-
Notifications
You must be signed in to change notification settings - Fork 12
/
hicup_filter
executable file
·1462 lines (1244 loc) · 64.4 KB
/
hicup_filter
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
use strict;
use warnings;
use Getopt::Long;
use POSIX ":sys_wait_h"; #for nonblocking read
use POSIX;
use Carp;
use FindBin '$Bin';
use lib $Bin;
use hicup_module;
use hicup_module qw(hashVal outdirFileNamer get_csome_position);
use Data::Dumper;
###################################################################################
###################################################################################
##This file is Copyright (C) 2023, Steven Wingett ##
## ##
## ##
##This file is part of HiCUP. ##
## ##
##HiCUP is free software: you can redistribute it and/or modify ##
##it under the terms of the GNU General Public License as published by ##
##the Free Software Foundation, either version 3 of the License, or ##
##(at your option) any later version. ##
## ##
##HiCUP is distributed in the hope that it will be useful, ##
##but WITHOUT ANY WARRANTY; without even the implied warranty of ##
##MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ##
##GNU General Public License for more details. ##
## ##
##You should have received a copy of the GNU General Public License ##
##along with HiCUP. If not, see <http://www.gnu.org/licenses/>. ##
###################################################################################
###################################################################################
#Option variables
my %config = (
digest => '',
config => '',
example => '',
datestamp => '',
help => '',
outdir => '',
quiet => '',
threads => '',
version => '',
longest => '',
shortest => '',
r => '',
re1 => '',
re2 => '',
samtools => '',
zip => ''
);
##########################################################
#Get user-supplied parameters
my $config_result = GetOptions(
"datestamp=s" => \$config{datestamp}, #Hidden option passed from the HiCUP master script
"digest=s" => \$config{digest},
"example" => \$config{example},
"config=s" => \$config{config},
"help" => \$config{help},
"outdir=s" => \$config{outdir},
"longest=i" => \$config{longest},
"quiet" => \$config{quiet},
"shortest=i" => \$config{shortest},
"threads=i" => \$config{threads},
"version" => \$config{version},
"r=s" => \$config{r},
"samtools" => \$config{samtools},
"zip" => \$config{zip}
);
die "Could not parse options.\n" unless ($config_result);
$config{help} = 1 unless ( hashVal(%config) ); #Print help and exit if no command line parameters
if ( $config{help} ) {
print while (<DATA>);
exit(0);
}
#Print version and exit
if ( $config{version} ) {
print "HiCUP Filter v$hicup_module::VERSION\n";
exit(0);
}
if ( $config{example} ) {
print_example_config_file('filter_example.conf');
exit(0);
}
check_dependencies();
my @files; #Files to be processed
@files = process_config( $config{config}, \%config ) if ( hasval( $config{config} ) ); #Modifies %config and returns an array of the filenames
push( @files, @ARGV ) if @ARGV;
@files = sort deduplicate_array (@files);
die "Please specify files to be filtered.\n" unless (@files);
##########################################################
#Check user-supplied parameters are ok
unless ( check_parameters() ) {
die "Please change configuration file and/or command-line parameters and/or installation accordingly\n";
}
my $protocol = "Double_Digest";
my %ditag_sizes; #Hash of %{ditag_size} -> frequency. (For the double-digest protocol the sizes will be of the di-tags that map to restriction fragment sites only i.e. ignore "unmapped")
my $hicup_executed = 0;
if ( hasval( $config{datestamp} ) ) { #Script executed by hicup master script
$hicup_executed = 1;
}
my $insert_size_check;
if ( $config{longest} or $config{shortest} ) {
$insert_size_check = 1;
}
my %inOutFilenames = outdirFileNamer( \@files, $config{outdir} );
unless ( hasval( $config{datestamp} ) ) {
$config{datestamp} = datestampGenerator();
}
#Check input files exist and output files don't.
die "Please correctly specify files to be filtered.\n" unless ( check_files_exist( \@files, 'EXISTS' ) );
my @hicup_filter_outfiles = fileNamer( \@files, \%config, 'filter', 1, 1, 1, 1, 1 );
foreach my $outfile (@hicup_filter_outfiles) {
$outfile = $config{outdir} . $outfile;
}
unless ( check_files_exist( \@hicup_filter_outfiles, 'NOT_EXISTS' ) ) {
die "HiCUP Filter will not run until files have been removed.\n";
}
#Create a directory for rejected Hi-C sequences
my ($rejdir) = fileNamer( '', \%config, 'filter', 0, 0, 0, 0, 1 ); #Rejects folder name
$rejdir = $config{outdir} . $rejdir;
mkdir $rejdir or die "Could not write to '$rejdir'\n";
#Processes the data in accordance with the protocol followed (i.e. double digest or sonication)
print "Filtering with HiCUP Filter v$hicup_module::VERSION\n" unless hasval( $config{quiet} );
my $terminate = 0; #Instruct script to die if error detected in child process
my %digest_fragments;
my %last_first_bases; #Lookup hash for double-digest analysis, but needs to be declared outside the conditional block to be available to child processes
my %children; #Hash of child processes
print "Processing digest file $config{digest}\n" unless hasval( $config{quiet} );
process_digest_file(); #Determines i)protocol followed i)populates %digest_fragments and, if appropriate, ii)populates %last_first_bases
my $summaryfile = summary_file_creator(); #Creates a summary file in accordance with the protocol followed
if ( $protocol eq 'Double_Digest' ) {
foreach my $filename (@files) {
my $pid = fork();
die "cannot fork" unless defined $pid;
if ( $pid == 0 ) {
double_digest_hic($filename);
exit 0;
} else {
$children{$pid} = 1;
while ( keys(%children) == $config{threads} ) {
sleep(1);
reaper();
}
}
}
close SUMMARY or die "Could not close filehandle on '$summaryfile' : $!";
} else {
foreach my $filename (@files) {
my $pid = fork();
die "cannot fork" unless defined $pid;
if ( $pid == 0 ) {
sonicate_hic($filename);
exit 0;
} else {
$children{$pid} = 1;
while ( keys(%children) == $config{threads} ) {
sleep(1);
reaper();
}
}
}
}
#Ensure all child processes have terminated before exiting
do {
sleep(1);
reaper();
} until ( keys(%children) == 0 );
if ($terminate) {
die "hicup_filter unable to process files\n";
}
#Produce summary graph
my $graphSuffix = ( fileNamer( '', \%config, 'filter', 0, 0, 1, 0, 0 ) )[1]; #Pass '' - which will return a suffix only i.e ".[suffix].svg"
unless ( $config{r} eq '0' ) {
if(-s $summaryfile){
if ( $protocol eq 'Sonication' ) {
my $command = $config{r} . 'script ' . "$Bin/r_scripts/hicup_filter_sonication_summary.r $summaryfile $config{outdir} $graphSuffix";
!system("$command") or warn "Could not produce hicup_filter pie chart: $command: $!";
} else {
my $command = $config{r} . 'script ' . "$Bin/r_scripts/hicup_filter_double_digest_summary.r $summaryfile $config{outdir} $graphSuffix";
!system("$command") or warn "Could not produce hicup_filter summary pie chart: $command: $!";
}
}else{
warn "Could not produce hicup_filter summary pie chart since '$summaryfile' contains no data\n";
}
}
print "Filtering complete\n" unless hasval( $config{quiet} );
exit(0);
#######################################################################################
#Subroutines #
#######################################################################################
###########################
#Subroutine "check_dependencies"
#Evaluates if the relevant dependencies
#are installed, and if so stores the path
#in the %dependencies hash_ref
sub check_dependencies {
#Check whether SAMtools is installed
if ( !system "which samtools >/dev/null 2>&1" ) {
$config{samtools} = `which samtools`;
}
chomp $config{samtools};
}
############################
#Subroutine "check_parameters":
#Check the user supplied parameters are ok
#Uses global variables
sub check_parameters {
my $parameters_ok = 1;
#Check whether SAMtools is installed
unless ( hasval( $config{samtools} ) ) {
if ( !system "which samtools >/dev/null 2>&1" ) {
$config{samtools} = `which samtools`;
chomp $config{samtools};
}
}
if ( hasval( $config{threads} ) ) {
if ( $config{threads} < 1 ) { #Ensure threads not set to less than 1!
warn "Threads changed from config{threads} to 1\n";
$config{threads} = 1;
}
} else {
print "Number of threads set to 1\n";
$config{threads} = 1;
}
$config{outdir} = './' unless ( hasval $config{outdir} ); #Set to CWD if not defined
#Check the output directory exists
unless ( -d $config{outdir} ) {
warn "Output directory '$config{outdir}' does not exist.\n";
$parameters_ok = 0;
}
#Make sure that $config{outdir} ends with the forward slash character
$config{outdir} .= '/' unless ( $config{outdir} =~ /\/$/ );
unless ( hasval( $config{digest} ) ) {
warn "Please specify a Hi-C SAM file and a digested reference genome file (--digest), or alternatively a configuration file (--config).\n";
$parameters_ok = 0;
}
#Check size-selection
foreach my $size_parameter ( 'longest', 'shortest' ) {
if ( hasval( $config{$size_parameter} ) ) {
unless ( $config{$size_parameter} =~ /^\d+$/ ) {
warn "Size-selection parameter '--" . $size_parameter . "' may only be an integer\n";
$parameters_ok = 0;
}
} else {
$config{$size_parameter} = 0;
}
}
checkR( \%config ); #Check R installed
return $parameters_ok;
}
##################################
#Subroutine "process_digest_file":
#reads the digest file, determines whether a double-digest or a sonication protocol
#was followed and processes accordingly, returning a hash of the results.
sub process_digest_file {
if ( $config{digest} =~ /.*\.gz$/ ) {
open( DIGEST, "gunzip -c $config{digest} |" ) or die "Cannot open file: $!";
} else {
open( DIGEST, $config{digest} ) or die "Cannot open file: $!";
}
my $first_line = <DIGEST>; #Determine whether an enzymic double digest or sonication protocol
unless ( $first_line =~ /^.+\t(.+)\t(.+)\t.+$/ ) {
die "Genome digest file header is not in the correct format\n";
}
if ( $2 eq "Restriction_Enzyme2:None" ) { #Sonication protocol
$protocol = "Sonication";
print "Sonication protocol followed - $1\n" unless $config{quiet};
while (<DIGEST>) {
unless (/\w+\t\d+\t\d+\t\d+/) {
next;
}
my $chromosome_name = ( split /\t/ )[0];
my $first_base = ( split /\t/ )[1];
my $last_base = ( split /\t/ )[2];
my $fragment_number = ( split /\t/ )[3];
my $ten_kb_region = ceil( $first_base / 10000 );
my $fragment_end_ten_kb_region = ceil( $last_base / 10000 );
do {
$digest_fragments{"$chromosome_name\t$ten_kb_region"}{$first_base} = "$last_base\t$fragment_number";
$ten_kb_region++;
} while ( $ten_kb_region <= $fragment_end_ten_kb_region );
}
} else { #Double-digest protocol
#First check if re1 & re2 have only a single enzyme each
unless ( $first_line =~ /.+\tRestriction_Enzyme1:(.+\[.+\])\tRestriction_Enzyme2:(.+\[.+\])\t.+/ ) {
die "Genome digest file $config{digest} is not in the correct format.\n";
}
my ($re1, $re2) = ($1, $2);
my ($re1count, $re2count) = (0, 0);
$re1count++ while ($re1 =~ m/(\S+)\s\[(\S+)\]/g);
$re2count++ while ($re2 =~ m/(\S+)\s\[(\S+)\]/g);
if ($re1count > 1 || $re2count > 1) {
die "Double-digest protocol does not support multiple enzyme digestion...\nPlease ensure you are using only one enzyme for RE1 as well as only one enzyme for RE2.\n"
}
#Determine the sequences of re1 and re2
unless ( $first_line =~ /.+\t.+\[(.+)\]\t.+\[(.+)\]/ ) {
die "Genome digest file $config{digest} is not in the correct format.\n";
}
$config{re1} = $1; #Declared as a global variable
$config{re2} = $2; #Declared as a global variable
print "Double digest protocol followed using $config{re1} and then $config{re2}\n" unless $config{quiet};
unless ( $config{re1} =~ /^[ATCGN\^]+$/ ) {
die "The restriction site (re1) needs to be a valid DNA sequence.\n";
}
unless ( ( $config{re1} =~ tr/\^// ) == 1 ) {
die "The restriction site (re1) should contain one cut position, denoted by '^'.\n";
}
unless ( $config{re2} =~ /^[ATCGN\^]+$/ ) {
die "The restriction site (re2) needs to be a valid DNA sequence.\n";
}
unless ( ( $config{re2} =~ tr/\^// ) == 1 ) {
die "The restriction site (re2) should contain one cut position, denoted by '^'.\n";
}
#If the restriction enzymes are not blunt-ended cutters, the sticky ends will be filled-in
#prior to A-tailing. This needs to be taken into account when aligning reads to the digested reference genome.
my ( $re1_start_correction, $re1_end_correction ) = fillin( $config{re1} );
my ( $re2_start_correction, $re2_end_correction ) = fillin( $config{re2} );
#Process the genome digest file: create a hash with the chromosome number + restriction fragment start positions as the keys.
#The remaining terms are stored as hash values.
$_ = <DIGEST>; #Ignore header line.
while (<DIGEST>) {
#Chromosome, Start position, End Position, Fragment Number, Re1 Fragment Number, 5'-Cut Site, 3'-Cutsite.
if (/^\s$/) {
next;
}
my ( $chromosome, $first_base, $last_base, $fragment_number, $re1_fragment_number, $five_prime_enz, $three_prime_enz ) = split /\t/;
if ( $five_prime_enz eq 'RE1' ) {
$first_base += $re1_start_correction;
} elsif ( $five_prime_enz eq 'RE2' ) {
$first_base += $re2_start_correction; #or do nothing if enzyme equals 'NONE'
}
if ( $three_prime_enz eq 'RE1' ) {
$last_base += $re1_end_correction;
} elsif ( $three_prime_enz eq 'RE2' ) {
$last_base += $re2_end_correction; #or nothing if enzyme equals 'NONE'
}
$digest_fragments{ $chromosome . "\t" . $first_base } = join( "\t", $last_base, $fragment_number, $re1_fragment_number, $five_prime_enz, $three_prime_enz );
}
}
#Forward reads will map to the front of a restriction fragment, whereas reverse reads will map to the end.
#Consequently we need to relate end positions to a given fragment.
#The code below creates a "lookup" hash with fragment end positions as keys and first base pair positions as values.
foreach my $key ( keys %digest_fragments ) {
my $chromosome = ( split( /\t/, $key ) )[0];
my $first_base = ( split( /\t/, $key ) )[1];
my $last_base = ( split( /\t/, $digest_fragments{$key} ) )[0];
$last_first_bases{"$chromosome\t$last_base"} = "$chromosome\t$first_base";
}
close DIGEST or die "Could not close filehandle on '$config{digest}' : $!";
}
#####################
#Subroutine "fillin":
#fills-in overhangs of a restriction fragment
#Receives the restriction site sequence (positive strand) as input, returns the values of i) how many bases the
#front should be brought forwards and ii) by how many bases the end should be extended. Both the returned values
#refer to the positive strand.
#For example, consider the HindIII sequence A^AGCTT. The front of the sequence will remain the same i.e. the base
#after the cute site, but the end of the sequence will be extened by 4 bases. The returned values will therefore
#be 0,4.
sub fillin {
my $re = $_[0];
my ( $before_cut, $after_cut ) = split( /\^/, $re );
my $difference = length($after_cut) - length($before_cut);
if ( $difference > 0 ) {
return ( 0, $difference );
} elsif ( $difference < 0 ) {
return ( $difference, 0 );
} else {
return ( 0, 0 );
}
}
###################################
#Subroutine "summary_file_creator":
#creates the summary files for both Hi-C protocols
#Opens a filehandle to the summary file and returns the
#summary filename
sub summary_file_creator {
# my $summaryfile = $config{outdir}.'hicup_filter_summary_'.$config{datestamp}.'.txt';
my ($summaryfile) = fileNamer( '', \%config, 'filter', 0, 1, 0, 0, 0 ); #Array returned
$summaryfile = $config{outdir} . $summaryfile;
if ( -e "$summaryfile" ) {
die "Summary file \'$summaryfile\' already exists. Please delete \'$summaryfile\'.\n\n";
}
open( SUMMARY, ">$summaryfile" ) or die "Could not write to $summaryfile\n";
if ( $protocol eq 'Double_Digest' ) {
#Create a summary file of the results and begin printing output to that file.
print SUMMARY
"File\tTotal_pairs\tValid_pairs\tCis_<10kbp\tCis_>10kbp\tTrans-ligation\tInvalid_pairs\tNo_ligation\tRe-ligation\tSelf-ligation\tNo_Ligation_Internal_Re2\tUnclassified\tWrong_size\tUnmapped\n";
} else {
print SUMMARY
"File\tTotal_pairs\tValid_pairs\tCis_<10kbp\tCis_>10kbp\tTrans\tInvalid_pairs\tSame_circularised\tSame_dangling_ends\tSame_internal\tRe-ligation\tContiguous_sequence\tWrong_size\n";
}
return $summaryfile;
}
################################
#Subroutine "double_digest_hic":
#analyses the data assuming a double-digest protocol has been followed
sub double_digest_hic {
my $filename = $_[0];
if ( $filename =~ /\.gz$/ ) {
open( PAIRED_READS, "gunzip -c $filename |" ) or die "Couldn't read $filename : $!";
} elsif ( $filename =~ /\.bam$/ ) {
if ( $config{samtools} ) {
open( PAIRED_READS, "$config{samtools} view -h $filename |" ) or die "Couldn't read $filename: $!";
} else {
die "Cannot process BAM files - either install SAMtools to process '$filename' or only provide SAM files\n";
}
} else {
open( PAIRED_READS, $filename ) or die "Could not read $filename: $!";
}
#Create outputfiles
my $outputfilename_base = fileNamer( $filename, \%config, 'filter' );
#my $outputfilename_base = $filename;
my $file_extension;
my $write_command;
# $outputfilename_base =~ s/^.+\///; #Remove folder references
if ( $config{samtools} and $config{zip} ) {
$file_extension = '.bam'; #BAM format
$write_command = '| samtools view -bSh 2>/dev/null - >';
} elsif ( $config{zip} ) {
$file_extension = '.sam.gz';
$write_command = "| gzip -c - >"; #SAM format then compressed
} else {
$file_extension = '.sam'; #SAM format
$write_command = ">";
}
my @output_files;
open( HIC_READS, $write_command . $config{outdir} . $outputfilename_base ) or die $!;
push( @output_files, $config{outdir} . $outputfilename_base );
open( UNMAPPED, $write_command . $rejdir . '/' . $outputfilename_base . "_unmapped" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_unmapped" . $file_extension );
if ($insert_size_check) {
open( WRONG_SIZE, $write_command . $rejdir . '/' . $outputfilename_base . "_wrong_size" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_wrong_size" . $file_extension );
}
open( NO_LIGATION, $write_command . $rejdir . '/' . $outputfilename_base . "_no_ligation" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_no_ligation" . $file_extension );
open( INTERNAL_RE2, $write_command . $rejdir . '/' . $outputfilename_base . "_internal_re2" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_internal_re2" . $file_extension );
open( SELF_LIGATION, $write_command . $rejdir . '/' . $outputfilename_base . "_self_ligation" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_self_ligation" . $file_extension );
open( RE_LIGATION, $write_command . $rejdir . '/' . $outputfilename_base . "_re_ligation" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_re_ligation" . $file_extension );
open( UNCLASSIFIED, $write_command . $rejdir . '/' . $outputfilename_base . "_unclassified" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_unclassified" . $file_extension );
open( INVALID, $write_command . $rejdir . '/' . $outputfilename_base . "_invalid" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_invalid" . $file_extension );
#Hash to count the different types of Hi-C ligation products
my %category_counter = (
'No_ligation' => 0,
'Internal_Re2' => 0,
'Self-ligation' => 0,
'Re-ligation' => 0,
'Cis_close' => 0,
'Cis_far' => 0,
'Trans-ligation' => 0,
'Wrong_size' => 0,
'Unclassified' => 0,
'Unmapped' => 0,
'Total' => 0,
'Invalid_format' => 0
);
#Read through the pair file and match the reads against %digest_fragments
my %digest_results;
print "Filtering $filename\n" unless $config{quiet};
while (<PAIRED_READS>) {
if (/^@/) { #Print SAM header lines
print HIC_READS $_;
print UNMAPPED $_;
if ($insert_size_check) {
print WRONG_SIZE $_;
}
print NO_LIGATION $_;
print INTERNAL_RE2 $_;
print SELF_LIGATION $_;
print RE_LIGATION $_;
print UNCLASSIFIED $_;
print INVALID $_;
next;
}
my $read1 = $_;
chomp $read1;
my $read2 = scalar <PAIRED_READS>;
chomp $read2;
#Check the reads are in the valid format
unless ( $read1 =~ /^.+\t\d+\t\S+\t\d+\t\d+\t\S+\t.+\t\d+\t\d+\t[ATCGN]+\t.+$/ and $read2 =~ /^.+\t\d+\t\S+\t\d+\t\d+\t\S+\t.+\t\d+\t\d+\t[ATCGN]+\t.+$/ ) {
$category_counter{Invalid_format}++;
print INVALID "$read1\n";
print INVALID "$read2\n";
next;
}
$category_counter{Total}++;
#Compare the reads to the genome digest file.
#Determine if we need to map to the front or rear of a fragment.
my $chromosome1 = ( split( /\t/, $read1 ) )[2];
my $chromosome2 = ( split( /\t/, $read2 ) )[2];
my $chromosome_position1 = ( split( /\t/, $read1 ) )[3];
my $chromosome_position2 = ( split( /\t/, $read2 ) )[3];
my $position_to_lookup1;
my $position_to_lookup2;
my $read1_strand;
my $read2_strand;
if ( ( ( split( /\t/, $read1 ) )[1] ) & 0x10 ) { #Analyse the SAM bitwise flag to determine which strand
$read1_strand = '-';
} else {
$read1_strand = '+';
}
if ( ( ( split( /\t/, $read2 ) )[1] ) & 0x10 ) { #Analyse the SAM bitwise flag to determine which strand
$read2_strand = '-';
} else {
$read2_strand = '+';
}
if ( $read1_strand eq '+' ) {
$position_to_lookup1 = $chromosome1 . "\t" . $chromosome_position1;
} else {
$position_to_lookup1 = $chromosome1 . "\t" . ( $chromosome_position1 + ( length( ( split( /\t/, $read1 ) )[9] ) ) - 1 ); #Add (read length - 1) to reach the end of the restriction fragment
if ( exists $last_first_bases{$position_to_lookup1} ) {
$position_to_lookup1 = $last_first_bases{$position_to_lookup1}; #Find the first base of the fragment
} else {
$category_counter{"Unmapped"}++;
print UNMAPPED "$read1\n";
print UNMAPPED "$read2\n";
next;
}
}
if ( $read2_strand eq '+' ) {
$position_to_lookup2 = $chromosome2 . "\t" . $chromosome_position2;
} else {
$position_to_lookup2 = $chromosome2 . "\t" . ( $chromosome_position2 + ( length( ( split( /\t/, $read2 ) )[9] ) ) - 1 ); #Add (read length - 1) to reach the end of the restriction fragment
if ( exists $last_first_bases{$position_to_lookup2} ) {
$position_to_lookup2 = $last_first_bases{$position_to_lookup2}; #Find the first base of the fragment
} else {
$category_counter{"Unmapped"}++;
print UNMAPPED "$read1\n";
print UNMAPPED "$read2\n";
next;
}
}
#Begin the categorisation.
my $fragment1_data;
my $fragment2_data;
if ( exists $digest_fragments{$position_to_lookup1} ) {
$fragment1_data = $position_to_lookup1 . "\t" . $digest_fragments{$position_to_lookup1};
} else {
$category_counter{"Unmapped"}++;
print UNMAPPED "$read1\n";
print UNMAPPED "$read2\n";
next;
}
if ( exists $digest_fragments{$position_to_lookup2} ) {
$fragment2_data = $position_to_lookup2 . "\t" . $digest_fragments{$position_to_lookup2};
} else {
$category_counter{"Unmapped"}++;
print UNMAPPED "$read1\n";
print UNMAPPED "$read2\n";
next;
}
#Determines the type of fragment pair e.g. cis-ligations, trans-ligation.
my $linkage;
if ( ( split( /\t/, $fragment1_data ) )[0] eq ( split( /\t/, $fragment2_data ) )[0] ) {
if ( ( split( /\t/, $fragment1_data ) )[4] == ( split( /\t/, $fragment2_data ) )[4] ) {
$linkage = "Same(Re1)";
if ( ( split( /\t/, $fragment1_data ) )[3] == ( split( /\t/, $fragment2_data ) )[3] ) {
$linkage .= "_same(Re1-Re2)";
} elsif ( abs( ( split( /\t/, $fragment1_data ) )[3] - ( split( /\t/, $fragment2_data ) )[3] ) == 1 ) {
$linkage .= "_adjacent(Re1-Re2)";
} else {
$linkage .= "_different(Re1-Re2)";
}
} elsif ( abs( ( split( /\t/, $fragment1_data ) )[4] - ( split( /\t/, $fragment2_data ) )[4] ) == 1 ) {
$linkage = "Adjacent(Re1)";
} else {
$linkage = "Cis(not_adjacent_Re1)";
}
} else {
$linkage = "Trans"; # On different chromosomes.
}
#Determines the 5'-> 3' orientation of restriction enzymes to distinguish between ligation products.
##Firstly, check whether a read is in the forward or reverse orientation (+ or -) and process accordingly.
my $enzymes;
if ( $read1_strand eq '+' ) {
$enzymes = ( split( /\t/, $fragment1_data ) )[5] . "_" . ( split( /\t/, $fragment1_data ) )[6] . "+";
} else {
$enzymes = ( split( /\t/, $fragment1_data ) )[6] . "_" . ( split( /\t/, $fragment1_data ) )[5] . "-";
}
if ( $read2_strand eq '+' ) { #The reverse is true.
$enzymes .= "_" . ( split( /\t/, $fragment2_data ) )[6] . "_" . ( split( /\t/, $fragment2_data ) )[5] . "+";
} else {
$enzymes .= "_" . ( split( /\t/, $fragment2_data ) )[5] . "_" . ( split( /\t/, $fragment2_data ) )[6] . "-";
}
my $digest_pattern = $linkage . "_" . $enzymes;
$digest_pattern =~ s/\n|\r//g; #Remove line breaks from the string.
#Determine the combined length of the di-tag pairs and distance between them
my $fragment1_length = ( split( /\t/, $fragment1_data ) )[2] - ( split( /\t/, $fragment1_data ) )[1];
my $fragment2_length = ( split( /\t/, $fragment2_data ) )[2] - ( split( /\t/, $fragment2_data ) )[1];
my $ditag_length = $fragment1_length + $fragment2_length;
$ditag_sizes{$ditag_length}++; #Record the di-tag length distribution
#Check whther the di-tag fall within the accepted size limits of the library
if ($insert_size_check) {
if ( ( $ditag_length > $config{longest} ) or ( $ditag_length < $config{shortest} ) ) {
print WRONG_SIZE "$read1\n";
print WRONG_SIZE "$read2\n";
$category_counter{Wrong_size}++;
next;
}
}
#Count the type of output generated - only correct size putative di-tags
if ( exists $digest_results{$digest_pattern} ) {
$digest_results{$digest_pattern}++;
} else {
$digest_results{$digest_pattern} = 1;
}
#Print to file valid HiC pairs.
if (
$digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1+_Re1_Re2-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1-_Re1_Re2+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1+_Re1_Re2+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1-_Re1_Re2-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1+_Re1_Re2-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1-_Re1_Re2+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1+_Re1_Re2+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1-_Re1_Re2-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1+_Re1_Re1-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1-_Re1_Re1+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1+_Re1_Re1+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re2_Re1-_Re1_Re1-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1+_Re1_Re1-"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1-_Re1_Re1+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1+_Re1_Re1+"
or $digest_pattern eq "Cis(not_adjacent_Re1)_Re1_Re1-_Re1_Re1-"
)
{
#Determine if these are close or far (separation >10kbp) cis pairs
if ( ( split( /\t/, $fragment1_data ) )[1] < ( split( /\t/, $fragment2_data ) )[1] ) { #Is fragment 1 upstream of fragment 2, or vice versa?
if ( ( ( split( /\t/, $fragment2_data ) )[2] - ( split( /\t/, $fragment1_data ) )[1] - $ditag_length ) > 10000 ) { #Determine separation distance
print HIC_READS $read1 . "\tCT:Z:FAR\n";
print HIC_READS $read2 . "\tCT:Z:FAR\n";
$category_counter{Cis_far}++;
} else {
print HIC_READS $read1 . "\tCT:Z:CLOSE\n";
print HIC_READS $read2 . "\tCT:Z:CLOSE\n";
$category_counter{Cis_close}++;
}
} else {
if ( ( ( split( /\t/, $fragment1_data ) )[2] - ( split( /\t/, $fragment2_data ) )[1] - $ditag_length ) > 10000 ) { #Determine separation distance
print HIC_READS $read1 . "\tCT:Z:FAR\n";
print HIC_READS $read2 . "\tCT:Z:FAR\n";
$category_counter{Cis_far}++;
} else {
print HIC_READS $read1 . "\tCT:Z:CLOSE\n";
print HIC_READS $read2 . "\tCT:Z:CLOSE\n";
$category_counter{Cis_close}++;
}
}
}
#Trans-ligations
elsif (
$digest_pattern eq "Trans_Re2_Re1+_Re1_Re2-"
or $digest_pattern eq "Trans_Re2_Re1-_Re1_Re2+"
or $digest_pattern eq "Trans_Re2_Re1+_Re1_Re2+"
or $digest_pattern eq "Trans_Re2_Re1-_Re1_Re2-"
or $digest_pattern eq "Trans_Re1_Re1+_Re1_Re2-"
or $digest_pattern eq "Trans_Re1_Re1-_Re1_Re2+"
or $digest_pattern eq "Trans_Re1_Re1+_Re1_Re2+"
or $digest_pattern eq "Trans_Re1_Re1-_Re1_Re2-"
or $digest_pattern eq "Trans_Re2_Re1+_Re1_Re1-"
or $digest_pattern eq "Trans_Re2_Re1-_Re1_Re1+"
or $digest_pattern eq "Trans_Re2_Re1+_Re1_Re1+"
or $digest_pattern eq "Trans_Re2_Re1-_Re1_Re1-"
or $digest_pattern eq "Trans_Re1_Re1+_Re1_Re1-"
or $digest_pattern eq "Trans_Re1_Re1-_Re1_Re1+"
or $digest_pattern eq "Trans_Re1_Re1+_Re1_Re1+"
or $digest_pattern eq "Trans_Re1_Re1-_Re1_Re1-"
)
{
print HIC_READS $read1 . "\tCT:Z:TRANS\n";
print HIC_READS $read2 . "\tCT:Z:TRANS\n";
$category_counter{"Trans-ligation"}++;
}
#No ligation Internal Re2:
elsif ( $digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re2_Re2+_Re2_Re2-' or $digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re2_Re2-_Re2_Re2+' ) {
print INTERNAL_RE2 "$read1\n";
print INTERNAL_RE2 "$read2\n";
$category_counter{"Internal_Re2"}++;
}
#Re-ligation:
elsif ( $digest_pattern eq 'Adjacent(Re1)_Re2_Re1+_Re1_Re2-' or $digest_pattern eq 'Adjacent(Re1)_Re2_Re1-_Re1_Re2+' ) {
print RE_LIGATION "$read1\n";
print RE_LIGATION "$read2\n";
$category_counter{"Re-ligation"}++;
}
#Self-ligation:
elsif ( $digest_pattern eq 'Same(Re1)_different(Re1-Re2)_Re2_Re1+_Re1_Re2-' or $digest_pattern eq 'Same(Re1)_different(Re1-Re2)_Re2_Re1-_Re1_Re2+' ) {
print SELF_LIGATION "$read1\n";
print SELF_LIGATION "$read2\n";
$category_counter{"Self-ligation"}++;
}
#No Ligation (other)
elsif ( $digest_pattern =~ /Same\(Re1\)/ ) {
print NO_LIGATION "$read1\n";
print NO_LIGATION "$read2\n";
$category_counter{"No_ligation"}++;
}
# #No ligation:
# elsif($digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re2_Re1+_Re2_Re1-' or $digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re2_Re1-_Re2_Re1+' or $digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re1_Re2-_Re1_Re2+' or $digest_pattern eq 'Same(Re1)_same(Re1-Re2)_Re1_Re2+_Re1_Re2-'){
#print "$digest_pattern\n";
# print "$digest_pattern\n";
# $category_counter{"No_ligation"}++;
# }
#Unclassified
else {
print UNCLASSIFIED "$read1\n";
print UNCLASSIFIED "$read2\n";
$category_counter{"Unclassified"}++;
}
}
if ( $category_counter{Invalid_format} ) {
warn "File $filename contained $category_counter{Invalid_format} pairs that were removed for not being in the correct SAM format\n";
}
#Print the results to file
if ( $category_counter{Total} ) { #Only provide statisitcs if there are di-tags in the correct format
my $percent_no_ligation = $category_counter{No_ligation} / $category_counter{Total} * 100;
my $percent_re_ligation = $category_counter{"Re-ligation"} / $category_counter{Total} * 100;
my $percent_self_ligation = $category_counter{"Self-ligation"} / $category_counter{Total} * 100;
my $percent_internal_re2 = $category_counter{Internal_Re2} / $category_counter{Total} * 100;
my $percent_cis_close = $category_counter{Cis_close} / $category_counter{Total} * 100;
my $percent_cis_far = $category_counter{Cis_far} / $category_counter{Total} * 100;
my $percent_trans = $category_counter{"Trans-ligation"} / $category_counter{Total} * 100;
my $percent_unclassified = $category_counter{Unclassified} / $category_counter{Total} * 100;
my $percent_wrong_size = $category_counter{Wrong_size} / $category_counter{Total} * 100;
my $percent_unmapped = $category_counter{Unmapped} / $category_counter{Total} * 100;
my $valid_hic_pairs = $category_counter{Cis_close} + $category_counter{Cis_far} + $category_counter{"Trans-ligation"};
my $invalid_hic_pairs =
$category_counter{No_ligation} +
$category_counter{"Re-ligation"} +
$category_counter{"Self-ligation"} +
$category_counter{Internal_Re2} +
$category_counter{Unclassified} +
$category_counter{Wrong_size} +
$category_counter{Unmapped};
my $percent_valid_hic_pairs = $valid_hic_pairs / $category_counter{Total} * 100;
my $percent_invalid_hic_pairs = $invalid_hic_pairs / $category_counter{Total} * 100;
my $filename_for_summary = ( split( /\//, $filename ) )[-1]; #Removes folder extensions
print SUMMARY join( "\t",
$filename_for_summary, $category_counter{Total}, $valid_hic_pairs, $category_counter{Cis_close}, $category_counter{Cis_far},
$category_counter{"Trans-ligation"}, $invalid_hic_pairs, $category_counter{No_ligation}, $category_counter{"Re-ligation"}, $category_counter{"Self-ligation"},
$category_counter{Internal_Re2}, $category_counter{Unclassified}, $category_counter{Wrong_size}, $category_counter{Unmapped} );
print SUMMARY "\n";
#Create a line graph of di-tag length vs frequency
my %edited_ditag_sizes;
%edited_ditag_sizes = edit_ditag_sizes( \%ditag_sizes ); #Sort Di-tags in the size range of 1-2000 and aggregate in 10s
unless ( $config{r} eq '0' ) {
createFreqDistPlot( $filename, \%edited_ditag_sizes );
}
if ($hicup_executed) { #Write the ditag length to a file to be read by hicup for the HTML report (when this script is executed by the hicup master script)
# open(DITAG_LENGTHS, '>', $inOutFilenames{$filename}.'.ditag_lengths.'.$config{datestamp}.".temp") or die "Could not write to '$config{outdir}.$filename."."ditag_lengths."."$config{datestamp}.temp : $!";
# print DITAG_LENGTHS "Bin\tFrequency\n";
my $ditagLength_HTML_Report = ( fileNamer( $filename, \%config, 'filter', 0, 0, 0, 1, 0 ) )[1];
open( DITAG_LENGTHS, '>', $ditagLength_HTML_Report ) or die "Could not write to '$ditagLength_HTML_Report' : $!";
print DITAG_LENGTHS "Bin\tFrequency\n";
foreach my $bin ( sort ( keys %edited_ditag_sizes ) ) {
print DITAG_LENGTHS "$bin\t$edited_ditag_sizes{$bin}\n";
}
close DITAG_LENGTHS or warn "Could not close filehandle on '$ditagLength_HTML_Report' : $!";
}
} else {
warn "There are no di-tags in the correct format in file $filename.\n";
}
close HIC_READS or warn "Filehandle on '$config{outdir} . $outputfilename_base' did not close correctly, either an error or file contains no valid reads (check summary report) : $!";
close UNMAPPED;
close PAIRED_READS or die "Could not close filehandle on '$filename' : $!";
if ($insert_size_check) {
close WRONG_SIZE;
}
close NO_LIGATION;
close INTERNAL_RE2;
close SELF_LIGATION;
close RE_LIGATION;
close UNCLASSIFIED;
close INVALID;
}
########################################################################
#Subroutine "sonicate_hic":
#analyses the data assuming a sonication Hi-C protocol has been followed
sub sonicate_hic {
my $filename = $_[0];
warn "Filtering $filename\n" unless $config{quiet};
#Create outputfiles
#my $outputfilename_base = $filename;
my $outputfilename_base = fileNamer( $filename, \%config, 'filter' );
my $write_command;
my @output_files;
#$outputfilename_base =~ s/^.+\///; #Remove folder references
if ( $config{samtools} and $config{zip} ) {
#$file_extension = '.bam'; #BAM format
$write_command = '| samtools view -bSh 2>/dev/null - >';
} elsif ( $config{zip} ) {
#$file_extension = '.sam.gz'; #SAM format then compressed
$write_command = "| gzip -c - >";
} else {
#$file_extension = '.sam'; #SAM format
$write_command = ">";
}
#Create outputfiles
open( HIC_READS, $write_command . $config{outdir} . $outputfilename_base ) or die $!;
push( @output_files, $config{outdir} . $outputfilename_base );
#For the reject files, determine the names of the files here, using the output from the fileNamer
#subroutine as a base
#Determine the file extension of the files
$outputfilename_base =~ s/\.filt\.(bam|sam|sam\.gz)$//;
my $file_extension = $1;
$file_extension = '.filter.' . $file_extension;
#$outputfilename_base =~ s/\.filt\.(bam|sam|sam\.gz)$//;
if ($insert_size_check) {
open( WRONG_SIZE, $write_command . $rejdir . '/' . $outputfilename_base . "_wrong_size" . $file_extension ) or die $!;
push( @output_files, $rejdir . $outputfilename_base . "_wrong_size" . $file_extension );
}
open( INVALID, $write_command . $rejdir . '/' . $outputfilename_base . "_invalid" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_invalid" . $file_extension );
open( SAME_CIRCULARISED, $write_command . $rejdir . '/' . $outputfilename_base . "_same_circularised" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_same_circularised" . $file_extension );
open( SAME_DANGLING_ENDS, $write_command . $rejdir . '/' . $outputfilename_base . "_same_dangling_ends" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_same_dangling_ends" . $file_extension );
open( SAME_INTERNAL, $write_command . $rejdir . '/' . $outputfilename_base . "_same_internal" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_same_internal" . $file_extension );
open( RE_LIGATION, $write_command . $rejdir . '/' . $outputfilename_base . "_re_ligation" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_re_ligation" . $file_extension );
open( CONTIGUOUS, $write_command . $rejdir . '/' . $outputfilename_base . "_contiguous" . $file_extension ) or die $!;
push( @output_files, $rejdir . '/' . $outputfilename_base . "_contiguous" . $file_extension );
#Create the category counter
my %category_counter = (
'wrong_size' => 0,
'same_circularised' => 0,
'same_dangling_ends' => 0,
'same_internal' => 0,
're_ligation' => 0,
'contiguous' => 0,
'cis_close' => 0,