forked from deweylab/RSEM
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrsem-calculate-expression
executable file
·1588 lines (1129 loc) · 70.4 KB
/
rsem-calculate-expression
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/env perl
use Getopt::Long qw(:config no_auto_abbrev);
use Pod::Usage;
use File::Basename;
use FindBin;
use lib $FindBin::RealBin;
use rsem_perl_utils qw(runCommand collectResults showVersionInfo getSAMTOOLS hasPolyA);
use Env qw(@PATH);
@PATH = ($FindBin::RealBin, "$FindBin::RealBin/" . getSAMTOOLS(), @PATH);
use strict;
use warnings;
# Fork specific
use Data::Dumper qw(Dumper);
my $DIESTRING = "ERROR: Something is wrong with the parameters you are using, either an incorrect name or combination of parameters. Please run:".
"\n".$0." -h"."\n".
"and make sure you are using the correct parameter names.\n";
#const
my $BURNIN = 200;
my $NCV = 1000;
my $SAMPLEGAP = 1;
my $CONFIDENCE = 0.95;
my $NSPC = 50;
my $NMB = 1024; # default
my $status = 0;
my $read_type = 1; # default, single end with qual
my $strandedness = "none"; # none, forward, reverse
my $probF = undef; # deprecated
my $strand_specific = undef; # deprecated
my $bowtie_path = "";
my $C = 2;
my $E = 99999999;
my $L = 25;
my $maxHits = 200;
my $chunkMbs = 0; # 0 = use bowtie default
my $phred33 = 0;
my $phred64 = 0;
my $solexa = 0;
my $is_alignment = 0;
my $faiF = "";
my $tagName = "XM";
my $minL = 1;
my $maxL = 1000;
my $mean = -1;
my $sd = 0;
my $estRSPD = 0;
my $B = 20;
my $nThreads = 1;
my $genBamF = 1; # default is generating transcript bam file
my $genGenomeBamF = 0;
my $sampling = 0;
my $sort_bam_by_coordinate = 0;
my $sort_bam_by_read_name = 0;
my $sort_bam_memory = "1G"; # default as 1G per thread
my $calcPME = 0;
my $calcCI = 0;
my $single_cell_prior = 0;
my $quiet = 0;
my $help = 0;
my $paired_end = 0;
my $no_qual = 0;
my $keep_intermediate_files = 0;
my $bowtie2 = 0;
my $bowtie2_path = "";
my $bowtie2_mismatch_rate = 0.1;
my $bowtie2_k = 200;
my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast", "sensitive", "very_sensitive"
my $seed = "NULL";
my $appendNames = 0;
my $version = 0;
my $mTime = 0;
my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
my $mate1_list = "";
my $mate2_list = "";
my $inpF = "";
my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ('') x 7;
my $gap = 32;
my $alleleS = 0;
my $star = 0;
my $star_path = '';
my $star_gzipped_read_file = 0;
my $star_bzipped_read_file = 0;
my $star_output_genome_bam = 0;
my $star_shared_memory = 0;
my $star_sam_unmapped = 0;
my $SHARED_MEMORY_METHOD = "NoSharedMemory"; # Default
my $SAM_UNMAPPED = "Within"; # Default
my $EXPECTED_ARGS = 3; # List of input, <Optional; List of Mates>, Reference, Output prefix, <Optional; Shared memory setting>
# pRSEM options
my $run_prsem = 0;
my $chipseq_target_read_files = '';
my $chipseq_control_read_files = '';
my $chipseq_peak_file = '';
my $partition_model = 'pk';
my $chipseq_read_files_multi_targets = ''; ## read files for multiple targets
## delimited by comma
my $chipseq_bed_files_multi_targets = ''; ## BED files for multiple targets
## delimited by comma
my $cap_stacked_chipseq_reads = 0; ## for multiple targets, remove redundant
## reads aligned to the same position
my $n_max_stacked_chipseq_reads = 5; ## as above
GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
"temporary-folder=s" => \$temp_dir,
"no-qualities" => \$no_qual,
"paired-end" => \$paired_end,
"strandedness=s" => \$strandedness,
"alignments" => \$is_alignment,
"fai=s" => \$faiF,
"tag=s" => \$tagName,
"seed-length=i" => \$L,
"bowtie-path=s" => \$bowtie_path,
"bowtie-n=i" => \$C,
"bowtie-e=i" => \$E,
"bowtie-m=i" => \$maxHits,
"bowtie-chunkmbs=i" => \$chunkMbs,
"phred33-quals" => \$phred33,
"phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
"solexa-quals" => \$solexa,
"bowtie2" => \$bowtie2,
"bowtie2-path=s" => \$bowtie2_path,
"bowtie2-mismatch-rate=f" => \$bowtie2_mismatch_rate,
"bowtie2-k=i" => \$bowtie2_k,
"bowtie2-sensitivity-level=s" => \$bowtie2_sensitivity_level,
"fragment-length-min=i" => \$minL,
"fragment-length-max=i" => \$maxL,
"fragment-length-mean=f" => \$mean,
"fragment-length-sd=f" => \$sd,
"estimate-rspd" => \$estRSPD,
"num-rspd-bins=i" => \$B,
"p|num-threads=i" => \$nThreads,
"append-names" => \$appendNames,
"sampling-for-bam" => \$sampling,
"no-bam-output" => sub { $genBamF = 0; },
"output-genome-bam" => \$genGenomeBamF,
"sort-bam-by-coordinate" => \$sort_bam_by_coordinate,
"sort-bam-by-read-name" => \$sort_bam_by_read_name,
"sort-bam-memory-per-thread=s" => \$sort_bam_memory,
"single-cell-prior" => \$single_cell_prior,
"calc-pme" => \$calcPME,
"gibbs-burnin=i" => \$BURNIN,
"gibbs-number-of-samples=i" => \$NCV,
"gibbs-sampling-gap=i", \$SAMPLEGAP,
"calc-ci" => \$calcCI,
"ci-credibility-level=f" => \$CONFIDENCE,
"ci-memory=i" => \$NMB,
"ci-number-of-samples-per-count-vector=i" => \$NSPC,
'star' => \$star,
'star-path=s' => \$star_path,
"star-gzipped-read-file" => \$star_gzipped_read_file,
"star-bzipped-read-file" => \$star_bzipped_read_file,
"star-output-genome-bam" => \$star_output_genome_bam,
"star-shared-memory" => \$star_shared_memory,
"star-sam-unmapped" => \$star_sam_unmapped,
"seed=i" => \$seed,
'run-pRSEM' => \$run_prsem,
'chipseq-target-read-files=s' => \$chipseq_target_read_files,
## delimited by comma if more than one
'chipseq-control-read-files=s' => \$chipseq_control_read_files,
## delimited by comma if more than one
'chipseq-read-files-multi-targets=s' => \$chipseq_read_files_multi_targets,
## delimited by comma
'chipseq-bed-files-multi-targets=s' => \$chipseq_bed_files_multi_targets,
## delimited by comma
'cap-stacked-chipseq-reads' => \$cap_stacked_chipseq_reads,
'n-max-stacked-chipseq-reads=i' => \$n_max_stacked_chipseq_reads,
'chipseq-peak-file=s' => \$chipseq_peak_file,
'partition-model=s' => \$partition_model,
"time" => \$mTime,
# deprecated
"strand-specific" => \$strand_specific,
"forward-prob=f" => \$probF,
"sam|bam" => \$is_alignment,
# help
"version" => \$version,
"q|quiet" => \$quiet,
"h|help" => \$help) or die( $DIESTRING ); #pod2usage(-exitval => 2, -verbose => 2);
pod2usage(-verbose => 2) if ($help == 1);
&showVersionInfo($FindBin::RealBin) if ($version == 1);
#check parameters and options
#print "NARGS:" . scalar(@ARGV)."\n\n";
#print Dumper \@ARGV;
#print "\n";
#die;
# mbelmadani: Update EXPECTED_ARGS
$EXPECTED_ARGS += ($paired_end + $star_shared_memory);
if ($star_shared_memory){
$SHARED_MEMORY_METHOD = $ARGV[$EXPECTED_ARGS-1]; # Assuming this will always be the last argument.
}
if ($star_sam_unmapped){
$SAM_UNMAPPED = "None";
}
pod2usage(-msg => "Invalid number of arguments! Expected ".$EXPECTED_ARGS." ; got " . scalar(@ARGV) . " ." , -exitval => 2, -verbose => 0) if (scalar(@ARGV) != $EXPECTED_ARGS);
if ($is_alignment) {
pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals, --solexa-quals, --bowtie2, --bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k, --bowtie2-sensitivity-level, --star, --star-path, and --star-output-genome-bam cannot be set if input is SAM/BAM/CRAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa || $bowtie2 || $bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive" || $star || $star_path ne "" || $star_output_genome_bam);
}
else {
pod2usage(-msg => "If --no-qualities is set, neither --phred33-quals, --phred64-quals or --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($no_qual && ($phred33 + $phred64 + $solexa > 0)); pod2usage(-msg => "Only one of --phred33-quals, --phred64-quals, and --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
pod2usage(-msg => "--bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if bowtie aligner is used!", -exitval => 2, -verbose => 2) if (!$bowtie2 && ($bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive"));
pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m cannot be set if bowtie2 aligner is used!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200));
pod2usage(-msg => "Mismatch rate must be within [0, 1]!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie2_mismatch_rate < 0.0 || $bowtie2_mismatch_rate > 1.0));
pod2usage(-msg => "Sensitivity level must be one of \"very_fast\", \"fast\", \"sensitive\", and \"very_sensitive\"!", -exitval => 2, -verbose => 2) if ($bowtie2 && (($bowtie2_sensitivity_level ne "very_fast") && ($bowtie2_sensitivity_level ne "fast") && ($bowtie2_sensitivity_level ne "sensitive") && ($bowtie2_sensitivity_level ne "very_sensitive")));
if ($faiF ne "") { print "Warning: There is no need to set --fai if you ask RSEM to align reads for you.\n" }
}
pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
pod2usage(-msg => "The seed for random number generator must be a non-negative 32bit integer!\n", -exitval => 2, -verbose => 2) if (($seed ne "NULL") && ($seed < 0 || $seed > 0xffffffff));
pod2usage(-msg => "The credibility level should be within (0, 1)!\n", -exitval => 2, -verbose => 2) if ($CONFIDENCE <= 0.0 || $CONFIDENCE >= 1.0);
pod2usage(-msg => "Gzipped read files can only be used for aligner STAR\n", -exitval=>2, -verbose =>2) if ( ( $star == 0 ) && ( $star_gzipped_read_file != 0));
pod2usage(-msg => "Bzipped read files can only be used for aligner STAR\n", -exitval=>2, -verbose =>2) if ( ( $star == 0 ) && ( $star_bzipped_read_file != 0));
pod2usage(-msg => "Specify shared memory options for aligner STAR with --star-shared-memory. \n Options: NoSharedMemory, LoadAndKeep, LoadAndRemove, LoadAndExit.", -exitval=>2, -verbose =>0) if ( ( $star_shared_memory == 0 ) && ( $star != 0));
## pod2usage(-msg => "Switch to exclude unmappable read in output SAM from STAR.", -exitval=>2, -verbose =>0) if ( ( $star_sam_unmapped != 0 ) && ( $star != 0) );
if ( $run_prsem ) {
my $msg = '';
if ( ( $chipseq_peak_file eq '' ) &&
( ( $chipseq_target_read_files eq '' ) ||
( $chipseq_control_read_files eq '' ) ||
( $bowtie_path eq '' ) ) &&
( ( $chipseq_read_files_multi_targets eq '' ) ||
( $bowtie_path eq '' ) ) &&
( $chipseq_bed_files_multi_targets eq '' )
) {
$msg = "please define one set of the following options to run pRSEM:\n" .
"1. --chipseq-peak-file <string>\n" .
"2. --chipseq-target-read-files <string> and\n" .
" --chipseq-control-read-files <string> and\n" .
" --bowtie-path <path>\n" .
"3. --chipseq-read-files-multi-targets <string> and\n" .
" --bowtie-path <path>\n" .
"4. --chipseq-bed-files-multi-targets <string>\n";
}
my @prsem_partition_models = (
'pk', 'pk_lgtnopk',
'lm3', 'lm4', 'lm5', 'lm6',
'nopk_lm2pk', 'nopk_lm3pk', 'nopk_lm4pk', 'nopk_lm5pk',
'pk_lm2nopk', 'pk_lm3nopk', 'pk_lm4nopk', 'pk_lm5nopk',
'cmb_lgt'
);
my %prtmdl2one = ();
foreach my $prtmdl (@prsem_partition_models) {
$prtmdl2one{$prtmdl} = 1;
}
if ( exists $prtmdl2one{$partition_model} ) {
if ( ( $partition_model eq 'cmb_lgt' ) &&
( ( $chipseq_read_files_multi_targets eq '' ) &&
( $chipseq_bed_files_multi_targets eq '' ) ) ){
$msg = 'either --chipseq-read-files-multi-targets <string> or ' .
'--chipseq-bed-files-multi-targets <string> needs to be ' .
"defined for pRSEM's partition model: '$partition_model'";
} elsif ( ( $partition_model ne 'pk' ) &&
( $partition_model ne 'cmb_lgt' ) &&
( ( $chipseq_target_read_files eq '' ) ||
( $chipseq_control_read_files eq '' ) ||
( $bowtie_path eq '' ) ) ){
$msg = '--chipseq-target-read-files <string> and ' .
'--chipseq-control-read-files <string> and ' .
'--bowtie-path <path> need to be defined for ' .
"pRSEM's partition model: '$partition_model'";
}
} else {
$msg = '--partition-model <string> must be one of [' .
join(', ', @prsem_partition_models) . "]";
}
if ( $msg ne '' ) {
pod2usage(-msg => "$msg\n", -exitval => 2, -verbose => 2);
}
if ( ( $partition_model ne 'cmb_lgt' ) &&
( ( $chipseq_read_files_multi_targets ne '' ) ||
( $chipseq_bed_files_multi_targets ne '' ) ) ) {
print "\nCombining signals from multiple sources, partition model is set to 'cmb_lgt'\n\n";
$partition_model = 'cmb_lgt';
}
}
if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
# strandedness
if (!defined($probF)) {
if ($strandedness eq "forward" || ($strandedness eq "none" && defined($strand_specific))) {
$probF = 1.0;
}
elsif ($strandedness eq "reverse") {
$probF = 0.0;
}
else {
$probF = 0.5;
}
}
pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
if ($paired_end) {
if ($no_qual) { $read_type = 2; }
else { $read_type = 3; }
}
else {
if ($no_qual) { $read_type = 0; }
else { $read_type = 1; }
}
# mbelmadani: The 4th argument is used for shared memory facilities.
# The sampleName here is also really just the output directory/prefix.
if (!$paired_end) {
if ($is_alignment) {
$inpF = $ARGV[0];
}
else {
$mate1_list = $ARGV[0];
}
$refName = $ARGV[1];
$sampleName = $ARGV[2];
}
else {
$mate1_list = $ARGV[0];
$mate2_list = $ARGV[1];
$refName = $ARGV[2];
$sampleName = $ARGV[3];
}
if (((-e "$refName.ta") && !(-e "$refName.gt")) || (!(-e "$refName.ta") && (-e "$refName.gt"))) {
print "Allele-specific expression related reference files are corrupted!\n";
exit(-1);
}
$alleleS = (-e "$refName.ta") && (-e "$refName.gt");
pod2usage(-msg => "RSEM reference cannot contain poly(A) tails if you want to use STAR aligner!", -exitval => 2, -verbose => 2) if ($star && (&hasPolyA("$refName.seq")));
if ($genGenomeBamF) {
open(INPUT, "$refName.ti");
my $line = <INPUT>; chomp($line);
close(INPUT);
my ($M, $type) = split(/ /, $line);
pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
}
my $pos = rindex($sampleName, '/');
if ($pos < 0) { $sampleToken = $sampleName; }
else { $sampleToken = substr($sampleName, $pos + 1); }
if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
$stat_dir = "$sampleName.stat";
if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
$imdName = "$temp_dir/$sampleToken";
$statName = "$stat_dir/$sampleToken";
if (!$is_alignment && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
my ($mate_minL, $mate_maxL) = (1, $maxL);
if ($bowtie_path ne "") { $bowtie_path .= "/"; }
if ($bowtie2_path ne "") { $bowtie2_path .= "/"; }
if ($star_path ne '') { $star_path .= '/'; }
my $command = "";
if (!$is_alignment) {
if ( $star ) {
## align reads by STAR
my $star_genome_path = dirname($refName);
$command = "$star_path"."STAR" .
## ENCODE3 pipeline parameters
" --genomeDir $star_genome_path " .
## ' --outSAMunmapped Within ' .
' --outFilterType BySJout ' .
' --outSAMattributes NH HI AS NM MD ' .
' --outFilterMultimapNmax 20 ' .
' --outFilterMismatchNmax 999 ' .
' --outFilterMismatchNoverLmax 0.04 ' .
' --alignIntronMin 20 ' .
' --alignIntronMax 1000000 ' .
' --alignMatesGapMax 1000000 ' .
' --alignSJoverhangMin 8 ' .
' --alignSJDBoverhangMin 1 ' .
' --sjdbScore 1 ' .
" --runThreadN $nThreads " .
##
## different than ENCODE3 pipeline
' --genomeLoad '. $SHARED_MEMORY_METHOD .' ' .
' --outSAMunmapped '. $SAM_UNMAPPED .' ' .
##
## different than ENCODE3 pipeline, which sorts output BAM
## no need to do it here to save time and memory
' --outSAMtype BAM Unsorted ' .
##
## unlike ENCODE3, we don't output bedGraph files
' --quantMode TranscriptomeSAM '.
' --outSAMheaderHD \@HD VN:1.4 SO:unsorted '.
## define output file prefix
" --outFileNamePrefix $imdName ";
##
#<<<<<<< HEAD
#if ( $gzipped_read_file ) {
# $command .= ' --readFilesCommand zcat ';
#} elsif ( $bzipped_read_file ) {
# $command .= ' --readFilesCommand bzcat ';
#}
#if ( $read_type == 0 || $read_type == 1 ) {
# $command .= " --readFilesIn $mate1_list ";
#} else {
# $command .= " --readFilesIn $mate1_list $mate2_list";
#}
#=======
if ( $star_gzipped_read_file ) {
$command .= ' --readFilesCommand zcat ';
} elsif ( $star_bzipped_read_file ) {
$command .= ' --readFilesCommand bzip2 -c ';
}
#>>>>>>> master
if ( $read_type == 0 || $read_type == 1 ) {
$command .= " --readFilesIn $mate1_list ";
} else {
$command .= " --readFilesIn $mate1_list $mate2_list";
}
} elsif (!$bowtie2) {
$command = $bowtie_path."bowtie";
if ($no_qual) { $command .= " -f"; }
else { $command .= " -q"; }
if ($phred33) { $command .= " --phred33-quals"; }
elsif ($phred64) { $command .= " --phred64-quals"; }
elsif ($solexa) { $command .= " --solexa-quals"; }
$command .= " -n $C -e $E -l $L";
if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
if ($probF == 1.0) { $command .= " --norc"; }
elsif ($probF == 0.0) { $command .= " --nofw"; }
$command .= " -p $nThreads -a -m $maxHits -S";
if ($quiet) { $command .= " --quiet"; }
$command .= " $refName";
if ($read_type == 0 || $read_type == 1) {
$command .= " $mate1_list";
}
else {
$command .= " -1 $mate1_list -2 $mate2_list";
}
# pipe to samtools to generate a BAM file
$command .= " | samtools view -S -b -o $imdName.bam -";
}
else {
$command = $bowtie2_path."bowtie2";
if ($no_qual) { $command .= " -f"; }
else { $command .= " -q"; }
if ($phred33) { $command .= " --phred33"; }
elsif ($phred64) { $command .= " --phred64"; }
elsif ($solexa) { $command .= " --solexa-quals"; }
if ($bowtie2_sensitivity_level eq "very_fast") { $command .= " --very-fast"; }
elsif ($bowtie2_sensitivity_level eq "fast") { $command .= " --fast"; }
elsif ($bowtie2_sensitivity_level eq "sensitive") { $command .= " --sensitive"; }
else { $command .= " --very-sensitive"; }
$command .= " --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-$bowtie2_mismatch_rate";
if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL --no-mixed --no-discordant"; }
if ($probF == 1.0) { $command .= " --norc"; }
elsif ($probF == 0.0) { $command .= " --nofw"; }
$command .= " -p $nThreads -k $bowtie2_k";
if ($quiet) { $command .= " --quiet"; }
$command .= " -x $refName";
if ($read_type == 0 || $read_type == 1) {
$command .= " -U $mate1_list";
}
else {
$command .= " -1 $mate1_list -2 $mate2_list";
}
# pipe to samtools to generate a BAM file
$command .= " | samtools view -S -b -o $imdName.bam -";
}
if ($mTime) { $time_start = time(); }
&runCommand($command);
if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
$inpF = "$imdName.bam";
if ( $star ) {
my $star_tr_bam = $imdName . 'Aligned.toTranscriptome.out.bam';
rename $star_tr_bam, $inpF
or die "can't rename $star_tr_bam to $inpF: $!\n";
rmdir $imdName . "_STARtmp/";
my $star_genome_bam = $imdName . "Aligned.out.bam";
my $rsem_star_genome_bam = $sampleName.'.STAR.genome.bam';
if ( $star_output_genome_bam ) {
rename $star_genome_bam, $rsem_star_genome_bam or die
"can't move $star_genome_bam to $rsem_star_genome_bam: $!\n";
} else {
unlink $star_genome_bam or die "can't remove $star_genome_bam: $!\n";
}
}
}
if ( $sort_bam_by_read_name ) {
my $sorted_bam = "$imdName.sorted.bam";
$command = "samtools sort -n -@ $nThreads -m $sort_bam_memory -o $sorted_bam $inpF";
&runCommand($command);
if (!$is_alignment) {
$command = "rm -f $inpF";
&runCommand($command);
}
$inpF = $sorted_bam;
}
if ($mTime) { $time_start = time(); }
$command = "rsem-parse-alignments $refName $imdName $statName $inpF $read_type";
if ($faiF ne "") { $command .= " -t $faiF"; }
if ($tagName ne "") { $command .= " -tag $tagName"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
$command = "rsem-build-read-index $gap";
if ($read_type == 0) { $command .= " 0 $quiet $imdName\_alignable.fa"; }
elsif ($read_type == 1) { $command .= " 1 $quiet $imdName\_alignable.fq"; }
elsif ($read_type == 2) { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
elsif ($read_type == 3) { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
else { print "Impossible! read_type is not in [1,2,3,4]!\n"; exit(-1); }
&runCommand($command);
my $doesOpen = open(OUTPUT, ">$imdName.mparams");
if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
print OUTPUT "$minL $maxL\n";
print OUTPUT "$probF\n";
print OUTPUT "$estRSPD\n";
print OUTPUT "$B\n";
print OUTPUT "$mate_minL $mate_maxL\n";
print OUTPUT "$mean $sd\n";
print OUTPUT "$L\n";
close(OUTPUT);
my @seeds = ();
if ($seed ne "NULL") {
srand($seed);
for (my $i = 0; $i < 3; $i++) {
push(@seeds, int(rand(1 << 32)));
}
}
$command = "rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
if ($genBamF) {
$command .= " -b $inpF";
if ($faiF ne "") { $command .= " 1 $faiF"; }
else { $command .= " 0"; }
if ($sampling) { $command .= " --sampling"; }
if ($seed ne "NULL") { $command .= " --seed $seeds[0]"; }
}
if ($calcPME || $calcCI) { $command .= " --gibbs-out"; }
if ($appendNames) { $command .= " --append-names"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
if ($alleleS) {
&collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
else {
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
if ($genBamF) {
if ($genGenomeBamF) {
$command = "rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
&runCommand($command);
}
if ($sort_bam_by_coordinate) {
$command = "samtools sort -@ $nThreads -m $sort_bam_memory -o $sampleName.transcript.sorted.bam $sampleName.transcript.bam";
&runCommand($command);
$command = "samtools index $sampleName.transcript.sorted.bam";
&runCommand($command);
if ($genGenomeBamF) {
$command = "samtools sort -@ $nThreads -m $sort_bam_memory -o $sampleName.genome.sorted.bam $sampleName.genome.bam";
&runCommand($command);
$command = "samtools index $sampleName.genome.sorted.bam";
&runCommand($command);
}
}
}
if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
if ($mTime) { $time_start = time(); }
if ($calcPME || $calcCI ) {
$command = "rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
$command .= " -p $nThreads";
if ($seed ne "NULL") { $command .= " --seed $seeds[1]"; }
if ($single_cell_prior) { $command .= " --pseudo-count 0.1"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
}
if ($calcPME || $calcCI) {
if ($alleleS) {
system("mv $sampleName.alleles.results $imdName.alleles.results.bak1");
system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
system("mv $sampleName.genes.results $imdName.genes.results.bak1");
&collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
else {
system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
system("mv $sampleName.genes.results $imdName.genes.results.bak1");
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
}
if ($calcCI) {
$command = "rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
$command .= " -p $nThreads";
if ($seed ne "NULL") { $command .= " --seed $seeds[2]"; }
if ($single_cell_prior) { $command .= " --pseudo-count 0.1"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
if ($alleleS) {
system("mv $sampleName.alleles.results $imdName.alleles.results.bak2");
system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
system("mv $sampleName.genes.results $imdName.genes.results.bak2");
&collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
else {
system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
system("mv $sampleName.genes.results $imdName.genes.results.bak2");
&collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
&collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
}
}
if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
if ($mTime) { $time_start = time(); }
## To-do: only run gibbs sampling once, either for pRSEM or uniform prior 1
if ( $run_prsem ) {
$command = "$FindBin::RealBin/pRSEM/prsem-calculate-expression " .
" --num-threads $nThreads " .
" --partition-model $partition_model " .
" --gibbs-burnin $BURNIN " .
" --gibbs-number-of-samples $NCV " .
" --gibbs-sampling-gap $SAMPLEGAP ";
####
## ChIP-seq peak file from single source
if ( $chipseq_peak_file ne '') { ## only for partition model pk
## need to add sanity check!!
$command .= " --chipseq-peak-file $chipseq_peak_file";
} elsif ( $partition_model eq 'cmb_lgt' ) { ## multi-sources
if ( $chipseq_bed_files_multi_targets ne '' ) { ## use bed over read
$command .= ' --chipseq-bed-files-multi-targets ' .
$chipseq_bed_files_multi_targets;
} elsif ( $chipseq_read_files_multi_targets ne '' ) {
$command .= ' --chipseq-read-files-multi-targets ' .
$chipseq_read_files_multi_targets .
" --bowtie-path $bowtie_path" ;
}
if ( $cap_stacked_chipseq_reads ) {
$command .= ' --cap-stacked-chipseq-reads ' .
" --n-max-stacked-chipseq-reads $n_max_stacked_chipseq_reads";
}
} else { ## ChIP-seq reads files from single source
$command .= " --chipseq-target-read-files $chipseq_target_read_files " .
" --bowtie-path $bowtie_path" ;
if ( $chipseq_control_read_files ne '' ) {
$command .= " --chipseq-control-read-files $chipseq_control_read_files";
}
}
if ( $quiet ) {
$command .= ' --quiet ';
}
$command .= " $refName $sampleName $statName $imdName";
&runCommand($command);
## collect pRSEM results
my $fiso_res = "$imdName.iso_res";
my $fgene_res = "$imdName.gene_res";
my $fprsem_iso_res = "${imdName}_prsem.iso_res";
my $fprsem_gene_res = "${imdName}_prsem.gene_res";
system("head -8 $fiso_res > $fprsem_iso_res" );
system("tail -5 $fiso_res >> $fprsem_iso_res" );
system("head -7 $fgene_res > $fprsem_gene_res");
system("tail -4 $fgene_res >> $fprsem_gene_res");
my $fstat_iso_results = "${statName}_uniform_prior_1.isoforms.results";
my $fstat_gene_results = "${statName}_uniform_prior_1.genes.results";
my $fiso_results = "${sampleName}.isoforms.results";
my $fgene_results = "${sampleName}.genes.results";
rename $fiso_results, $fstat_iso_results or die
"can't rename $fiso_results to $fstat_iso_results: $!\n";
rename $fgene_results, $fstat_gene_results or die
"can't rename $fgene_results to $fstat_gene_results: $!\n";
collectResults("isoform", $fprsem_iso_res, $fiso_results);
collectResults("gene", $fprsem_gene_res, $fgene_results);
}
if (!$keep_intermediate_files) {
&runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
}
if ($mTime) { $time_end = time(); }
if ($mTime) {
open(OUTPUT, ">$sampleName.time");
print OUTPUT "Aligning reads: $time_alignment s.\n";
print OUTPUT "Estimating expression levels: $time_rsem s.\n";
print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
# my $time_del = $time_end - $time_start;
# print OUTPUT "Delete: $time_del s.\n";
close(OUTPUT);
}
__END__
=head1 NAME
rsem-calculate-expression - Estimate gene and isoform expression from RNA-Seq data.
=head1 SYNOPSIS
rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
rsem-calculate-expression [options] --alignments [--paired-end] input reference_name sample_name
For STAR shared memory usage, use the setting as the last parameter.
rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name star_shared_memory
=head1 ARGUMENTS
=over
=item B<upstream_read_files(s)>
Comma-separated list of files containing single-end reads or upstream reads for paired-end data. By default, these files are assumed to be in FASTQ format. If the --no-qualities option is specified, then FASTA format is expected.
=item B<downstream_read_file(s)>
Comma-separated list of files containing downstream reads which are paired with the upstream reads. By default, these files are assumed to be in FASTQ format. If the --no-qualities option is specified, then FASTA format is expected.
=item B<input>
SAM/BAM/CRAM formatted input file. If "-" is specified for the filename, the input is instead assumed to come from standard input. RSEM requires all alignments of the same read group together. For paired-end reads, RSEM also requires the two mates of any alignment be adjacent. In addition, RSEM does not allow the SEQ and QUAL fields to be empty. See Description section for how to make input file obey RSEM's requirements.
=item B<reference_name>
The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
=item B<sample_name>
The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
=back
=head1 BASIC OPTIONS
=over
=item B<--paired-end>
Input reads are paired-end reads. (Default: off)
=item B<--no-qualities>
Input reads do not contain quality scores. (Default: off)
=item B<--strandedness> <none|forward|reverse>
This option defines the strandedness of the RNA-Seq reads. It recognizes three values: 'none', 'forward', and 'reverse'. 'none' refers to non-strand-specific protocols. 'forward' means all (upstream) reads are derived from the forward strand. 'reverse' means all (upstream) reads are derived from the reverse strand. If 'forward'/'reverse' is set, the '--norc'/'--nofw' Bowtie/Bowtie 2 option will also be enabled to avoid aligning reads to the opposite strand. For Illumina TruSeq Stranded protocols, please use 'reverse'. (Default: 'none')
=item B<-p/--num-threads> <int>
Number of threads to use. Both Bowtie/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
=item B<--alignments>
Input file contains alignments in SAM/BAM/CRAM format. The exact file format will be determined automatically. (Default: off)
=item B<--fai> <file>
If the header section of input alignment file does not contain reference sequence information, this option should be turned on. <file> is a FAI format file containing each reference sequence's name and length. Please refer to the SAM official website for the details of FAI format. (Default: off)
=item B<--bowtie2>
Use Bowtie 2 instead of Bowtie to align reads. Since currently RSEM does not handle indel, local and discordant alignments, the Bowtie2 parameters are set in a way to avoid those alignments. In particular, we use options '--sensitive --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-0.1' by default. The last parameter of '--score-min', '-0.1', is the negative of maximum mismatch rate. This rate can be set by option '--bowtie2-mismatch-rate'. If reads are paired-end, we additionally use options '--no-mixed' and '--no-discordant'. (Default: off)
=item B<--star>
Use STAR to align reads. Alignment parameters are from ENCODE3's STAR-RSEM pipeline. To save computational time and memory resources, STAR's Output BAM file is unsorted. It is stored in RSEM's temporary directory with name as 'sample_name.bam'. Each STAR job will have its own private copy of the genome in memory. (Default: off)
=item B<--append-names>
If gene_name/transcript_name is available, append it to the end of gene_id/transcript_id (separated by '_') in files 'sample_name.isoforms.results' and 'sample_name.genes.results'. (Default: off)
=item B<--seed> <uint32>
Set the seed for the random number generators used in calculating posterior mean estimates and credibility intervals. The seed must be a non-negative 32 bit integer. (Default: off)
=item B<--single-cell-prior>
By default, RSEM uses Dirichlet(1) as the prior to calculate posterior mean estimates and credibility intervals. However, much less genes are expressed in single cell RNA-Seq data. Thus, if you want to compute posterior mean estimates and/or credibility intervals and you have single-cell RNA-Seq data, you are recommended to turn on this option. Then RSEM will use Dirichlet(0.1) as the prior which encourage the sparsity of the expression levels. (Default: off)
=item B<--calc-pme>
Run RSEM's collapsed Gibbs sampler to calculate posterior mean estimates. (Default: off)
=item B<--calc-ci>
Calculate 95% credibility intervals and posterior mean estimates. The credibility level can be changed by setting '--ci-credibility-level'. (Default: off)
=item B<-q/--quiet>
Suppress the output of logging information. (Default: off)
=item B<-h/--help>
Show help information.
=item B<--version>
Show version information.
=back
=head1 OUTPUT OPTIONS
=over
=item B<--sort-bam-by-read-name>
Sort BAM file aligned under transcript coordidate by read name. Setting this option on will produce deterministic maximum likelihood estimations from independent runs. Note that sorting will take long time and lots of memory. (Default: off)
=item B<--no-bam-output>
Do not output any BAM file. (Default: off)
=item B<--sampling-for-bam>
When RSEM generates a BAM file, instead of outputting all alignments a read has with their posterior probabilities, one alignment is sampled according to the posterior probabilities. The sampling procedure includes the alignment to the "noise" transcript, which does not appear in the BAM file. Only the sampled alignment has a weight of 1. All other alignments have weight 0. If the "noise" transcript is sampled, all alignments appeared in the BAM file should have weight 0. (Default: off)
=item B<--output-genome-bam>
Generate a BAM file, 'sample_name.genome.bam', with alignments mapped to genomic coordinates and annotated with their posterior probabilities. In addition, RSEM will call samtools (included in RSEM package) to sort and index the bam file. 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' will be generated. (Default: off)
=item B<--sort-bam-by-coordinate>
Sort RSEM generated transcript and genome BAM files by coordinates and build associated indices. (Default: off)
=item B<--sort-bam-memory-per-thread> <string>
Set the maximum memory per thread that can be used by 'samtools sort'. <string> represents the memory and accepts suffices 'K/M/G'. RSEM will pass <string> to the '-m' option of 'samtools sort'. Note that the default used here is different from the default used by samtools. (Default: 1G)
=back
=head1 ALIGNER OPTIONS
=over
=item B<--seed-length> <int>
Seed length used by the read aligner. Providing the correct value is important for RSEM. If RSEM runs Bowtie, it uses this value for Bowtie's seed length parameter. Any read with its or at least one of its mates' (for paired-end reads) length less than this value will be ignored. If the references are not added poly(A) tails, the minimum allowed value is 5, otherwise, the minimum allowed value is 25. Note that this script will only check if the value >= 5 and give a warning message if the value < 25 but >= 5. (Default: 25)
=item B<--phred33-quals>
Input quality scores are encoded as Phred+33. (Default: on)
=item B<--phred64-quals>
Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
=item B<--solexa-quals>
Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
=item B<--bowtie-path> <path>
The path to the Bowtie executables. (Default: the path to the Bowtie executables is assumed to be in the user's PATH environment variable)
=item B<--bowtie-n> <int>
(Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
=item B<--bowtie-e> <int>
(Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
=item B<--bowtie-m> <int>
(Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
=item B<--bowtie-chunkmbs> <int>
(Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use Bowtie's default)
=item B<--bowtie2-path> <path>
(Bowtie 2 parameter) The path to the Bowtie 2 executables. (Default: the path to the Bowtie 2 executables is assumed to be in the user's PATH environment variable)
=item B<--bowtie2-mismatch-rate> <double>
(Bowtie 2 parameter) The maximum mismatch rate allowed. (Default: 0.1)