-
Notifications
You must be signed in to change notification settings - Fork 9
/
Copy pathRiboFlow.groovy
2256 lines (1672 loc) · 75.2 KB
/
RiboFlow.groovy
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
/*
vim: syntax=groovy
-*- mode: groovy;-*-
*/
/*
Developed and tested on:
N E X T F L O W ~ version 19.04.1
*/
// TODO
// DEDUPLICATE IN RNA-SEQ
// UPDATE DOCKER IMAGE
// Simplify Output
////////////////////////////////////////////////////////////////////////////////
////// General Function Definitions ////////////////////////////////////////////
String get_storedir(output_type){
new File( params.output.intermediates.base,
params.output.intermediates.get(output_type, output_type) )
.getCanonicalPath()
}
String get_publishdir(output_type){
new File( params.output.output.base,
params.output.output.get(output_type, output_type) )
.getCanonicalPath()
}
String get_dedup_method(String dedup_arg, String dedup_old){
/*
dedup_arg: User provided dedup method
dedup_old: In the first version, dedup vas a boolean parameter
We provide back-compatibility in the absenceo of dedup_arg
Possible dedup_arg types are
umi_tools: deduplication is based on umi umi_tools
in this case looks for UMI_EXTRACT and UMI_DEDUP
parameters if available to use them.
position: position based deduplication.
This is the method in the first version of ReiboFlow
none: Do not deduplicate
*/
def valid_methods = ["position", "umi_tools", "none"]
dedup_param = dedup_arg.toLowerCase()
if(dedup_param != "none"){
if(dedup_param in valid_methods){
return(dedup_param)
}
else {
println("Invalid deduplication method " + dedup_param + " . Valid methods are: ")
println( valid_methods.join(",") )
System.exit(1)
}
}
else {
// We make it compatible with the earlier versions.
// So if the dedup flag is true, and dedup_method is not provided
// it should be
// position based dedup
if( dedup_old.toLowerCase() != "false" ){
return("position")
}
else{
return("none")
}
}
}
////// General Function Definitions ////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////
dedup_method = get_dedup_method(params.get("dedup_method", "none").toString(),
params.get("deduplicate", false).toString() )
// to be deleted
//println(dedup_method)
//println(params.umi_tools_extract_arguments)
//System.exit(0)
fastq_base = params.input.get("fastq_base", "")
if(! fastq_base.endsWith("/") && fastq_base != ""){
fastq_base = "${fastq_base}/"
}
// Group input files into a list of tuples where each item is
// [ sample, fileindex, path_to_fastq_file]
Channel.from(params.input.fastq.collect{k,v ->
v.collect{ z -> [k, v.indexOf(z) + 1,
file("${fastq_base}${z}")] } })
.flatten().collate(3).into{ INPUT_SAMPLES_VERBOSE;
INPUT_SAMPLES_MD5;
INPUT_SAMPLES_EXISTENCE;
INPUT_SAMPLES_FASTQC;
INPUT_SAMPLES_CLIP;
INPUT_SAMPLES_LOG;
INPUT_SAMPLES_READ_LENGTH;
INPUT_FOR_METADATA}
// Create a log file of index <-> fastq-file correspondence
INPUT_SAMPLES_LOG.flatMap{ sample, index, fastq -> "${sample}\t${index}\t${fastq}" }
.collectFile(name: 'correspondence.txt', newLine: true)
.set{INPUT_SAMPLES_LOG_FILES}
// Move the above correspondence file to an output folder via a process
process write_fastq_correspondence{
executor 'local'
publishDir get_publishdir("stats"), mode: 'move'
input:
file(correspondence) from INPUT_SAMPLES_LOG_FILES
output:
file("index_fastq_correspondence.txt")
"""
cat ${correspondence} > index_fastq_correspondence.txt
"""
}
////////////////////////////////////////////////////////////////////////////////
////// Check File Existence ////////////////////////////////////////////////////
boolean file_exists(file_path) {
this_file = file(file_path)
assert this_file.exists()
return true
}
boolean hisat2_ref_exists(hisat2_ref) {
Channel.from( ["1.ht2", "2.ht2", "3.ht2","4.ht2","5.ht2","6.ht2", "7.ht2", "8.ht2"])
.map{ this_suffix -> file_exists( "${hisat2_ref}.${this_suffix}".replaceAll('\\*', "") ) }
return true
}
boolean bt2_ref_exists(bt2_ref) {
Channel.from( ["1.bt2", "2.bt2", "3.bt2","4.bt2","rev.1.bt2","rev.2.bt2"])
.map{ this_suffix -> file_exists( "${bt2_ref}.${this_suffix}".replaceAll('\\*', "") ) }
return true
}
if(params.do_check_file_existence){
// Make Sure Fastq Files Exist
INPUT_SAMPLES_EXISTENCE.map{ sample, index, this_file -> file_exists(this_file) }
// Make Sure bt2 and hisat reference files exist.
bt2_ref_exists( params.input.reference.filter )
bt2_ref_exists( params.input.reference.transcriptome )
if( params.input.reference.get("genome", false) ){
hisat2_ref_exists( params.input.reference.genome )
}
if( params.input.reference.get("post_genome", false) ){
bt2_ref_exists( params.input.reference.post_genome )
}
file_exists(params.input.reference.regions)
file_exists(params.input.reference.transcript_lengths)
root_meta_file = params.input.get("root_meta", false)
if( root_meta_file ){
file_exists(root_meta_file)
}
}
////// Check File Existence ////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////
//////////////////////// P R O C E S S E S /////////////////////////////
////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* RAW_FASTQC */
process raw_fastqc{
publishDir get_publishdir("fastqc")+"/raw", mode: 'copy'
input:
set val(sample), val(index), file(fastq) from INPUT_SAMPLES_FASTQC
output:
set val(sample), file("${sample}.${index}_fastqc.html"),
file("${sample}.${index}_fastqc.zip") into RAW_FASTQC_OUT
when:
params.do_fastqc
"""
if [ ! -f ${sample}.${index}.fastq.gz ]; then
ln -s $fastq ${sample}.${index}.fastq.gz
fi
fastqc ${sample}.${index}.fastq.gz --outdir=\$PWD -t ${task.cpus}
"""
}
// RAW_FASTQC
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* CLIP */
process clip{
storeDir get_storedir("clip")
input:
set val(sample), val(index), file(fastq) from INPUT_SAMPLES_CLIP
output:
set val(sample), val(index), file("${sample}.${index}.clipped.fastq.gz") into CLIP_OUT
set val(sample), val(index), file("${sample}.${index}.clipped.log") into CLIP_LOG
"""
cutadapt --cores=${task.cpus} ${params.clip_arguments} ${fastq} 2>${sample}.${index}.clipped.log \
| gzip -c > ${sample}.${index}.clipped.fastq.gz
"""
}
// CLIP
///////////////////////////////////////////////////////////////////////////////////////
CLIP_OUT.into{ CLIP_OUT_FASTQC; CLIP_OUT_DEDUP; CLIP_OUT_FILTER ; CLIP_OUT_READ_LENGTH}
///////////////////////////////////////////////////////////////////////////////////////
/* EXTRACT UMI via UMI_tools */
process extract_umi_via_umi_tools{
storeDir get_storedir("umi_tools") + "/" + params.output.merged_lane_directory
input:
set val(sample), val(index), file(fastq) from CLIP_OUT_DEDUP
output:
set val(sample), val(index), file("${sample}.${index}.umi_extracted.fastq.gz") into UMI_EXTRACT_OUT
set val(sample), val(index), file("${sample}.${index}.umi_extracted.log") into UMI_EXTRACT_LOG
when:
dedup_method == "umi_tools"
"""
umi_tools extract -I ${fastq} -S ${sample}.${index}.umi_extracted.fastq.gz \
-L ${sample}.${index}.umi_extracted.log \
${params.get("umi_tools_extract_arguments", "")}
"""
}
/* EXTRACT UMI via UMI_tools */
///////////////////////////////////////////////////////////////////////////////////////
if(dedup_method == "none" || dedup_method == "position"){
CLIP_OUT_FILTER.set{ FILTER_INPUT_FASTQ }
}
else if(dedup_method == "umi_tools"){
UMI_EXTRACT_OUT.set{ FILTER_INPUT_FASTQ }
}
///////////////////////////////////////////////////////////////////////////////////////
/* CLIPPED FASTQC */
process clipped_fastqc{
publishDir get_publishdir("fastqc") + "/clipped", mode: 'copy'
input:
set val(sample), val(index), file(fastq) from CLIP_OUT_FASTQC
output:
set val(sample), file("${sample}.${index}.clipped_fastqc.html"),
file("${sample}.${index}.clipped_fastqc.zip") into CLIPPED_FASTQC_OUT
when:
params.do_fastqc
"""
if [ ! -f ${sample}.${index}.clipped.fastq.gz ]; then
ln -s $fastq ${sample}.${index}.clipped.fastq.gz
fi
fastqc ${sample}.${index}.clipped.fastq.gz --outdir=\$PWD -t ${task.cpus}
"""
}
// CLIPPED FASTQC
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* FILTER */
// Reads are mapped against (typically) rRNA, tRNA, adapter sequneces and etc
// that have no use for downstream analysis
// So we take the UNaligned reads from this process and use it for downstream processing
FILTER_INDEX = Channel.from([[
params.input.reference.filter
.split('/')[-1]
.replaceAll('\\*$', "")
.replaceAll('\\.$', ""),
file(params.input.reference.filter),
]])
process filter{
storeDir get_storedir("filter")
input:
set val(sample), val(index), file(fastq) from FILTER_INPUT_FASTQ
set val(bowtie2_index_base), file(bowtie2_index_files) from FILTER_INDEX.first()
output:
set val(sample), val(index), file("${sample}.${index}.filter.bam") \
into FILTER_BAM
set val(sample), val(index), file("${sample}.${index}.filter.bam.bai") \
into FILTER_BAI
set val(sample), val(index), file("${sample}.${index}.aligned.filter.fastq.gz") \
into FILTER_ALIGNED
set val(sample), val(index), file("${sample}.${index}.unaligned.filter.fastq.gz") \
into FILTER_UNALIGNED
set val(sample), val(index), file("${sample}.${index}.filter.log") \
into FILTER_LOG
set val(sample), val(index), file("${sample}.${index}.filter.stats") \
into FILTER_STATS
"""
bowtie2 ${params.alignment_arguments.filter} \
-x ${bowtie2_index_base} -q ${fastq} \
--threads ${task.cpus} \
--al-gz ${sample}.${index}.aligned.filter.fastq.gz \
--un-gz ${sample}.${index}.unaligned.filter.fastq.gz \
2> ${sample}.${index}.filter.log \
| samtools view -bS - \
| samtools sort -@ ${task.cpus} -o ${sample}.${index}.filter.bam \
&& samtools index -@ {task.cpus} ${sample}.${index}.filter.bam \
&& samtools idxstats -@ {task.cpus} ${sample}.${index}.filter.bam > \
${sample}.${index}.filter.stats
"""
}
FILTER_ALIGNED.into{FILTER_ALIGNED_FASTQ_READ_LENGTH;
FILTER_ALIGNED_FASTQ_FASTQC}
FILTER_UNALIGNED.into{FILTER_UNALIGNED_FASTQ_READ_LENGTH;
FILTER_UNALIGNED_FASTQ_FASTQC;
FILTER_UNALIGNED_TRANSCRIPTOME}
// FILTER
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* TRANSCRIPTOME ALIGNMENT */
TRANSCRIPTOME_INDEX = Channel.from([[
params.input.reference.transcriptome
.split('/')[-1]
.replaceAll('\\*$', "")
.replaceAll('\\.$', ""),
file(params.input.reference.transcriptome),
]])
process transcriptome_alignment{
storeDir get_storedir("transcriptome_alignment") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(fastq) from FILTER_UNALIGNED_TRANSCRIPTOME
set val(transcriptome_reference), file(transcriptome_Reference_files) \
from TRANSCRIPTOME_INDEX.first()
output:
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.bam") \
into TRANSCRIPTOME_ALIGNMENT_BAM_PRE
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.bam.bai") \
into TRANSCRIPTOME_ALIGNMENT_BAI
set val(sample), val(index), file("${sample}.${index}.aligned.transcriptome_alignment.fastq.gz") \
into TRANSCRIPTOME_ALIGNMENT_ALIGNED
set val(sample), val(index), file("${sample}.${index}.unaligned.transcriptome_alignment.fastq.gz") \
into TRANSCRIPTOME_ALIGNMENT_UNALIGNED
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.log") \
into TRANSCRIPTOME_ALIGNMENT_LOG
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.stats") \
into TRANSCRIPTOME_ALIGNMENT_STATS
"""
bowtie2 ${params.alignment_arguments.transcriptome} \
-x ${transcriptome_reference} -q ${fastq} \
--threads ${task.cpus} \
--al-gz ${sample}.${index}.aligned.transcriptome_alignment.fastq.gz \
--un-gz ${sample}.${index}.unaligned.transcriptome_alignment.fastq.gz \
2> ${sample}.${index}.transcriptome_alignment.log \
| samtools view -bS -o ${sample}.${index}.tmp.transcriptome_alignment.bam \
&& samtools addreplacerg -r ID:${sample}.${index} -@ ${task.cpus} \
${sample}.${index}.tmp.transcriptome_alignment.bam \
| samtools sort -@ ${task.cpus} -o ${sample}.${index}.transcriptome_alignment.bam \
&& samtools index -@ {task.cpus} ${sample}.${index}.transcriptome_alignment.bam \
&& samtools idxstats -@ {task.cpus} ${sample}.${index}.transcriptome_alignment.bam > \
${sample}.${index}.transcriptome_alignment.stats
rm ${sample}.${index}.tmp.transcriptome_alignment.bam
"""
}
// TRANSCRIPTOME ALIGNMENT
///////////////////////////////////////////////////////////////////////////////////////
TRANSCRIPTOME_ALIGNMENT_BAM_PRE.into{ TRANSCRIPTOME_ALIGNMENT_BAM;
TRANSCRIPTOME_ALIGNMENT_BAM_MERGE;
TRANSCRIPTOME_ALIGNMENT_BAM_FOR_QUALITY}
///////////////////////////////////////////////////////////////////////////////////////
/* QUALITY FILTER */
process quality_filter{
storeDir get_storedir("quality_filter")
input:
set val(sample), val(index), file(bam) from TRANSCRIPTOME_ALIGNMENT_BAM_FOR_QUALITY
output:
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.qpass.bam") \
into TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_PRE
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.qpass.bam.bai") \
into TRANSCRIPTOME_ALIGNMENT_QPASS_BAI
set val(sample), val(index), file("${sample}.${index}.qpass.count") \
into TRANSCRIPTOME_QPASS_COUNTS
set val(sample), val(index), file("${sample}.${index}.transcriptome_alignment.qpass.stats") \
into TRANSCRIPTOME_ALIGNMENT_QPASS_STATS
"""
samtools view -b -q ${params.mapping_quality_cutoff} ${bam}\
| samtools sort -@ ${task.cpus} -o ${sample}.${index}.transcriptome_alignment.qpass.bam \
&& samtools view -b -c ${sample}.${index}.transcriptome_alignment.qpass.bam > ${sample}.${index}.qpass.count \
&& samtools index -@ {task.cpus} ${sample}.${index}.transcriptome_alignment.qpass.bam \
&& samtools idxstats -@ {task.cpus} ${sample}.${index}.transcriptome_alignment.qpass.bam > \
${sample}.${index}.transcriptome_alignment.qpass.stats
"""
}
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_PRE.into{ QPASS_BAM_READ_LENGTH;
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM;
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_FOR_MERGE;
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_FOR_DEDUP;
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_FOR_ARRANGE}
// QUALITY FILTER
///////////////////////////////////////////////////////////////////////////////////////
TRANSCRIPTOME_QPASS_COUNTS.into{TRANSCRIPTOME_QPASS_COUNTS_FOR_INDEX;
TRANSCRIPTOME_QPASS_COUNTS_FOR_TABLE}
// We need to copy output channels of transcriptome alignment
// for merging and variaous steps of downstream processing
TRANSCRIPTOME_ALIGNMENT_BAI.into{ TRANSCRIPTOME_ALIGNMENT_BAI_MERGE ;
TRANSCRIPTOME_ALIGNMENT_BAI_REGION_COUNT}
TRANSCRIPTOME_ALIGNMENT_ALIGNED.into{ TRANSCRIPTOME_ALIGNMENT_ALIGNED_MERGE ;
TRANSCRIPTOME_ALIGNMENT_ALIGNED_LENGTH ;
TRANSCRIPTOME_ALIGNMENT_ALIGNED_FASTQC }
TRANSCRIPTOME_ALIGNMENT_UNALIGNED.into{ TRANSCRIPTOME_ALIGNMENT_UNALIGNED_MERGE ;
TRANSCRIPTOME_ALIGNMENT_UNALIGNED_GENOME ;
TRANSCRIPTOME_ALIGNMENT_UNALIGNED_LENGTH ;
TRANSCRIPTOME_ALIGNMENT_UNALIGNED_FASTQC }
TRANSCRIPTOME_ALIGNMENT_LOG.into{ TRANSCRIPTOME_ALIGNMENT_LOG_MERGE ;
TRANSCRIPTOME_ALIGNMENT_LOG_TABLE }
TRANSCRIPTOME_ALIGNMENT_STATS.into{ TRANSCRIPTOME_ALIGNMENT_STATS_MERGE ;
TRANSCRIPTOME_ALIGNMENT_STATS_TABLE }
///////////////////////////////////////////////////////////////////////////////////////
/* MERGE TRANSCRIPTOME ALIGNMENT */
TRANSCRIPTOME_ALIGNMENT_BAM_MERGE.map{sample, index, bam -> [sample, bam]}.groupTuple()
.set{ TRANSCRIPTOME_ALIGNMENT_GROUPED_BAM }
TRANSCRIPTOME_ALIGNMENT_ALIGNED_MERGE.map{sample, index, fastq -> [sample, fastq]}.groupTuple()
.set{ TRANSCRIPTOME_ALIGNMENT_GROUPED_ALIGNED }
TRANSCRIPTOME_ALIGNMENT_UNALIGNED_MERGE.map{sample, index, fastq -> [sample, fastq]}.groupTuple()
.set{ TRANSCRIPTOME_ALIGNMENT_GROUPED_UNALIGNED }
TRANSCRIPTOME_ALIGNMENT_LOG_MERGE.map{sample, index, log -> [sample, log]}.groupTuple()
.set{ TRANSCRIPTOME_ALIGNMENT_GROUPED_LOG }
TRANSCRIPTOME_ALIGNMENT_GROUPED_BAM.join(TRANSCRIPTOME_ALIGNMENT_GROUPED_ALIGNED)
.join(TRANSCRIPTOME_ALIGNMENT_GROUPED_UNALIGNED)
.join(TRANSCRIPTOME_ALIGNMENT_GROUPED_LOG)
.into{TRANSCRIPTOME_ALIGNMENT_GROUPED_JOINT;
TRANSCRIPTOME_ALIGNMENT_GROUPED_JOINED_VERBOSE}
process merge_transcriptome_alignment{
storeDir get_storedir("transcriptome_alignment") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bam), file(aligned_fastq),
file(unaligned_fastq), file(alignment_log) from\
TRANSCRIPTOME_ALIGNMENT_GROUPED_JOINT
output:
set val(sample), file("${sample}.transcriptome.bam"),
file("${sample}.transcriptome.bam.bai") into \
TRANSCRIPTOME_ALIGNMENT_MERGED_BAM
set val(sample), file("${sample}.transcriptome.bam.bai") into \
TRANSCRIPTOME_ALIGNMENT_MERGED_BAI
set val(sample), file("${sample}.transcriptome.aligned.fastq.gz") into \
TRANSCRIPTOME_ALIGNMENT_MERGED_ALIGNED
set val(sample), file("${sample}.transcriptome.unaligned.fastq.gz") into \
TRANSCRIPTOME_ALIGNMENT_MERGED_UNALIGNED
set val(sample), file("${sample}.transcriptome.log") into \
TRANSCRIPTOME_ALIGNMENT_MERGED_LOG
"""
samtools merge ${sample}.transcriptome.bam ${bam} && \
samtools index ${sample}.transcriptome.bam && \
zcat ${aligned_fastq} | gzip -c > ${sample}.transcriptome.aligned.fastq.gz && \
zcat ${unaligned_fastq} | gzip -c > ${sample}.transcriptome.unaligned.fastq.gz && \
rfc merge bowtie2-logs --out ${sample}.transcriptome.log ${alignment_log}
"""
}
// MERGE TRANSCRIPTOME ALIGNMENT
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* TRANSCRIPTOME INDIVIDUAL FASTQC */
process transcriptome_aligned_individual_fastqc{
publishDir get_publishdir("fastqc") + "/transcriptome_aligned", mode: 'copy'
input:
set val(sample), val(index), file(fastq) from TRANSCRIPTOME_ALIGNMENT_ALIGNED_FASTQC
output:
set val(sample), file("${sample}.${index}.transcriptome.aligned_fastqc.html"),
file("${sample}.${index}.transcriptome.aligned_fastqc.zip") \
into TRANSCRIPTOME_ALIGNED_INDIVIDUAL_FASTQC_OUT
when:
params.do_fastqc
"""
if [ ! -f ${sample}.${index}.transcriptome.aligned.fastq.gz ]; then
ln -s ${fastq} ${sample}.${index}.transcriptome.aligned.fastq.gz
fi
fastqc ${sample}.${index}.transcriptome.aligned.fastq.gz --outdir=\$PWD -t ${task.cpus}
"""
}
process transcriptome_unaligned_individual_fastqc{
publishDir get_publishdir("fastqc") + "/transcriptome_unaligned", mode: 'copy'
input:
set val(sample), val(index), file(fastq) from TRANSCRIPTOME_ALIGNMENT_UNALIGNED_FASTQC
output:
set val(sample), file("${sample}.${index}.transcriptome.unaligned_fastqc.html"),
file("${sample}.${index}.transcriptome.unaligned_fastqc.zip") \
into TRANSCRIPTOME_UNALIGNED_INDIVIDUAL_FASTQC_OUT
when:
params.do_fastqc
"""
if [ ! -f ${sample}.${index}.transcriptome.unaligned.fastq.gz ]; then
ln -s ${fastq} ${sample}.${index}.transcriptome.unaligned.fastq.gz
fi
fastqc ${sample}.${index}.transcriptome.unaligned.fastq.gz --outdir=\$PWD -t ${task.cpus}
"""
}
// TRANSCRIPTOME INDIVIDUAL FASTQC
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
/* GENOME ALIGNMENT */
do_align_genome = params.input.reference.get("genome", false)
if(do_align_genome){
GENOME_INDEX = Channel.from([[
params.input.reference.genome
.split('/')[-1]
.replaceAll('\\*$', "")
.replaceAll('\\.$', ""),
file(params.input.reference.genome),
]])
process genome_alignment{
storeDir get_storedir("genome_alignment") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(fastq) from TRANSCRIPTOME_ALIGNMENT_UNALIGNED_GENOME
set val(genome_base), file(genome_files) from GENOME_INDEX.first()
output:
set val(sample), val(index), file("${sample}.${index}.genome_alignment.bam") \
into GENOME_ALIGNMENT_BAM
set val(sample), val(index), file("${sample}.${index}.genome_alignment.bam.bai") \
into GENOME_ALIGNMENT_BAI
set val(sample), val(index), file("${sample}.${index}.genome_alignment.aligned.fastq.gz") \
into GENOME_ALIGNMENT_ALIGNED
set val(sample), val(index), file("${sample}.${index}.genome_alignment.unaligned.fastq.gz") \
into GENOME_ALIGNMENT_UNALIGNED
set val(sample), val(index), file("${sample}.${index}.genome_alignment.log") \
into GENOME_ALIGNMENT_LOG
set val(sample), val(index), file("${sample}.${index}.genome_alignment.csv") \
into GENOME_ALIGNMENT_CSV
"""
hisat2 ${params.alignment_arguments.genome} \
-x ${genome_base} -U ${fastq} \
-p ${task.cpus} \
--al-gz ${sample}.${index}.genome_alignment.aligned.fastq.gz \
--un-gz ${sample}.${index}.genome_alignment.unaligned.fastq.gz \
2> ${sample}.${index}.genome_alignment.log \
| samtools view -bS - \
| samtools sort -@ ${task.cpus} -o ${sample}.${index}.genome_alignment.bam \
&& samtools index -@ {task.cpus} ${sample}.${index}.genome_alignment.bam \
&& rfc bt2-log-to-csv -o ${sample}.${index}.genome_alignment.csv \
-n ${sample} -p genome -l ${sample}.${index}.genome_alignment.log
"""
}
GENOME_ALIGNMENT_ALIGNED.into{ GENOME_ALIGNMENT_ALIGNED_FASTQ_READ_LENGTH;
GENOME_ALIGNMENT_ALIGNED_MERGE;
GENOME_ALIGNMENT_ALIGNED_FASTQ_FASTQC }
GENOME_ALIGNMENT_UNALIGNED.into{ GENOME_ALIGNMENT_UNALIGNED_FASTQ_READ_LENGTH;
GENOME_ALIGNMENT_UNALIGNED_MERGE;
GENOME_ALIGNMENT_UNALIGNED_FASTQ_FASTQC;
FOR_POST_GENOME }
// GENOME ALIGNMENT
///////////////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* MERGE GENOME ALIGNMENT */
GENOME_ALIGNMENT_LOG.into{ GENOME_ALIGNMENT_LOG_MERGE; GENOME_ALIGNMENT_LOG_TABLE }
GENOME_ALIGNMENT_LOG_TABLE
.map{ sample, index, genome_log -> [ [sample, index], genome_log ] }
.set{GENOME_ALIGNMENT_LOG_TABLE_INDEXED}
GENOME_ALIGNMENT_BAM.map{sample, index, bam -> [sample, bam]}.groupTuple()
.set{ GENOME_ALIGNMENT_GROUPED_BAM }
GENOME_ALIGNMENT_ALIGNED_MERGE.map{sample, index, fastq -> [sample, fastq]}.groupTuple()
.set{ GENOME_ALIGNMENT_GROUPED_ALIGNED_FASTQ }
GENOME_ALIGNMENT_UNALIGNED_MERGE.map{sample, index, fastq -> [sample, fastq]}.groupTuple()
.set{ GENOME_ALIGNMENT_GROUPED_UNALIGNED_FASTQ }
GENOME_ALIGNMENT_LOG_MERGE.map{sample, index, log -> [sample, log]}.groupTuple()
.set{ GENOME_ALIGNMENT_GROUPED_LOG }
GENOME_ALIGNMENT_GROUPED_BAM.join( GENOME_ALIGNMENT_GROUPED_ALIGNED_FASTQ )
.join(GENOME_ALIGNMENT_GROUPED_UNALIGNED_FASTQ)
.join(GENOME_ALIGNMENT_GROUPED_LOG)
.set{ GENOME_ALIGNMENT_GROUPED_JOINT }
process merge_genome_alignment{
storeDir get_storedir("genome_alignment") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bam), file(aligned_fastq), \
file(unaligned_fastq), file(alignment_log) from GENOME_ALIGNMENT_GROUPED_JOINT
output:
set val(sample), file("${sample}.genome.bam") \
into GENOME_ALIGNMENT_MERGED_BAM
set val(sample), file("${sample}.genome.bam.bai") \
into GENOME_ALIGNMENT_MERGED_BAI
set val(sample), file("${sample}.genome.aligned.fastq.gz") \
into GENOME_ALIGNMENT_MERGED_ALIGNED_FASTQ
set val(sample), file("${sample}.genome.unaligned.fastq.gz") \
into GENOME_ALIGNMENT_MERGED_UNALIGNED_FASTQ
set val(sample), file("${sample}.genome.log") \
into GENOME_ALIGNMENT_MERGED_LOG
set val(sample), file("${sample}.genome.csv") \
into GENOME_ALIGNMENT_MERGED_CSV
"""
samtools merge ${sample}.genome.bam ${bam} && samtools index ${sample}.genome.bam && \
zcat ${aligned_fastq} | gzip -c > ${sample}.genome.aligned.fastq.gz && \
zcat ${unaligned_fastq} | gzip -c > ${sample}.genome.unaligned.fastq.gz && \
rfc merge bowtie2-logs -o ${sample}.genome.log ${alignment_log} && \
rfc bt2-log-to-csv -n ${sample} -l ${sample}.genome.log -p genome \
-o ${sample}.genome.csv
"""
}
GENOME_ALIGNMENT_CSV
.map{ sample, index, stats_file -> stats_file }
.toSortedList().set{GENOME_ALIGNMENT_CSV_INDIVIDUAL_LIST}
GENOME_ALIGNMENT_MERGED_CSV
.map{ sample, stats_file -> stats_file }
.toSortedList().set{GENOME_ALIGNMENT_CSV_MERGED_LIST}
process combine_individual_genome_stats{
storeDir get_storedir("genome_alignment") + "/logs"
input:
file(stats_input_files) from GENOME_ALIGNMENT_CSV_INDIVIDUAL_LIST
file(stats_input_files_merged) from GENOME_ALIGNMENT_CSV_MERGED_LIST
output:
file("genome_individual_stats.csv") \
into GENOME_ALIGNMENT_CSV_INDIVIDUAL_COMBINED
file("genome_merged_stats.csv") \
into GENOME_ALIGNMENT_CSV_MERGED_COMBINED
"""
rfc merge overall-stats -o genome_individual_stats.csv ${stats_input_files} ; \
rfc merge overall-stats -o genome_merged_stats.csv ${stats_input_files_merged}
"""
}
// MERGE GENOME ALIGNMENT
///////////////////////////////////////////////////////////////////////////////
} // end of if(do_align_genome){
// END OF GENOME ALIGNMENT
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////
/* BAM TO BED */
/*
We assume that duplicates are coming from PCR. So for each sample,
we merge the sequencing lanes ,
Add a sample.index column to the bed file.
sort the entire bed file by the first 3 columns ( sort -k1,1 -k2,2n -k3,3n )
Then we can deduplicate the entire file
Then separate the file based on the additional column that we added
*/
process bam_to_bed{
storeDir get_storedir("bam_to_bed") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(bam) from TRANSCRIPTOME_ALIGNMENT_QPASS_BAM
output:
set val(sample), val(index), file("${sample}.${index}.bed") into BAM_TO_BED
set val(sample), val(index), file("${sample}.${index}_nodedup_count.txt") \
into INDIVIDUAL_DEDUP_COUNT_WITHOUT_DEDUP
"""
if [ `samtools view -c ${bam}` -eq 0 ];
then
touch ${sample}.${index}.bed
else
bamToBed -i ${bam} > ${sample}.${index}.bed
fi
wc -l ${sample}.${index}.bed > ${sample}.${index}_nodedup_count.txt
"""
}
BAM_TO_BED.into{ BED_NODEDUP; BED_FOR_DEDUP; BED_FOR_INDEX_SEP_PRE }
process add_sample_index_col_to_bed{
storeDir get_storedir("bam_to_bed") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(bed) from BED_FOR_DEDUP
output:
set val(sample), file("${sample}.${index}.with_sample_index.bed")\
into BED_FOR_DEDUP_INDEX_COL_ADDED
"""
awk -v newcol=${sample}.${index} '{print(\$0"\\t"newcol)}' ${bed}\
> ${sample}.${index}.with_sample_index.bed
"""
}
BED_FOR_DEDUP_INDEX_COL_ADDED.groupTuple()
.set{ BED_FOR_DEDUP_INDEX_COL_ADDED_GROUPED }
process merge_bed{
storeDir get_storedir("bam_to_bed") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bed_files) from BED_FOR_DEDUP_INDEX_COL_ADDED_GROUPED
output:
set val(sample), file("${sample}.merged.pre_dedup.bed") \
into MERGE_BED_OUT
when:
dedup_method == "position"
"""
cat ${bed_files} | sort -k1,1 -k2,2n -k3,3n > ${sample}.merged.pre_dedup.bed
"""
}
MERGE_BED_OUT.into{BED_FOR_DEDUP_MERGED_PRE_DEDUP;
MERGED_BED_FOR_RIBO}
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_FOR_MERGE.map{sample, index, bam -> [sample, bam]}.groupTuple()
.set{ TRANSCRIPTOME_ALIGNMENT_QPASS_GROUPED_BAM }
process merge_bam_post_qpass{
storeDir get_storedir("transcriptome_alignment") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bam_files) from TRANSCRIPTOME_ALIGNMENT_QPASS_GROUPED_BAM
output:
set val(sample), file("${sample}.merged.pre_dedup.bam"),\
file("${sample}.merged.pre_dedup.bam.bai") \
into MERGED_BAM_PRE_DEDUP
when:
dedup_method == "umi_tools"
"""
samtools merge ${sample}.merged.pre_dedup.bam ${bam_files}
samtools index ${sample}.merged.pre_dedup.bam ${sample}.merged.pre_dedup.bam.bai
"""
}
///////////////////////////////////////////////////////////////////////////////
// D E D U P L I C A T I O N
process deduplicate_position{
storeDir get_storedir("alignment_ribo") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bed) from BED_FOR_DEDUP_MERGED_PRE_DEDUP
output:
set val(sample), file("${sample}.merged.post_dedup.bed") \
into BED_FOR_DEDUP_MERGED_POST_DEDUP
when:
dedup_method == "position"
"""
rfc dedup -i ${bed} -o ${sample}.merged.post_dedup.bed
"""
}
process deduplicate_umi_tools{
storeDir get_storedir("umi_tools") + "/" + params.output.merged_lane_directory
input:
set val(sample), file(bam), file(bai) from MERGED_BAM_PRE_DEDUP
output:
set val(sample), file("${sample}.dedup.bam") into UMI_TOOLS_DEDUP_BAM
set val(sample), file("${sample}.dedup.bed") into UMI_TOOLS_BED_FOR_DEDUP_MERGED_POST_DEDUP
set val(sample), file("${sample}.dedup.log") into UMI_TOOLS_DEDUP_LOG
set val(sample), file("${sample}.dedup.stats_edit_distance.tsv"),
file("${sample}.dedup.stats_per_umi_per_position.tsv"),
file("${sample}.dedup.stats_per_umi.tsv") \
into UMI_TOOLS_DEDUP_STATS
when:
dedup_method == "umi_tools"
"""
umi_tools dedup ${params.get("umi_tools_dedup_arguments", "")} \
-I ${bam} --output-stats=${sample}.dedup.stats -S ${sample}.dedup.bam -L ${sample}.dedup.log
bamToBed -i ${sample}.dedup.bam > ${sample}.dedup.bed
"""
}
// D E D U P L I C A T I O N
///////////////////////////////////////////////////////////////////////////////
BED_FOR_DEDUP_MERGED_POST_DEDUP.into{BED_FOR_DEDUP_MERGED_POST_DEDUP_FOR_SEP;
BED_FOR_DEDUP_MERGED_POST_DEDUP_FOR_RIBO}
BED_FOR_INDEX_SEP_PRE.map{ sample,index,file -> [sample, index] }
.combine(BED_FOR_DEDUP_MERGED_POST_DEDUP_FOR_SEP, by:0)
.set{ BED_FOR_INDEX_SEP_POST_DEDUP }
process separate_bed_post_dedup{
storeDir get_storedir("alignment_ribo") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(bed) from BED_FOR_INDEX_SEP_POST_DEDUP
output:
set val(sample), val(index), file("${sample}.${index}.post_dedup.bed") \
into BED_DEDUPLICATED
set val(sample), val(index), file("${sample}.${index}.count_after_dedup.txt")\
into INDIVIDUAL_DEDUP_COUNT_WITH_DEDUP
when:
dedup_method == "position"
"""
awk -v this_sample=${sample}.${index} \
'{ if(\$7 == this_sample ){print(\$1"\\t"\$2"\\t"\$3"\\t"\$4"\\t"\$5"\\t"\$6)} }' ${bed} \
> ${sample}.${index}.post_dedup.bed \
&& wc -l ${sample}.${index}.post_dedup.bed > ${sample}.${index}.count_after_dedup.txt
"""
}
TRANSCRIPTOME_ALIGNMENT_QPASS_BAM_FOR_ARRANGE.map{ sample,index,file -> [sample, index] }
.combine(UMI_TOOLS_DEDUP_BAM , by:0)
.set{ BAM_FOR_INDEX_SEP_POST_DEDUP }
process separate_bam_post_dedup{
storeDir get_storedir("alignment_ribo") + "/" + params.output.individual_lane_directory
input:
set val(sample), val(index), file(bam) from BAM_FOR_INDEX_SEP_POST_DEDUP
output:
set val(sample), val(index), file("${sample}.${index}.post_dedup.bam") \
into BAM_INDIVIDUAL_DEDUPLICATED
set val(sample), val(index), file("${sample}.${index}.count_after_dedup.txt")\
into BAM_INDIVIDUAL_DEDUP_COUNT_WITH_DEDUP
when:
dedup_method == "umi_tools"
"""
samtools view -B -r ${sample}.${index} ${bam} -o ${sample}.${index}.post_dedup.bam
samtools view -c ${sample}.${index}.post_dedup.bam > ${sample}.${index}.count_after_dedup.txt