-
Notifications
You must be signed in to change notification settings - Fork 5
/
main.nf
2587 lines (1889 loc) · 80 KB
/
main.nf
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
/*
** This pipeline is written for Nextflow DSL 1.
*/
nextflow.enable.dsl = 1
/*
** Check that Nextflow version meets minimum version requirements.
*/
def minMajorVersion = 20
def minMinorVersion = 07
checkNextflowVersion( minMajorVersion, minMinorVersion )
/*
** Check OS version.
** Notes:
** o works only for Linux systems
** o used to distinguish between CentOS 6 and CentOS 7
*/
( osName, osDistribution, osRelease ) = getOSInfo()
// Parse input parameters
params.help = false
params.samples = false
params.star_file = "$baseDir/bin/star_file.txt"
params.gene_file = "$baseDir/bin/gene_file.txt"
params.umi_cutoff = 100
params.rt_barcode_file="default"
params.max_cores = 16
params.hash_list = false
params.max_wells_per_sample = 20
params.garnett_file = false
params.skip_doublet_detect = false
params.run_emptyDrops = true
params.hash_umi_cutoff = 5
params.hash_ratio = false
params.hash_dup = false // Default is false. Other options are "p5" or "pcr_plate". params.hash_list must also be true.
//print usage
if (params.help) {
log.info ''
log.info 'BBI sci-RNA-seq Pipeline'
log.info '--------------------------------'
log.info ''
log.info 'For reproducibility, please specify all parameters to a config file'
log.info 'by specifying -c CONFIG_FILE.config.'
log.info ''
log.info 'Usage: '
log.info ' nextflow run bbi-sci -c CONFIG_FILE'
log.info ''
log.info 'Help: '
log.info ' --help Show this message and exit.'
log.info ''
log.info 'Required parameters (specify in your config file):'
log.info ' params.output_dir = OUTPUT DIRECTORY Output directory.'
log.info ' params.sample_sheet = SAMPLE_SHEET_PATH Sample sheet of the format described in the README.'
log.info ' params.demux_out = DEMUX OUTPUT DIR Path to the demux_out folder from the bbi-dmux run.'
log.info ' params.level = 3 2 or 3 level sci?'
log.info ''
log.info 'Optional parameters (specify in your config file):'
log.info ' params.rt_barcode_file = "default" The path to a custom RT barcode file. If "default", default BBI barcodes will be used.'
log.info ' params.max_cores = 16 The maximum number of cores to use - fewer will be used if appropriate.'
log.info ' process.maxForks = 20 The maximum number of processes to run at the same time on the cluster.'
log.info ' process.queue = "trapnell-short.q" The queue on the cluster where the jobs should be submitted. '
log.info ' params.samples = [sample1, sample2] Add to only run certain samples from trimming on. Default is to run all.'
log.info ' params.star_file = PATH/TO/FILE File with the genome to star maps, similar to the one included with the package.'
log.info ' params.gene_file = PATH/TO/FILE File with the genome to gene model maps, similar to the one included with the package.'
log.info ' params.umi_cutoff = 100 The umi cutoff to be called a cell in matrix output.'
log.info ' params.hash_list = false Path to a tab-delimited file with at least two columns, first the hash name and second the hash barcode sequence. Default is false to indicate no hashing.'
log.info ' params.max_wells_per_sample = 20 The maximum number of wells per sample - if a sample is in more wells, the fastqs will be split then reassembled for efficiency.'
log.info ' params.garnett_file = false Path to a csv with two columns, first is the sample name, and second is a path to the Garnett classifier to be applied to that sample. Default is false - no classification.'
log.info ' params.skip_doublet_detect = false Whether to skip doublet detection, i.e. scrublet - useful for very large datasets.'
log.info ' params.hash_umi_cutoff = 5 The hash umi cutoff to determine hash vs background in top to second best hash oligo. Default is 5'
log.info ' params.hash_ratio = false The min hash umi ratio for top to second best. Default is false and not filtered'
log.info ' params.hash_dup = false Whether to run hash PCR duplication rate per plate and what indicates a plate. Options are "p5" and "pcr_plate". params.hash_list also needs to be set to true. Default is false.'
log.info 'Issues? Contact [email protected]'
exit 1
}
// check required options
if (!params.output_dir || !params.sample_sheet || !params.level || !params.demux_out) {
exit 1, "Must include config file using -c CONFIG_FILE.config that includes output_dir, sample_sheet, level and demux_out"
}
/*************
Process: check_sample_sheet
Inputs:
params.sample_sheet
params.star_file
params.level
params.max_wells_per_sample
params.rt_barcode_file
Outputs:
good_sample_sheet - corrected csv sample sheet
logfile - running log
log_piece1 - piece of log to be concatenated for full log
Pass through:
Summary:
Check and process sample sheet - check_sample_sheet.py
Start log
Downstream:
gather_info
trim_fastqs
combine_logs
Published:
Notes:
*************/
process check_sample_sheet {
cache 'lenient'
output:
file "*.csv" into good_sample_sheet
file '*.log' into log_check_sample
file 'start.txt' into log_piece1
"""
# bash watch for errors
set -ueo pipefail
printf "BBI bbi-sci Pipeline Log\n\n" > start.log
printf "Run started at: \$(date)\n\n" >> start.log
printf "***** BEGIN PIPELINE *****: \n\n" >> start.log
printf "** Start process 'check_sample_sheet' at: \$(date)\n\n" >> start.log
printf " Process versions:
\$(python --version)\n\n" >> start.log
printf " Process command:
check_sample_sheet.py
--sample_sheet $params.sample_sheet
--star_file $params.star_file
--level $params.level --rt_barcode_file $params.rt_barcode_file
--max_wells_per_samp $params.max_wells_per_sample\n\n" >> start.log
check_sample_sheet.py --sample_sheet $params.sample_sheet --star_file $params.star_file \
--level $params.level --rt_barcode_file $params.rt_barcode_file \
--max_wells_per_samp $params.max_wells_per_sample
printf "** End process 'check_sample_sheet' at: \$(date)\n\n" >> start.log
cp start.log start.txt
"""
}
// Generate a sample list with fixed naming
samp_file = file(params.sample_sheet)
def samp_list = []
for (line in samp_file.readLines()) {
samp_list.add(line.split(",")[1])
}
samp_list = samp_list.collect{"$it".replaceAll(/\s/, ".").replaceAll(/_/, ".").replaceAll(/-/, ".").replaceAll(/\\//, ".")}
samp_list.removeElement("Sample.ID")
if (params.samples != false) {
samp_list = samp_list.intersect(params.samples.collect{"$it".replaceAll(/\s/, ".").replaceAll(/_/, ".").replaceAll(/-/, ".").replaceAll(/\\//, ".")})
}
/*************
Process: trim_fastqs
Inputs:
input_fastq - all fastq files from params.demux_out folder
logfile - running log
Outputs:
trim_out - output folder from trimming - stops here
key - sample id
name - file id (including lane and split info)
trimmed_fastq - trimmed, gzipped fastq
logfile - running log
log_piece2 - piece of log to be concatenated for full log
Pass through:
input_fastq - all fastq files from params.demux_out folder
Summary:
Trim fastqs - trim_galore
Continue log
Downstream:
gather_info
process_hashes
Published:
Notes:
Only moves forward if sample is in samp_list - where params.samples comes in
*************/
process trim_fastqs {
cache 'lenient'
input:
file input_fastq from Channel.fromPath("${params.demux_out}/*.fastq.gz")
file logfile from log_check_sample
output:
file "trim_out" into trim_output
set val(key), val(name), file("trim_out/*.fq.gz"), file('trim.log'), file('*trim.txt') into trimmed_fastqs
set val(key), file(input_fastq) into fastqs_out
when:
!((input_fastq.name.split(/-L[0-9]{3}/)[0].split(/\.fq.part/)[0]) in "Undetermined") && ((input_fastq.name.split(/-L[0-9]{3}/)[0].split(/\.fq.part/)[0]) in samp_list)
script:
name = input_fastq.baseName - ~/.fastq/
key = input_fastq.baseName.split(/-L[0-9]{3}/)[0].split(/\.fq.part/)[0]
"""
# bash watch for errors
set -ueo pipefail
cat ${logfile} > trim.log
printf "** Start process 'trim_fastqs' for $input_fastq at: \$(date)\n\n" > piece.log
printf " Process versions:
" >> piece.log
python --version &>> piece.log
printf " trim_galore \$(trim_galore -v | grep version | awk '{\$1=\$1;print}')
cutadapt version \$(cutadapt --version)\n\n" >> piece.log
printf " Process command:
trim_galore $input_fastq -a AAAAAAAA --three_prime_clip_R1 1
--gzip -o ./trim_out/\n
Process output:\n" >> piece.log
mkdir trim_out
trim_galore $input_fastq \
-a AAAAAAAA \
--three_prime_clip_R1 1 \
--gzip \
-o ./trim_out/
cat trim_out/*trimming_report.txt | sed '/Overview of/,/RUN/{//!d}' | sed 's/Overview of removed sequences//' >> piece.log
printf "** End process 'trim_fastqs' at: \$(date)\n\n" >> piece.log
cp piece.log ${name}_trim.txt
cat piece.log >> trim.log
"""
}
/*************
Process: gather_info
Inputs:
good_sample_sheet - corrected csv sample sheet
key - sample id
params.star_file
params.gene_file
Outputs:
key - sample id
star_path - path to star index folder
gtf_path - path to gtf info folder
star_mem - GB needed for star alignment
Pass through:
name - file id (including lane and split info)
trimmed_fastq - trimmed, gzipped fastq
log_piece2 - piece of log to be concatenated for full log
logfile - running log
Summary:
Gather the star and gtf paths and info for downstream
Downstream:
split_bam
make_matrix
align_reads
Published:
Notes:
o the 'spec' variable uses the awk split() function to remove
'_fq_part', which is added when very large fastq files are
split. The gsub() function removes unacceptable characters
from the sample names.
*************/
process gather_info {
cache 'lenient'
input:
file good_sample_sheet
set val(key), val(name), file(trimmed_fastq), file(logfile), file(log_piece2) from trimmed_fastqs
output:
set val(key), val(name), env(star_path), env(star_mem), file(trimmed_fastq), file(logfile), file(log_piece2) into align_prepped
set val(key), env(gtf_path) into gtf_info
set val(key), env(gtf_path) into gtf_info2
"""
# bash watch for errors
set -ueo pipefail
spec=`sed 's/ *\$//g' good_sample_sheet.csv | awk 'BEGIN {FS=",";OFS=","}{split(\$2,a,"_fq_part");gsub("[_ /-]", ".", a[1]);print(\$1, a[1], \$3)}' | awk 'BEGIN {FS=","}; \$2=="$key" {print \$3}' | uniq`
star_mem=`awk -v var="\$spec" '\$1==var {print \$3}' $params.star_file | uniq`
star_path=`awk -v var="\$spec" '\$1==var {print \$2}' $params.star_file | uniq`
gtf_path=`awk -v var="\$spec" '\$1==var {print \$2}' $params.gene_file | uniq`
"""
}
/*************
Process: process_hashes
Inputs:
key - sample id
input_fastq - all fastq files from params.demux_out folder
params.hash_list
Outputs:
hash_log - log of the hash information
hash_mtx - MatrixMarket matrix of hash information
hash_cell - Cell info for matrix of hash information
hash_hash - Hash info for matrix of hash information
Pass through:
Summary:
Collect and process hash barcodes - process_hashes.py
Downstream:
Published:
hash_mtx - MatrixMarket matrix of hash information
hash_cell - Cell info for matrix of hash information
hash_hash - Hash info for matrix of hash information
Notes:
Only when params.hash = true
*************/
// Group fastqs for finding hash barcodes
// Second channel will be used to calculate hash PCR duplication rate
fastqs_out.into{fastqs_out_copy01; fastqs_for_hash_copy02}
fastqs_out_copy01
.groupTuple()
.set { fastqs_for_hash_copy01 }
save_hash_cell = {params.output_dir + "/" + it - ~/.hashumis_cells.txt/ + "/" + it}
save_hash_hash = {params.output_dir + "/" + it - ~/.hashumis_hashes.txt/ + "/" + it}
save_hash_mtx = {params.output_dir + "/" + it - ~/.hashumis.mtx/ + "/" + it}
process process_hashes {
cache 'lenient'
publishDir path: "${params.output_dir}/", saveAs: save_hash_cell, pattern: "*hashumis_cells.txt", mode: 'copy'
publishDir path: "${params.output_dir}/", saveAs: save_hash_hash, pattern: "*hashumis_hashes.txt", mode: 'copy'
publishDir path: "${params.output_dir}/", saveAs: save_hash_mtx, pattern: "*.mtx", mode: 'copy'
input:
set key, file(input_fastq) from fastqs_for_hash_copy01
output:
file("*hash.log") into hash_logs
set key, file("*mtx"), file("*hashumis_cells.txt"), file("*hashumis_hashes.txt") into hash_mats
when:
params.hash_list != false
"""
# bash watch for errors
set -ueo pipefail
process_hashes.py --hash_sheet $params.hash_list \
--fastq <(zcat $input_fastq) --key $key
"""
}
/*************
Process: align_reads
Inputs:
name - file id (including lane and split info)
star_path - path to star index folder
star_mem - GB needed for star alignment
trimmed_fastq - trimmed, gzipped fastq
logfile - running log
cores_align - number of cores to use
Outputs:
align_out - folder of all alignment output - stops here
name - file id (including lane and split info)
aligned_bam - bam output from star alignment
logfile - running log
log_piece3 - piece of log to be concatenated for full log
Pass through:
key - sample id
log_piece2 - piece of log to be concatenated for full log
Summary:
Align reads to genome using STAR
Downstream:
sort_and_filter
Published:
Notes:
*************/
// Cores for alignment set at 8 unless limit is lower
cores_align = params.max_cores < 8 ? params.max_cores : 8
process align_reads {
cache 'lenient'
memory { star_mem.toInteger()/cores_align + " GB" }
cpus cores_align
input:
set val(key), val(name), val(star_path), val(star_mem), file(trimmed_fastq), file(logfile), file(log_piece2) from align_prepped
output:
file "align_out" into align_output
set val(key), val(name), file("align_out/*Aligned.out.bam"), file('align.log'), file(log_piece2), file("*align.txt") into aligned_bams
"""
# bash watch for errors
set -ueo pipefail
cat ${logfile} > align.log
printf "** Start process 'align_reads' for $trimmed_fastq at: \$(date)\n\n" > piece.log
printf " Process versions:
\$(STAR --version)\n\n" >> piece.log
printf " Process command:
STAR --runThreadN $cores_align --genomeDir $star_path
--readFilesIn $trimmed_fastq --readFilesCommand zcat
--outFileNamePrefix ./align_out/${name} --outSAMtype BAM Unsorted
--outSAMmultNmax 1 --outSAMstrandField intronMotif\n
Reference genome information:
\$(grep fastq_url $star_path/../*gsrc/record.out | awk '{\$1=\$2=""; print \$0}')
FASTA download date: \$(grep fastq_download_date $star_path/../*gsrc/record.out | awk '{\$1=\$2=""; print \$0}')
Non REF sequences removed.
\$(grep gtf_url $star_path/../*gsrc/record.out | awk '{\$1=\$2=""; print \$0}')
GTF download date: \$(grep gtf_download_date $star_path/../*gsrc/record.out | awk '{\$1=\$2=""; print \$0}')
\$(grep gtf_include_biotypes $star_path/record.out | awk '{\$1=\$2=""; print \$0}')
Process output:\n" >> piece.log
mkdir align_out
STAR \
--runThreadN $cores_align \
--genomeDir $star_path \
--readFilesIn $trimmed_fastq \
--readFilesCommand zcat \
--outFileNamePrefix ./align_out/${name} \
--outSAMtype BAM Unsorted \
--outSAMmultNmax 1 \
--outSAMstrandField intronMotif
cat align_out/*Log.final.out >> piece.log
printf "\n** End process 'align_reads' at: \$(date)\n\n" >> piece.log
cp piece.log ${name}_align.txt
cat piece.log >> align.log
"""
}
/*************
Process: sort_and_filter
Inputs:
name - file id (including lane and split info)
aligned_bam - bam output from star alignment
logfile - running log
cores_sf - number of cores to use
Outputs:
name - file id (including lane and split info)
sorted_bam - sorted and quality filtered bam
log_piece4 - piece of log to be concatenated for full log
Pass through:
key - sample id
log_piece2 - piece of log to be concatenated for full log
log_piece3 - piece of log to be concatenated for full log
Summary:
Use samtools to filter for read quality 30 and sort bam
Downstream:
merge_bams
combine_logs
Published:
Notes:
*************/
// Cores for sort and filter set at 10 unless limit is lower
cores_sf = params.max_cores < 10 ? params.max_cores : 10
process sort_and_filter {
cache 'lenient'
cpus cores_sf
input:
set val(key), val(name), file(aligned_bam), file(logfile), file(log_piece2), file(log_piece3) from aligned_bams
output:
set val(key), file("*.bam") into sorted_bams
set val(key), file(log_piece2), file(log_piece3), file("*_sf.txt") into log_pieces
"""
# bash watch for errors
set -ueo pipefail
printf "** Start process 'sort_and_filter' for $aligned_bam at: \$(date)\n\n" > ${name}_piece.log
printf " Process versions:
\$(samtools --version | tr '\n' ' ')\n\n" >> ${name}_piece.log
printf " Process command:
samtools view -bh -q 30 -F 4 '$aligned_bam'
| samtools sort -@ $cores_sf - > '${name}.bam'\n\n" >> ${name}_piece.log
samtools view -bh -q 30 -F 4 "$aligned_bam" \
| samtools sort -@ $cores_sf - \
> "${name}.bam"
printf " Process stats:
sort_and_filter starting reads: \$(samtools view -c $aligned_bam)
sort_and_filter ending reads : \$(samtools view -c ${name}.bam)\n\n" >> ${name}_piece.log
printf "** End process 'sort_and_filter' at: \$(date)\n\n" >> ${name}_piece.log
cp ${name}_piece.log ${name}_sf.txt
"""
}
/*************
Process: combine_logs
Inputs:
log_piece1 - piece of log to be concatenated for full log
log_piece2 - piece of log to be concatenated for full log
log_piece3 - piece of log to be concatenated for full log
log_piece4 - piece of log to be concatenated for full log
Outputs:
logfile - concatenated running log
Pass through:
key - sample id
Summary:
Combine the log pieces from the first steps in the correct order
Downstream:
merge_bams
Published:
Notes:
*************/
log_pieces
.groupTuple()
.set { logs_to_combine }
process combine_logs {
cache 'lenient'
input:
file log_piece1
set val(key), file(log_piece2), file(log_piece3), file(log_piece4) from logs_to_combine
output:
set val(key), file("*_pre.log") into log_premerge
"""
# bash watch for errors
set -ueo pipefail
cat $log_piece1 $log_piece2 $log_piece3 $log_piece4 > ${key}_pre.log
"""
}
/*************
Process: merge_bams
Inputs:
key - sample id
logfile - running log
sorted_bam - sorted and quality filtered bam
Outputs:
key - sample id
merged_bam - sorted and quality filtered bam merged by sample
read_count - file with the total reads listed
logfile - running log
Pass through:
Summary:
Use samtools to merge bams from the same sample
Count the number of reads in the sample
Downstream:
split_bam
calc_duplication_rate
Published:
merged_bam - sorted and quality filtered bam merged by sample
Notes:
*************/
cores_merge = params.max_cores < 8 ? params.max_cores : 8
sorted_bams
.groupTuple()
.set { bams_to_merge }
log_premerge.join(bams_to_merge).set{for_merge_bams}
save_bam = {params.output_dir + "/" + it - ~/.bam/ + "/" + it}
process merge_bams {
cache 'lenient'
cpus cores_merge
publishDir path: "${params.output_dir}/", saveAs: save_bam, pattern: "*.bam", mode: 'copy'
input:
set key, file(logfile), file(sorted_bam) from for_merge_bams
output:
set key, file("*.bam"), file("merge_bams.log") into sample_bams
set key, file("*.read_count.txt") into read_count
"""
# bash watch for errors
set -ueo pipefail
cat ${logfile} > merge_bams.log
printf "** Start process 'merge_bams' at: \$(date)\n\n" >> merge_bams.log
printf " Process versions:
\$(samtools --version | tr '\n' ' ')\n\n" >> merge_bams.log
printf " Process command:
samtools merge ${key}.bam $sorted_bam\n\n" >> merge_bams.log
samtools merge -@ $cores_merge ${key}.bam $sorted_bam
printf "${key}\t\$(samtools view -c ${key}.bam)" > ${key}.read_count.txt
printf "** End process 'merge_bams' at: \$(date)\n\n" >> merge_bams.log
"""
}
/*************
Process: split_bam
Inputs:
merged_bam - sorted and quality filtered bam merged by sample
logfile - running log
Outputs:
merged_bam - sorted and quality filtered bam merged by sample - stops here
split_bam - bams split by reference (chromosome)
Pass through:
key - sample id
gtf_path - path to gtf info folder
logfile - running log
Summary:
Use bamtools split to split bam by reference (chromosome) for speed
Combine the small non-chromosomal references to keep file number reasonable
Downstream:
merge_assignment
remove_dups_assign_genes
Published:
Notes:
Potential improvement: find a way to split bams into more evenly sized chunks
*************/
sample_bams.join(gtf_info).set{assign_prepped}
process split_bam {
cache 'lenient'
input:
set key, file(merged_bam), file(logfile), val(gtf_path) from assign_prepped
output:
set key, file("split_bams/*.bam"), val(gtf_path) into split_bams mode flatten
set key, file("remove_dups.log") into split_bam_log
file merged_bam into output
"""
# bash watch for errors
set -ueo pipefail
cat ${logfile} > remove_dups.log
printf "** Start processes 'remove duplicates, assign_genes, merge_assignment' at: \$(date)\n\n" >> remove_dups.log
printf " Process versions:
\$(bedtools --version)
\$(samtools --version | tr '\n' ' ')
\$(bamtools --version | grep bamtools)
\$(python --version)\n\n" >> remove_dups.log
echo ' Process command:
mkdir split_bams
bamtools split -in $merged_bam -reference -stub split_bams/split
samtools index -c in_bam
rmdup.py --bam in_bam --output_bam out.bam
samtools view -c out.bam > split_bam_umi_count.txt
bedtools bamtobed -i out.bam -split
| sort -k1,1 -k2,2n -k3,3n -S 5G
> "in_bam.bed"
bedtools map
-a in_bam.bed
-b exon_index
-nonamecheck -s -f 0.95 -c 7 -o distinct -delim "|"
| bedtools map
-a - -b gene_index
-nonamecheck -s -f 0.95 -c 4 -o distinct -delim "|"
| sort -k4,4 -k2,2n -k3,3n -S 5G
| datamash
-g 4 first 1 first 2 last 3 first 5 first 6 collapse 7 collapse 8
| assign-reads-to-genes.py gene_index
| awk \$3 == "exonic" || \$3 == "intronic" {{
split(\$1, arr, "|")
printf "%s_%s_%s\t%s\t%s\\n", arr[3], arr[4], arr[5], \$2, \$3
}}
| sort -k2,2 -k1,1 -S 5G > in_bam.txt
cat logfile > merge_assignment.log
cat split_bed > key.bed
sort -m -k1,1 -k2,2 split_gene_assign > key_ga.txt
datamash -g 1,2 count 2 < key_ga.txt
| gzip > key.gz
' >> remove_dups.log
printf " Process stats:
remove_dups starting reads: \$(samtools view -c $merged_bam)" >> remove_dups.log
mkdir split_bams
bamtools split -in $merged_bam -reference -stub split_bams/split
cd split_bams
if [[ \$(ls *.bam | egrep -v '_(chr)?([0-9]?[0-9]?[0-9]|M|Mt|MT|MtDNA|mitochondrion_genome|X|Y)\\.bam\$') ]]; then
ls *.bam | egrep -v '_(chr)?([0-9]?[0-9]?[0-9]|M|Mt|MT|MtDNA|mitochondrion_genome|X|Y)\\.bam\$' | samtools merge split.REFnonstand.bam.xxx -b -
ls *.bam | egrep -v '_(chr)?([0-9]?[0-9]?[0-9]|M|Mt|MT|MtDNA|mitochondrion_genome|X|Y)\\.bam\$' | xargs -d"\\n" rm
mv split.REFnonstand.bam.xxx split.REF_nonstand.bam
fi
"""
}
/*************
Process: remove_dups_assign_genes
Inputs:
split_bam - bams split by reference (chromosome)
gtf_path - path to gtf info folder
split_umi_count - file with count of umis in split bam
Outputs:
split_gene_assign - text file with 3 columns: sample|cell, gene, gene type (exonic, intronic)
split_bed - deduplicated sorted bed file
Pass through:
key - sample id
Summary:
1. Remove duplicate reads using rmdup.py
2. Use bedtools map to map the dedupped bed file to all exons with options:
-s forced strandedness
-f 0.95 95% of read must overlap exon
-c 7 map the name of the gene
-o distinct concatenate list of gene names
-delim "|" custom delimiter
-nonamecheck Don't error if there are different naming conventions for the chromosomes
3. Use bedtools map to map output to gene index
-s forced strandedness
-f 0.95 95% of read must overlap exon
-c 4 map the name of the cell name
-o distinct concatenate list of gene names
-delim "|" custom delimiter
-nonamecheck Don't error if there are different naming conventions for the chromosomes
4. Sort and collapse
5. Run assign-reads-to-genes.py to deal with exon v intron
Downstream:
merge_assignment
Published:
Notes:
Potential speed up - remove non-genic reads before sort?
*************/
process remove_dups_assign_genes {
cache 'lenient'
input:
set key, file(split_bam), val(gtf_path) from split_bams
output:
set key, file("*.bed"), file("*_ga.txt"), file("*_umi_count.txt") into remove_dup_part_out
"""
# bash watch for errors
set -ueo pipefail
samtools index -c $split_bam
rmdup.py --bam $split_bam --output_bam out.bam
samtools view -c out.bam > ${split_bam}_umi_count.txt
# bedtools complains now about the sorting. I imagine that this
# may be a result of something like a LOCALE variable. I use
# bedtools to sort instead.
# bedtools bamtobed -i out.bam -split \
# | sort -k1,1 -k2,2n -k3,3n -S 5G \
# > "${split_bam}.bed"
bedtools bamtobed -i out.bam -split > "${split_bam}.bed.unsorted"
bedtools sort -i "${split_bam}.bed.unsorted" > "${split_bam}.bed"
rm ${split_bam}.bed.unsorted
bedtools sort -i "${gtf_path}/latest.exons.bed" > latest.exons.bed.sort
bedtools sort -i "${gtf_path}/latest.genes.bed" > latest.genes.bed.sort
bedtools map \
-a "${split_bam}.bed" \
-b "latest.exons.bed.sort" \
-nonamecheck -s -f 0.95 -c 7 -o distinct -delim '|' \
| bedtools map \
-a - -b "latest.genes.bed.sort" \
-nonamecheck -s -f 0.95 -c 4 -o distinct -delim '|' \
| sort -k4,4 -k2,2n -k3,3n -S 5G\
| datamash \
-g 4 first 1 first 2 last 3 first 5 first 6 collapse 7 collapse 8 \
| assign-reads-to-genes.py "latest.genes.bed.sort" \
| awk '\$3 == "exonic" || \$3 == "intronic" {{
split(\$1, arr, "|")
printf "%s_%s_%s\t%s\t%s\\n", arr[3], arr[4], arr[5], \$2, \$3
}}' \
| sort -k1,1 -k2,2 -S 5G > "${split_bam}_ga.txt"
rm latest.exons.bed.sort latest.genes.bed.sort
"""
}
/*************
Process: merge_assignment
Inputs:
key - sample id
split_gene_assign - text file with 3 columns: sample|cell, gene, gene type (exonic, intronic)
split_bed - deduplicated sorted bed file
logfile - running log
split_umi_count - file with count of umis in split bam
read_count - file with the total reads listed
Outputs:
key - sample id
gene_assign - text file with 3 columns: sample|cell, gene, gene type (exonic, intronic)
cell_gene_count - gzipped text file with a count of cell, gene pairs
logfile - running log
dup_stats - file with duplication rate information for the sample
Pass through:
Summary:
merge bed files by sample
merge gene assignment files by sample
make cell gene count file
calculate duplication rate
Downstream:
count_umis_by_sample
reformat_qc
Published:
Notes:
*************/
remove_dup_part_out
.groupTuple()
.join(split_bam_log)
.join(read_count)
.set { for_cat_dups }
process merge_assignment {
cache 'lenient'
input:
set key, file(split_bed), file(split_gene_assign), file(split_umi_count), file(logfile), file(read_count) from for_cat_dups
output:
set key, file("*.gz"), file("*_ga.txt"), file("merge_assignment.log") into merge_assignment_out
set val(key), file("*duplication_rate_stats.txt") into duplication_rate_out
file "*.bed" into temp_bed
"""
# bash watch for errors
set -ueo pipefail
cat ${logfile} > merge_assignment.log
cat $split_bed > "${key}.bed"
sort -m -k1,1 -k2,2 $split_gene_assign > "${key}_ga.txt"
datamash -g 1,2 count 2 < "${key}_ga.txt" \
| gzip > "${key}.gz"
umi=`cat $split_umi_count | awk '{ sum += \$1 } END { print sum }'`
read=`cut -f2 $read_count`
perc=\$(echo "100.0 * (1 - \$umi/\$read)" | bc -l)
printf "%-18s %10d %10d %7.1f\\n" $key \$read \$umi \$perc \
>"${key}.duplication_rate_stats.txt"
printf "
remove_dups ending reads : \$(wc -l ${key}.bed | awk '{print \$1;}')\n\n
Read assignments:\n\$(awk '{count[\$3]++} END {for (word in count) { printf " %-20s %10i\\n", word, count[word]}}' ${key}_ga.txt)\n\n" >> merge_assignment.log
printf "** End processes 'remove duplicates, assign_genes, merge_assignment' at: \$(date)\n\n" >> merge_assignment.log
"""
}
/*************
Process: count_umis_by_sample
Inputs:
key - sample id
gene_assign - text file with 3 columns: sample|cell, gene, gene type (exonic, intronic)
logfile - running log