-
Notifications
You must be signed in to change notification settings - Fork 0
/
micpdp.pl
4074 lines (3332 loc) · 112 KB
/
micpdp.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 -w
use strict;
use Getopt::Std;
use File::Basename;
use Storable;
use Cwd 'abs_path';
my $script_path;
BEGIN {
$script_path = dirname(abs_path($0));
}
use lib $script_path;
use My_micPDP qw(&get_codon_pos_index dnds);
my $version='0.99.11';
my $usage= qq{
micPDP v$version
\nUsage: $0 -m multiple_alignment_file -s species_list -l min_orf_len -c chromosome -r annotation_files
[options]:
m multiple species alignment file in fasta format
r annotation files in ucsc table format
n non-coding gene annotations
c chromosome that is currently processed
l mininum orf length; default 27 nt = 9 AA
s list of species in maf according to phylogenetic tree
t output dir in subfolder projects
S ignore strand when checking for overlap with annotation files
b bed file with 12 coloumns so a maf file is not needed anymore, option -B and -b are mutually exclusive
[additional options]:
F mount point to folder 'ucsc' at which all maf files and indices are located
E exon mode - supply this option if you want only look for conservation in your exons bed file supplied by option -b
M maximum allowed length of an orf; default 300 nt = 100 AA
W set window size which is used when calculating entropies in neighboring regions; default ORF length
A output all orfs found and abort
R skip reapeat masked regions, only works if lower case letters in MAF file are repeats
N File with snps if these files are present
P path to reference sequence edits so we can filter out species that have frameshift mutations
G if given then gaps in the beginning and end of an alignment are corrected, default off since buggy still
T sequence is allowed to have this fraction of gaps, default is 0
B bed file with transcripts informing us about codon start positions --- must be used with option Y, otherwise there will be no effect !
K circular mode on genome, needs a 12 column bed file where CDS (c6 and c7) correspond to the circle in question
k print full exon alignment , only useful for circmode !
Y for Ka/Ks calc we ignore codons with gaps, more fair I think - On by default
y we return 1 for each codon substitution and not the hamming distance
X score also with phyloCSF
x mincodon number to have for scoring with phylocsf
v verbose mode
F disable flank scoring
q look also for ORFs on antisense strand
to get all orfs use -A -S
};
die $usage if(not $ARGV[0]);
my %options=();
getopts("F:c:m:i:j:a:s:z:l:r:EM:W:n:o:I:t:SRO:AP:GT:b:Kk:YyB:X:x:vFDC:Q:Jq",\%options);
checkopts(%options);
## change this value to whereever BIO2 is mounted
## can be done on command line by specifying option 'F'
my $ucsc_mount_point='/scratch/local/ucsc/';
if($options{'F'}){
$ucsc_mount_point=$options{'F'};
}
my %ii;
my @l;
my @iib;
if($options{'P'}){
open IN,"$options{'P'}/$options{'c'}.maf.index.sorted.i2" or die "Index file $options{'P'}/$options{'c'}.maf.index.sorted.i2 for index not given\n";
while(<IN>){
chomp;
if(/\#/){
$ii{0}=1;
push(@iib,0);
next;
}
@l=split();
$ii{$l[0]}=$l[1];
push(@iib,$l[0]);
}
close IN;
}
# open my $iif,"$options{'P'}/$options{'c'}.maf.index.sorted" or die "index file could not be opened\n";
# my $res=binarysearch2(\@iib,$pos_to_go);
# my $hi=$iib[$res];
# my $pos=$ii{$hi};
# seek $iif,$pos,0;
print STDERR "
#########################################################################
# micPep - microPeptide detection tool
# Version: $version
# Date: 16-12-2019
# Author: Sebastian Mackowiak
# Email: sd.mackowiak\@gmail.com
#
#########################################################################
";
## phylocsf parameters
my $currentgene;
my $phylo="$ucsc_mount_point/PhyloCSF";
my $param_phylo;
if($options{'s'} =~ /mm10/){
$param_phylo="mouse60";
}elsif($options{'s'} =~ /mm9/){
$param_phylo="mouse29";
}elsif($options{'s'} =~ /ce6/){
$param_phylo="elegans";
}elsif($options{'s'} =~ /dr7/){
$param_phylo="zebrafish";
}elsif($options{'s'} =~ /dm3/){
$param_phylo="15flies";
}elsif($options{'s'} =~ /mm10/){
$param_phylo="mouse60";
}else{
$param_phylo="46vertebrates";
}
#$options{'Y'} =1;
#$options{'y'} =1;
#die $usage if(not $options{'m'} and not $options{'b'});
use POSIX qw/strftime/;
print STDERR "#\n#start\t", strftime("%d-%m-%Y\t%T",localtime),"\n#\n###########################################\n\n";
## fraction of gaps allowed in sequence
my $gapthreshold=0;
$gapthreshold=$options{'T'} if($options{'T'});
my $mincodons=8;
$mincodons=$options{'x'} if($options{'x'});
## get information about CDS files if options{'C'} is given
my %cdsinfo=();
my $id;
if($options{'Q'}){ ## change this back to C when bugfixed
if(-f $options{'C'}){
open IN,$options{'C'} or die "File $options{'C'} could not be opened\n";
while(<IN>){
chomp;
@l=split();
next if($l[0] ne $options{'c'});
## this pattern match is for ensemble genes only, adapt when using refseq or sth else
$id=$l[1];
$cdsinfo{$id}{'start'}=$1 if($l[2] =~ /(\d)/);
$cdsinfo{$id}{'end'}=$1 if($l[3] =~ /(\d)/);
$cdsinfo{$id}{'len'}=$1 if($l[4] =~ /(\d)/);
$cdsinfo{$id}{'offset'}=$1 if($l[5] =~ /(\d)/);
$cdsinfo{$id}{'startX'}=$1 if($l[6] =~ /(\d)/);
$cdsinfo{$id}{'startshift'}=$1 if($l[7] =~ /(\d)/);
$cdsinfo{$id}{'endshift'}=$1 if($l[8] =~ /(\d)/);
$cdsinfo{$id}{'no-cdsf'}=$1 if($l[9] =~ /(\d)/);
$cdsinfo{$id}{'bonafide'}=$1 if($l[10] =~ /(\d)/);
}
close IN;
}
}
my $kaks_table=retrieve("$script_path/kaks_synmut.perlhash_storable");
my $kaks=$kaks_table;
## read in order of species in MAF
my @species;
lines_to_array($options{'s'},\@species);
my ($chr,$start,$len,$strand,$ms);
$ms=$species[0]; ## this is our reference species
$chr=$options{'c'};
my @selected;
my $hg19="$ucsc_mount_point/hg19/maf/";
my $hg19e=".maf.stitched.cmpl.repeats_lc";
my $ce6="$ucsc_mount_point/ucsc/celegans/stitched_mafs/";
my $ce6e=".stitched.cmpl.repeats_lc";
my $ce10="$ucsc_mount_point/ucsc/celegans/ws220_stitched_mafs/";
my $ce10e=".maf.stitched.cmpl.r";
my $dm3="$ucsc_mount_point/ucsc/dm3/stitched_mafs/";
my $dm3e=".stiched.cmpl.repeats_lc";
my $dr7="$ucsc_mount_point/ucsc/zebrafish/maf/splitup_blocks/";
my $dr7e=".maf.stitched.cmpl.repeats_lc";
my $mm9="$ucsc_mount_point";
my $mm9e=".maf.stitched.cmpl.repeats_lc.r";
my $mm10="$ucsc_mount_point/ucsc/mm10/mafs_ucsc/";
my $mm10e=".maf.stitched.cmpl.repeats_lc.r";
my ($msb,$mse,$sf,$sf2);
#if($ARGV[5]){$msb="$ARGV[5]/"}else{
if($ms eq 'hg19' or $ms eq 'hsa'){
$msb=$hg19;
}elsif($ms eq 'ce6' or $ms eq 'cel'){
$msb=$ce6;
}elsif($ms eq 'ce10'){
$msb=$ce10;
}elsif($ms eq 'dm3' or $ms eq 'dme'){
$msb=$dm3;
}elsif($ms eq 'dr7' or $ms eq 'danRer7'){
$msb=$dr7;
}elsif($ms eq 'mm9'){
$msb=$mm9;
}elsif($ms eq 'mm10'){
$msb=$mm10;
}else{
die "species not found\n";
}
if ($ms eq 'hg19') {
$mse=$hg19e;
$sf="$msb/hg19_species";
} elsif ($ms eq 'ce6') {
$mse=$ce6e;
$sf="$msb/ce6_species";
} elsif ($ms eq 'ce10') {
$mse=$ce10e;
$sf="$msb/ce10_species_ucsc_order";
} elsif ($ms eq 'dm3') {
$mse=$dm3e;
$sf="$msb/insect_species";
} elsif ($ms eq 'dr7' or $ms eq 'danRer7') {
$mse=$dr7e;
$sf="$msb/dr7_species";
} elsif ($ms eq 'mm9') {
$mse=$mm9e;
$sf="$msb/mm9_spec.reordered";
} elsif ($ms eq 'mm10') {
$mse=$mm10e;
$sf="$msb/mm10_species.reordered";
} else {
die "Species $ms is not valid\n";
}
if(-f $options{'m'}){
open MAF,'<',$options{'m'};
}else{
if(not -f "$msb$chr$mse"){ print STDERR "file $msb$chr$mse maf file not found\nskipping\n";exit;}
open MAF,"$msb$chr$mse" or die "maf file $msb$chr$mse not found\n";
}
my $fh=*MAF;
my ($refl,$end,$offset,$lenseq);
my $dmp;
while (<MAF>) {
if (/>[a-zA-Z0-9]+.$chr+\(\S\):(\d+)-(\d+)/) {
$offset=$1;
$end=$2;
$lenseq=$end-$offset;
$refl=length($_);
last;
} else {
die "pattern not matched $_\n";
}
}
my $length_chr=$end;
my %spec=();
open IN,$sf or die "species file $sf not found\n";
my @dmp;
my $mult=-1;
my $specl;
my $seql=0;
my $first=1;
my $s='';
my @species2;
my $origs;
my $real;
while (<IN>) {
if (/(\S+)/) {
if($ms =~ /mm\d/){
my $d=$_;
chomp $d;
if($d =~ /^(\S+)\s*(\S*)/){
$origs=$1;
$real=$2;
}
if ($ms ne 'mm10') { ## so it is mm9
$d=~ s/\s+/:/g;
} else {
if($real){
$d.=":";
}
}
$mult++;
$s="$origs:$real";
push(@species2,$origs);
if ($first) {
$first=0;
$specl+=$refl;
} else {
$specl+=length($s)+2;
$seql+=$lenseq+1;
}
$spec{$origs}=$specl+$seql;
}else{
@dmp=split(",",$1);
foreach my $d(@dmp){
$mult++;
if(/^>*(\S+)/){
$s=$1;
push(@species2,$s);
if($first){
$first=0;
$specl+=$refl;
}else{
$specl+=length($s)+2;
$seql+=$lenseq+1;
}
$spec{$s}=$specl+$seql;
}
}
}
}
}
close IN;
my %gapindex;
my %gapindexr; ## this has position and then as second key the species to delete
my $href=\%gapindex;
## if we want to retrieve hash with gap information and so on
my $line;
my $itergap;
if ($options{'P'}) {
#$href = retrieve("$options{'P'}/$options{'c'}.maf.perlhash_storable");
open GI,"$options{'P'}/$options{'c'}.maf.index.sorted" or die "Index.sorted file not found\n";
$itergap=filehandle_iterator(*GI);
$line=$itergap->();
$line=$itergap->() if($line =~ /\#/); ## only if we have a header line
@l=split(/\s+/,$line);
}
if(not -d "projects"){
mkdir "projects";
}
my $tag="default";
$tag=$options{'t'} if($options{'t'});
if (not -d "projects/$tag/") {
mkdir "projects/$tag/";
}
my $window=30;
$window=$options{'W'} if($options{'W'});
my %tss; ## holds all tss
my %tse; ## holds all tse
my @tssap;
my @tesap;
my @tssam;
my @tesam;
my ($dtss,$dtes);
my %anno=();
if ($options{'a'}) {
readin_annotation_files($options{'a'},\%anno);
}
my $min_orf_len=27;
$min_orf_len=$options{'l'} if($options{'l'});
my $max_size=300; ## max orf len
$max_size=$options{'M'} if $options{'M'};
$max_size++;
my $igs=0;
$igs=1 if($options{'S'});
my %ignores;
$ignores{'+'}='-';
$ignores{'-'}='+';
## read protein alphabet to hashes codons and rcodons
my %codons;
my %rcodons;
initProt(\%codons,\%rcodons);
my %refseq;
my %nc_refseq=();
my %oa_files=();
my ($pi,$mi);
my %fhh=();
my @files;
## read in file with transcript info
# my ($fhb,%codonpos);
my %cp;
if($options{'B'}){
open my $optionsB ,$options{'B'} or die "File $options{'B'} not found\n";
get_codon_pos_index($options{'B'},\%cp,$options{'c'});
print STDERR "codon pos read in for all transcripts on $options{'c'}\n";
my @j=sort {$b <=> $a} keys %cp;
# die join(",",@j),"\n";
## this can be optimized by using iterators on the file
# $fhb=filehandle_iterator(*$optionsB);
# $fhl=$fhb->(); #iteration1
# die $fhl;
}
if ($options{'r'}) {
@files=split(",",$options{'r'}) or die "$options{'r'} not given\n";
foreach my $f (@files) {
# if ($options{'Z'}) {
$f.=".sorted";
# }
open my $fh ,$f or die "File $f not found\n";
$fhh{$f}{'type'} = 'c';
$fhh{$f}{'fh'} = *$fh;
$fhh{$f}{'it'} = filehandle_iterator(*$fh);
$fhh{$f}{'l'} = $fhh{$f}{'it'} ->(); ## iteration 1
if ($fhh{$f}{'l'} =~ /\#/) {
readin_refseq(\%refseq,$fhh{$f}{'l'},$f);
$fhh{$f}{'l'} = $fhh{$f}{'it'} ->(); ## iteration2
}
get_tss_tse(\%fhh,$f);
}
}
if ($options{'n'}) {
@files=split(",",$options{'n'}) or die "$options{'n'} not given\n";
foreach my $f (@files) {
$f.=".sorted";
open my $fh ,$f or die "File $f not found\n";
$fhh{$f}{'type'} = 'n';
$fhh{$f}{'fh'} = *$fh;
$fhh{$f}{'it'} = filehandle_iterator(*$fh);
$fhh{$f}{'l'} = $fhh{$f}{'it'} ->(); ## iteration 1
if ($fhh{$f}{'l'} =~ /\#/) {
readin_refseq(\%nc_refseq,$fhh{$f}{'l'},$f);
$fhh{$f}{'l'} = $fhh{$f}{'it'} ->();
}
get_tss_tse(\%fhh,$f);
}
}
@tssap=sort {$a <=> $b} keys %{$tss{$chr}{'+'}};
@tssam=sort {$a <=> $b} keys %{$tss{$chr}{'-'}};
@tesap=sort {$a <=> $b} keys %{$tse{$chr}{'+'}};
@tesam=sort {$a <=> $b} keys %{$tse{$chr}{'-'}};
## read in maf with species alignments
my %maf=();
print STDERR "reading maf file now\n";
my $finalpos='';
my %positions=();
## if we use a bed file we ignore the given global maf file cause we extract everything directly from genome
my %ph=();
my @bl;
my @bs;
## open output files
my $what="genomic-strand\tmp-orientation";
my $whatc='#chr';
$what="tx-orientation_genomic\tmp-orientation" if($options{'b'});
$whatc='#transcript' if($options{'b'});
my $add='';
if($options{'K'}){
$add.="\tcirc_len\tstart.frag\tend.frag\t#junctionc";
}else{
$add="\ttype\tscoretxregion";
}
my %seen=();
if($options{'X'}){
mkdir $options{'X'} if(not -d $options{'X'});
$add.="\tomega\tomega_flankl\tomega_flankr\tomega_cds\tcodons-scored";
}
my $header="$whatc\t$what\tstart\tend\tlen\tframe\t#species\tsyn_mut\tAA\tDNA\tdnaH(orf)\taaH(orf)\taaH(pre)\taaH(suf)\tspecies\tkozak\tshine-d\tdistNTSS\tdistNTSE\tdistNstart\tdistNend\tother_annotations\twsum,codMut,specMut\tsyn_mut,nsyn_mut,uniq_syn_mut,uniq_nsyn_mut,ka,ks\tomega\t#startC:val\t#stopC:val\tucsc_coords\tmedian(dndsORF)\tmedian(dndsORF_iss)\tmedian(dndsleftF)\tmedian(dndsrightF)\tmean(dndsORF)\tmean(dndsleftF)\tmean(dndsrightF)\tsd(dndsORF)\tsd(dndsleftF)\tsd(dndsrightF)\t#frameshiftSpecies\tframeshiftSpecies$add";
$header.="\t#nonsense";
$header.="\n";
if(not $options{'b'}){
open COD,">projects/$tag/${chr}_coding_overlap" or die "File ${chr}_coding_overlap could not be created\n";
print COD $header;
open NC,">projects/$tag/${chr}_noncoding_overlap" or die "File ${chr}_noncoding_overlap could not be created\n";
print NC $header;
open IG,">projects/$tag/${chr}_intergenic" or die "File ${chr}_intergenic could not be created\n";
print IG $header;
open ASN,">projects/$tag/${chr}_asn" or die "File ${chr}_asn could not be created\n";
print ASN $header;
open ASC,">projects/$tag/${chr}_asc" or die "File ${chr}_asc could not be created\n";
print ASC $header;
open ERR ,">projects/$tag/${chr}.err" or die "Could not open file projects/$tag/${chr}.err\n";
}else{
## we need to put the filename in here
my $file;
if($options{'K'}){
if(not -d "$chr"){
mkdir "projects/$tag/${chr}";
my @sp=split("/",$options{'b'});
$file=$sp[$#sp];
}
#open IG,">projects/$tag/${chr}/${file}_transcripts" or die "Could not open file projects/$tag/${chr}_transcripts\n";
}else{
open IG,">projects/$tag/${chr}_transcripts" or die "Could not open file projects/$tag/${chr}_transcripts\n";
}
print IG $header;
open ERR ,">projects/$tag/${chr}_transcripts.err" or die "Could not open file projects/$tag/${chr}_transcripts.err\n";
}
if($options{'b'}){
if(not $options{'K'}){
open BEDI,">projects/$tag/${chr}_transcripts.bed" or die "Could not open Bed file for writing\n";
#open BEDIE,">projects/$tag/${chr}_transcripts_exons.bed" or die "Could not open Bed file for writing\n";
}
my $bs="$options{'b'}.sorted";
if(not -f $bs){
print STDERR "File $bs does not exist, checking local dir\n";
my ( $name2, $path2, $extension2 ) = fileparse ( $options{'b'}, '\..*' );
$bs="$name2$extension2.sorted";
if(not -f $bs){
print STDERR "File $bs does not exist, trying to generate it in local dir\n";
system("sort -nk2 $options{'b'} > $bs");
}else{
print STDERR "File $bs exists, using this one\n";
}
}
open IN,"$bs" or die "Bed file $bs not found for processing\n";
%seen=();
my @line;
my @iline;
my $pold;
my $tc=0;
my $rel;
my $curbp;
my $type;
my $i;
my $s;
my $il;
my %tmaf;
while(<IN>){
next if(/^\s*$/);
next if(/\#/);
@iline=split();
next if($iline[0] ne $chr);
$tc++;
# print STDERR "$tc\r";
%maf=();
%ph=();
chomp;
$il=join("\t",@iline);
if(not defined $iline[6]){
$il.="\t$iline[2]\t$iline[2]\t0\t1\t".($iline[2]-$iline[1])."\t0";
}
@line=split(/\s+/,$il);
print STDERR "$line[3]\n" if($options{'v'});
$currentgene=$line[3];
getseq_bed($fh,$offset,$chr,$il,\%maf,\@species);
$finalpos=length($maf{$species[0]});
$rel=-1; ## relative 0 based postion
$curbp=0;
$type='';
$ph{'strand'} = $line[5];
$ph{'name'} = $line[3];
if($line[5] ne '+' and $line[5] ne '-'){
$line[5] = '+';
$ph{'name'}.='nostrand';
}
$ph{'txs'} = $line[1];
$ph{'txe'} = $line[2];
if(defined $line[6]){
$ph{'cdss'} = $line[6];
$ph{'cdse'} = $line[7];
$ph{'bs'} = $line[11];
$ph{'bl'} = $line[10];
$ph{'bc'} = $line[9];
@bl=split(",",$line[10]);
@bs=split(",",$line[11]);
}else{
$ph{'cdss'} = $line[1];
$ph{'cdse'} = $line[1];
$ph{'bs'} = $line[1];
$ph{'bl'} = $line[2]-$line[1];
$ph{'bc'} = $line[1];
@bl=split(",",$ph{'bl'});
@bs=split(",",0);
}
my %newindex=();
## delete from gap index here until we reach next tx start so we always follow this guys here, maybe we only check postions where we have indeed gaps ??
## this may create huge computing overhead
if($pold and $options{'P'}){
if($pold != $ph{'txs'}){
for ($i = $pold;$i < $ph{'txs'}; $i++){
if($gapindexr{$i}){
foreach $s(keys %{$gapindexr{$i}}){
delete $gapindex{$s}{$i} if(exists $gapindex{$s}{$i});
}
delete $gapindexr{$i};
}
}
}
$pold=$ph{'txs'}; ## set new pold
}
## set the initial $pold variable
if(not $pold){
$pold = $ph{'txs'};
}
my $llen=0;
for($i= 0;$i<scalar @bs;$i++){
$llen+=$bl[$i];
}
my $pa=-1;
$llen--;
for($i= 0;$i<scalar @bs;$i++){
$curbp=-1;
$ph{'len'}+=$bl[$i];
for($s=$bs[$i]; $s < $bs[$i]+$bl[$i];$s++){
$curbp++;
$pa++;
if($ph{'strand'} eq '+'){
$rel=$pa;
}else{
$rel=$llen-$pa;
}
$ph{$rel}{'abs'}=$line[1]+$s; ## absolute genome position
if($ph{'strand'} eq '-'){
$ph{'cdsse'} = $rel if($ph{$rel}{'abs'} == $line[6]);
$ph{'cdssr'} = $rel if($ph{$rel}{'abs'} == $line[7]-1);
}else{
$ph{'cdssr'} = $rel if($ph{$rel}{'abs'} == $line[6]);
$ph{'cdsse'} = $rel if($ph{$rel}{'abs'} == $line[7]-1);
}
## where are we, utr or cds
if($line[6] != $line[7]){
if($ph{$rel}{'abs'} >= $line[6] and $ph{$rel}{'abs'} < $line[7]){$type='cds';} ## we also need a counter for the frames
if($ph{$rel}{'abs'} < $line[6]){$type='utr5';$type='utr3' if($line[5] eq '-')}
if($ph{$rel}{'abs'} >= $line[7]){$type='utr3';$type='utr5' if($line[5] eq '-')}
}else{
$type='nc';
}
$ph{$rel}{'t'}=$type;
$ph{$rel}{'pos'}=$bs[$i];
$ph{$rel}{'cpos'}=$curbp;
}
}
if($options{'K'}){ ## so we use circular mode , then extract first the circ from the full bed and then concat it 4 times
## if cds could not be identified cause start or end are not in extracted sequence then skip. This happens if one of them is not part of the exon structure given
if(not defined $ph{'cdsse'} or not defined $ph{'cdssr'}){
print STDERR "$ph{'name'} has inconsistent cds start or end and will be skipped\n";
next;
}
$ph{'circl'} = $ph{'cdsse'}-$ph{'cdssr'}+1;
if(not $ph{'circl'}){
print STDERR "here circl $ph{'name'}\n";
next;
}
foreach my $s(keys %maf){
$tmaf{$s}=substr($maf{$s},$ph{'cdssr'},$ph{'circl'});
# if($ph{'circl'} % 3 != 0){
$tmaf{$s}=$tmaf{$s}.$tmaf{$s}.$tmaf{$s}.$tmaf{$s}; ## we put it 4 times behind each other since we need to have a circle
# }
}
%maf=%tmaf;
$finalpos=length($maf{$species[0]});
if($options{'k'}){
if(not -d $options{'k'}){
mkdir $options{'k'};
}
open OUT,">$options{'k'}/${line[3]}";
foreach my $s(@species){
print OUT ">$s";
if($s eq $species[0]){
if($ph{'strand'} eq '+'){
print OUT "|$line[0]:$line[6]-$line[7]:$line[5]:0-$ph{'circl'}:0-",4*$ph{'circl'},":$ph{'cdssr'}-",$ph{'cdsse'}+1;
}else{
print OUT "|$line[0]:$line[6]-$line[7]:$line[5]:0-$ph{'circl'}:0-",4*$ph{'circl'},":",$ph{'cdssr'}+1,"-$ph{'cdsse'}";
}
}
print OUT "\n$maf{$s}\n";
}
close OUT;
}
}
## in case of a noncoding RNA we set this to 0 end length
$ph{'cdssr'} = 0 if(not defined $ph{'cdssr'}); ### in case we have a noncoding rna in here
$ph{'cdsse'} = $ph{'len'}-1 if(not defined $ph{'cdsse'}); ### in case we have a noncoding rna in here
## if we check for coords now we first have the offset of $ph{'cdssr'} and then we need to keep in mind, that we can be in circle round 1 2 3 or 4 when checking for gaps and so on
if($options{'K'}){
$ph{'txs'} = $line[6];
$ph{'txe'} = $line[7];
}
# die $cp{$ph{1543}{'abs'}};
## this seems to work, I need to track the coords for the circles if there is something in and we need to print the alignemnts in the end
my $skipnt=0;
if($options{'E'}){ ## we score only exons for conservation
detect_orfs_exons(\%maf,\%positions,\@species,\%refseq,\%nc_refseq,\%oa_files,$igs,$window,$kaks,$finalpos,\%ph,$itergap,\%cp,*GI,$skipnt);
}else{
detect_orfs(\%maf,\%positions,\@species,\%refseq,\%nc_refseq,\%oa_files,$igs,$window,$kaks,$finalpos,\%ph,$itergap,\%cp,*GI,$skipnt);
}
}
close IN;
close BEDI;
#close BEDIE;
close IG;
}else{
my $skipnt;
read_fasta($options{'m'},\%maf,\$finalpos,$species[0],\$skipnt);
print STDERR "Fasta file $options{'m'} read\n";
## now do the real job and detect micropeptidegs
detect_orfs(\%maf,\%positions,\@species,\%refseq,\%nc_refseq,\%oa_files,$igs,$window,$kaks,$finalpos,\%ph,$itergap,\%cp,*GI,$skipnt);
}
close MAF;
print STDERR "#\n#end\t", strftime("%d-%m-%Y\t%T",localtime),"\n#\n###########################################\n\n";
exit;
## cat files together and make bed files and html files
my $oo;
if (not $options{'O'}){$oo = "-o ";}else{ $oo = "-o $options{'O'} ";}
print STDERR "now do
cd projects/$tag
cat chr*intergenic > all_orfs_intergenic
perl ../../score.pl -i all_orfs_intergenic -o $oo > all_orfs_intergenic.tmp
head -n1 all_orfs_intergenic.tmp > all_orfs_intergenic.mssm
grep -v \\# all_orfs_intergenic.tmp |sort -rnk 2 >> all_orfs_intergenic.mssm
perl ../../make_bed_file.pl all_orfs_intergenic.mssm
";
print STDERR "Now you should upload your bedfiles to UCSC and then
create an html file with the correct hgsid
#mirpep2table.pl s_6_m_6.mssm.cand dme 1 hgsid 30
../../mp_make_html_red.pl -t all_orfs_intergenic.mssm -s 3 -e 4 -c 1 -i 0 -S cel -w 30 -I hgsid`
";
#`../../mp_make_html_red.pl -t all_orfs_intergenic.mssm -s 3 -e 4 -c 1 -i 0 -S cel -w 30`
exit;
my @F;
for(my $i=1;$i<=12;$i++){
open IIN,"all_orfs_intergenic_.mssm" or die "File all_orfs_intergenic.mssm not found\n";
open OUTI,">s_${i}_m_${i}.mssm.cand" or die "File s_${i}_m_${i}.mssm.cand could not be created\n";
while(<IIN>){
@F=split();
if(/\#/){print OUTI;}elsif($F[7]>$i && $F[8] > $i){print OUTI;}else{}
}
close OUTI;
close IIN;
`perl ../../mirpep_make_bed_file.pl s_${i}_m_${i}.mssm.cand $tag${i}${i}`;
}
print STDERR "Now you should upload your bedfiles to UCSC and then
create an html file with the correct hgsid
../../mp_make_html_red.pl -t all_orfs_intergenic.mssm -s 3 -e 4 -c 1 -i 0 -S cel -w 30 -a 6 -b 6`
";
#######################################################
#######################################################
#######################################################
sub getseq_bed{
## fuction needs to get a filehandle
## must be called like check(*IN,1234)
## the star is really important
## this is random access to index file, saves a lot of time
my ($fh,$offset,$chrr,$line,$maf,$selected)=@_;
my ($tseq,$seq,$pos,$first);
my ($chr,$start,$end,$name,$score,$strand,$dmp1,$dmp2,$color,$blockcount,$blocksizes,$blockstarts)=split(/\s+/,$line);
$blocksizes=$1 if($blocksizes =~ /(\S+),$/);
$blockstarts=$1 if($blockstarts =~ /(\S+),$/);
my @bs=split(",",$blocksizes);
my @bb=split(",",$blockstarts);
## get coords
my @cc;
my $coords='';
my ($b,$e);
for(my $i=0;$i<scalar @bs;$i++){
$b=$start+$bb[$i];
$e=$start+$bb[$i]+$bs[$i];
$coords.="$b,$e,";
push(@cc,$b);
push(@cc,$e);
}
# my @cc=split(",",$coords);
if($cc[0] == $cc[1]){
print STDERR "$name\tlen0\n";
next;
}
$first=0;
foreach my $s(@$selected){
$seq='';
if(not $first){
$first = 1;
#print ">$s.$chr($strand):$coords:$name\n";
}else{
#print ">$s\n";
}
for (my $i=0;$i<scalar @cc;$i+=2){
$len=$cc[$i+1]-$cc[$i]; ## get the length correctely
$start=$cc[$i];
$pos=$spec{$s}+$start-$offset;
seek $fh,$pos,0;
$tseq='';
read($fh,$tseq,$len);
$seq.=$tseq;
}
if($strand eq '-'){
$seq=rc($seq);
}
#print $seq,"\n";
$$maf{$s} = $seq;
}
}
sub getseq{
## fuction needs to get a filehandle
## must be called like check(*IN,1234)
## the star is really important
## this is random access to index file, saves a lot of time
my ($fh,$start,$len,$offset,$strand,$tmphash,$species)=@_;
my ($seq,$pos,$first);
foreach my $s (@$species) {
$pos=$spec{$s}+$start-$offset;
seek $fh,$pos,0;
read($fh,$seq,$len);
if ($strand eq '-') {
$seq=rc($seq);
}
$$tmphash{$s} = $seq;
}
}
## some iterator subs
sub Iterator (&) { return $_[0];}
sub filehandle_iterator {
my $fh = shift;
return Iterator { <$fh> };
}
sub get_tss_tse{
my ($fhh,$f)= @_;
my ($cname,$cchr,$cstrand,$ctxs,$ctxe,$ccds,$ccde,$ces,$cee)=(-1,-1,-1,-1,-1,-1,-1,-1,-1);
my @line;
($cchr,$cstrand,$ctxs,$ctxe,$ccds,$ccde,$cname)= ($fhh{$f}{'token'}{'chr'},$fhh{$f}{'token'}{'strand'}, $fhh{$f}{'token'}{'txstart'},$fhh{$f}{'token'}{'txend'},$fhh{$f}{'token'}{'cdsstart'},$fhh{$f}{'token'}{'cdsen\
d'}, $fhh{$f}{'token'}{'name'});
open IN,$f or die "File $f could not be opened\n";
while(<IN>){
next if(/\#/);
@line=split(/\s+/);
$tss{$line[$cchr]}{$line[$cstrand]}{$line[$ctxs]}=1;
$tse{$line[$cchr]}{$line[$cstrand]}{$line[$ctxe]}=1;
}
close IN;
}
sub check{
my ($i,$h,$line,$f,$maxlen,$fhh,$g2,$chr,$startpos) = @_;
return if(not defined $$fhh{$f}{'l'});
return if($startpos > $i+$maxlen+1);
#die $i if($f eq 'ce6_wormbase_RNAs_12_02_13' and $i == 895);
my ($utr,$cds,%ee,%es,$ie,$id,$pseudo,$extra)=();
## adapt this here
delete $$h{$chr}{'+'}{($i-3*$maxlen)} if (exists $$h{$chr}{'+'}{($i-3*$maxlen)}); ## delete previous positions if existed in hash
delete $$h{$chr}{'-'}{($i-3*$maxlen)} if (exists $$h{$chr}{'-'}{($i-3*$maxlen)}); ## delete previous positions if existed in hash
## get variables here for ctxstart,ctxend,cname and chromosome
my ($cname,$cchr,$cstrand,$ctxs,$ctxe,$ccds,$ccde,$ces,$cee)=(-1,-1,-1,-1,-1,-1,-1,-1,-1);
($cchr,$cstrand,$ctxs,$ctxe,$ccds,$ccde,$cname,$pseudo)= ($$fhh{$f}{'token'}{'chr'},$$fhh{$f}{'token'}{'strand'}, $$fhh{$f}{'token'}{'txstart'},$$fhh{$f}{'token'}{'txend'},$$fhh{$f}{'token'}{'cdsstart'},$$fhh{$f}{'token'}{'cdsend'}, $$fhh{$f}{'token'}{'name'},$$fhh{$f}{'token'}{'pseudo'});
if (not $ccde) {
die $f;
}
# die "here" if($f eq 'ce6_wormbase_RNAs_12_02_13' and $i == 895);
## goto next line if current does not match chromosome
while ($$line[$cchr] ne $chr) {
$$fhh{$f}{'l'} = $fhh{$f}{'it'} ->();
last if(not defined $$fhh{$f}{'l'});