) { print "Adding sbjct gap len=$sgaps[$i] at $i\n"; }
##print "Adding sbjct gap len=$sgaps[$i] at $i \n";
for ( my $j=0; $j<$sgaps[$i]; $j++ )
{
$o1 .= "-";
$o2 .= $charmismatch;
my $tmp = " ";
if ( $midx[$i] )
{
if ( $mor[$i] < 0 )
{ $tmp = $motifarrC[$midx[$i+$j] - 1]; }
else
{ $tmp = $motifarr[$midx[$i+$j] + 1]; }
}
##print "i $i j $j motif index $midx[$i+$j] Added $tmp\n";
$o3 .= $tmp;
$linelen++;
}
} # add gaps
if ( 0 ) {
# add gaps in motif (query)
if ( $qgaps[$i] )
{
if ( $debug ) { print "Adding query gap len=$qgaps[$i] at $i\n"; }
for ( my $j=0; $j<$qgaps[$i]; $j++ )
{
$o3 .= " ";
$o2 .= "^";
my $tmp = "#";
$o1 .= $tmp;
$linelen++;
}
} # add gaps
}
# line break rules
my $break = 0;
# old motif ends and new one starts
if ( $motiforient == 1 )
{
if ( $midx[$i] > $midx[$i+1] ) { $break = 1; }
}
if ( $motiforient == -1 )
{
if ( $midx[$i] < $midx[$i+1] ) { $break = 1; }
}
# no motif, line length over limit
if ( $linelen >= 60 ) { $break = 1; }
# new motif starts after no motif, and existing sequence ( > 5 bp ) on line
if ( ( $linelen >= 5 ) and ( $midx[$i+1] ) and ( ! $midx[$i] ) ) { $break = 1; }
# motif ends and no new one starts
if ( ( ! $midx[$i+1] ) and ( $midx[$i] ) ) { $break = 1; }
# don't break for short lines
if ( $linelen < 5 ) { $break = 0; }
if ( $break )
{
print OUT $o1, "\n";
##if ( $o3 ) { print "\"$o3\" eval to true\n"; } else { print "\"$o3\" eval to false\n"; }
unless ( $o3 =~ m/^\s*$/ )
{
print OUT $o2, "\n";
$o3 =~ s/^ /Motif/;
print OUT $o3, calcscore($o1,$o2,$o3,$motiforient), "\n";
}
print OUT "\n";
$o1 = sprintf ( "%5d ", $i+1 ); # + 1 because will be for next loop
$o2 = " ";
$o3 = " ";
$linelen = 0;
}
$prevmidx = $midx[$i];
$prevmotiforient = $motiforient;
} # for
# print anything leftover at the end
if ( $linelen )
{
print OUT $o1, "\n";
unless ( $o3 =~ m/^\s*$/ )
{
print OUT $o2, "\n";
if ( $o3 ) { $o3 =~ s/^ /Motif/; }
print OUT $o3, calcscore($o1,$o2,$o3,$prevmotiforient), "\n";
}
}
} # if ( $foundany )
else
{ print OUT "No motifs found in this sequence\n"; }
# cleanup temporary files from this loop
unlink $tmpseqfile;
unlink $tmpblastfile;
print OUT $dividerline;
} # foreach my $inseq ( @sequences )
############################################################
# motif statistics
############################################################
print OUT "Motif Summary Statistics\n";
print OUT "\n";
# print a header for each column
print OUT "Position Motif";
my @pct = @validchars;
foreach ( @pct ) { s/^/% /; }
foreach my $base ( @validchars, "Total", @pct, " %Motif" )
{ print OUT sprintf ( " %5s", $base ); }
print OUT "\n";
for ( my $i=1; $i<=$#motifarr; $i++ )
{
print OUT sprintf ( "%6d %6s ", $i, $motifarr[$i] );
my $total = 0;
foreach my $base ( @validchars )
{
print OUT sprintf ( " %5d", $motifstats[$i]->{$base} );
$total += $motifstats[$i]->{$base};
}
print OUT sprintf ( " %5d", $total );
my $highest = 0;
my $highestltr = "";
foreach my $base ( @validchars )
{
my $pct = ( $motifstats[$i]->{$base} * 100 / $total );
print OUT sprintf ( " %5.1f", $pct );
if ( $pct > $highest )
{
$highest = $pct;
$highestltr = $base;
}
}
print OUT sprintf ( " %5.1f", $highest ), "%", $highestltr;
if ( $highestltr ne $motifarr[$i] ) { print OUT " DIFFERENT FROM MOTIF"; }
print OUT "\n";
} # for
############################################################
# close output file and cleanup
############################################################
if ( $tbl2asnfile ) { close SEQ; }
close OUT;
unlink ( $tmpmotiffile );
print "Program finished at ", timestr(), "\n";
exit 0;
############################################################
sub calcscore { my ( $o1, $o2, $o3, $orient ) = @_;
############################################################
my $matches = 0;
my $mismatches = 0;
my $qgaps = 0;
my $sgaps = 0;
while ( $o1 =~ m/-/g ) { $sgaps++; }
while ( $o2 =~ m/$charmatchmeta/g ) { $matches++; }
while ( $o2 =~ m/$charmismatchmeta/g ) { $mismatches++; }
while ( $o3 =~ m/-/g ) { $qgaps++; }
my $tmp = " " . $matches . ";" . $qgaps . ";" . $sgaps . "/" . ( $matches + $mismatches );
if ( $orient == 1 )
{ $tmp .= ""; }
elsif ( $orient == -1 )
{ $tmp .= " Reverse Complement"; }
else
{ $tmp .= " ERR"; }
return $tmp;
} # sub calcscore
###############################################################
sub timestr
###############################################################
{
@_ = localtime(shift || time);
return(sprintf("%04d/%02d/%02d %02d:%02d", $_[5]+1900, $_[4]+1, $_[3], @_[2,1]));
} # sub timestr
###############################################################
sub commify
###############################################################
# http://perldoc.perl.org/perlfaq5.html#How-can-I-output-my-numbers-with-commas$
{
local $_ = shift;
1 while s/^([-+]?\d+)(\d{3})/$1,$2/;
return $_;
} # commify
############################################################
sub revcomp { my ( $dna ) = @_;
############################################################
# standard DNA reverse complement, including degenerate bases
my $revcomp = reverse ( $dna );
$revcomp =~ tr/AaCcTtGgMmRrYyKkVvHhDdBb/TtGgAaCcKkYyRrMmBbDdHhVv/;
return $revcomp;
} # sub revcomp
############################################################
sub debugmsg { my ( $text, $noreturn, $nolinenum ) = @_;
############################################################
if ( $debug )
{
my ($package, $filename, $line, $sub) = caller(0);
unless ( $nolinenum ) { $text = "Line $line: " . $text; }
if ( ! ( $noreturn ) ) { $text .= "\n"; }
print $text;
} # if ( $debug )
} # sub debugmsg
# for reference purposes
=pod
bl2seq 2.2.22 arguments:
-i First sequence [File In]
-j Second sequence [File In]
-p Program name: blastp, blastn, blastx, tblastn, tblastx. For blastx 1st sequence should be nucleotide, tblastn 2nd sequence nucleotide [String]
-g Gapped [T/F]
default = T
-o alignment output file [File Out]
default = stdout
-d theor. db size (zero is real size) [Real]
default = 0
-a Text ASN.1 output file [File Out] Optional
-G Cost to open a gap (-1 invokes default behavior) [Integer]
default = -1
-E Cost to extend a gap (-1 invokes default behavior) [Integer]
default = -1
-X X dropoff value for gapped alignment (in bits) (zero invokes default behavior)
blastn 30, megablast 20, tblastx 0, all others 15 [Integer]
default = 0
-W Word size, default if zero (blastn 11, megablast 28, all others 3) [Integer]
default = 0
-M Matrix [String]
default = BLOSUM62
-q Penalty for a nucleotide mismatch (blastn only) [Integer]
default = -3
-r Reward for a nucleotide match (blastn only) [Integer]
default = 1
-F Filter query sequence (DUST with blastn, SEG with others) [String]
default = T
-e Expectation value (E) [Real]
default = 10.0
-S Query strands to search against database (blastn only). 3 is both, 1 is top, 2 is bottom [Integer]
default = 3
-T Produce HTML output [T/F]
default = F
-m Use Mega Blast for search [T/F] Optional
default = F
-Y Effective length of the search space (use zero for the real size) [Real]
default = 0
-t Length of the largest intron allowed in tblastn for linking HSPs [Integer]
default = 0
-I Location on first sequence [String] Optional
-J Location on second sequence [String] Optional
-D Output format: 0 - traditional, 1 - tabular [Integer]
default = 0
-U Use lower case filtering for the query sequence [T/F] Optional
default = F
-A Input sequences in the form of accession.version [T/F]
default = F
-V Force use of the legacy BLAST engine [T/F] Optional
default = F
=end