-
Notifications
You must be signed in to change notification settings - Fork 720
/
Copy pathmain.nf
1710 lines (1496 loc) · 68.4 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
#!/usr/bin/env nextflow
/*
========================================================================================
nf-core/rnaseq
========================================================================================
nf-core/rnaseq Analysis Pipeline.
#### Homepage / Documentation
https://github.com/nf-core/rnaseq
----------------------------------------------------------------------------------------
*/
def helpMessage() {
log.info nfcoreHeader()
log.info """
Usage:
The typical command for running the pipeline is as follows:
nextflow run nf-core/rnaseq --reads '*_R{1,2}.fastq.gz' --genome GRCh37 -profile docker
Mandatory arguments:
--reads Path to input data (must be surrounded with quotes)
-profile Configuration profile to use. Can use multiple (comma separated)
Available: conda, docker, singularity, awsbatch, test and more.
Generic:
--singleEnd Specifies that the input is single-end reads
References: If not specified in the configuration file or you wish to overwrite any of the references.
--genome Name of iGenomes reference
--star_index Path to STAR index
--hisat2_index Path to HiSAT2 index
--salmon_index Path to Salmon index
--fasta Path to genome fasta file
--transcript_fasta Path to transcript fasta file
--splicesites Path to splice sites file for building HiSat2 index
--gtf Path to GTF file
--gff Path to GFF3 file
--bed12 Path to bed12 file
--saveReference Save the generated reference files to the results directory
--gencode Use fc_group_features_type = 'gene_type' and pass '--gencode' flag to Salmon
--compressedReference If provided, all reference files are assumed to be gzipped and will be unzipped before using
Strandedness:
--forwardStranded The library is forward stranded
--reverseStranded The library is reverse stranded
--unStranded The default behaviour
Trimming:
--clip_r1 [int] Instructs Trim Galore to remove bp from the 5' end of read 1 (or single-end reads)
--clip_r2 [int] Instructs Trim Galore to remove bp from the 5' end of read 2 (paired-end reads only)
--three_prime_clip_r1 [int] Instructs Trim Galore to remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed
--three_prime_clip_r2 [int] Instructs Trim Galore to remove bp from the 3' end of read 2 AFTER adapter/quality trimming has been performed
--trim_nextseq [int] Instructs Trim Galore to apply the --nextseq=X option, to trim based on quality after removing poly-G tails
--pico Sets trimming and standedness settings for the SMARTer Stranded Total RNA-Seq Kit - Pico Input kit. Equivalent to: --forwardStranded --clip_r1 3 --three_prime_clip_r2 3
--saveTrimmed Save trimmed FastQ file intermediates
Alignment:
--aligner Specifies the aligner to use (available are: 'hisat2', 'star')
--pseudo_aligner Specifies the pseudo aligner to use (available are: 'salmon'). Runs in addition to `--aligner`
--stringTieIgnoreGTF Perform reference-guided de novo assembly of transcripts using StringTie i.e. dont restrict to those in GTF file
--seq_center Add sequencing center in @RG line of output BAM header
--saveAlignedIntermediates Save the BAM files from the aligment step - not done by default
--skipAlignment Skip alignment altogether (usually in favor of pseudoalignment)
Read Counting:
--fc_extra_attributes Define which extra parameters should also be included in featureCounts (default: 'gene_name')
--fc_group_features Define the attribute type used to group features. (default: 'gene_id')
--fc_group_features_type Define the type attribute used to group features based on the group attribute (default: 'gene_biotype')
QC:
--skipQC Skip all QC steps apart from MultiQC
--skipFastQC Skip FastQC
--skipPreseq Skip Preseq
--skipDupRadar Skip dupRadar (and Picard MarkDuplicates)
--skipQualimap Skip Qualimap
--skipRseQC Skip RSeQC
--skipEdgeR Skip edgeR MDS plot and heatmap
--skipMultiQC Skip MultiQC
Other options
--sampleLevel Used to turn off the edgeR MDS and heatmap. Set automatically when running on fewer than 3 samples
--outdir The output directory where the results will be saved
-w/--work-dir The temporary directory where intermediate data will be saved
--email Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits
--maxMultiqcEmailFileSize Theshold size for MultiQC report to be attached in notification email. If file generated by pipeline exceeds the threshold, it will not be attached (Default: 25MB)
-name Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic
AWSBatch options:
--awsqueue The AWSBatch JobQueue that needs to be set when running on AWSBatch
--awsregion The AWS Region for your AWS Batch job to run on
""".stripIndent()
}
/*
* SET UP CONFIGURATION VARIABLES
*/
// Show help message
if (params.help){
helpMessage()
exit 0
}
// Check if genome exists in the config file
if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
exit 1, "The provided genome '${params.genome}' is not available in the iGenomes file. Currently the available genomes are ${params.genomes.keySet().join(", ")}"
}
// Reference index path configuration
// Define these here - after the profiles are loaded with the iGenomes paths
params.star_index = params.genome ? params.genomes[ params.genome ].star ?: false : false
params.fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false
params.gtf = params.genome ? params.genomes[ params.genome ].gtf ?: false : false
params.gff = params.genome ? params.genomes[ params.genome ].gff ?: false : false
params.bed12 = params.genome ? params.genomes[ params.genome ].bed12 ?: false : false
params.hisat2_index = params.genome ? params.genomes[ params.genome ].hisat2 ?: false : false
ch_mdsplot_header = Channel.fromPath("$baseDir/assets/mdsplot_header.txt", checkIfExists: true)
ch_heatmap_header = Channel.fromPath("$baseDir/assets/heatmap_header.txt", checkIfExists: true)
ch_biotypes_header = Channel.fromPath("$baseDir/assets/biotypes_header.txt", checkIfExists: true)
Channel.fromPath("$baseDir/assets/where_are_my_files.txt", checkIfExists: true)
.into{ch_where_trim_galore; ch_where_star; ch_where_hisat2; ch_where_hisat2_sort}
// Define regular variables so that they can be overwritten
clip_r1 = params.clip_r1
clip_r2 = params.clip_r2
three_prime_clip_r1 = params.three_prime_clip_r1
three_prime_clip_r2 = params.three_prime_clip_r2
forwardStranded = params.forwardStranded
reverseStranded = params.reverseStranded
unStranded = params.unStranded
// Preset trimming options
if (params.pico){
clip_r1 = 3
clip_r2 = 0
three_prime_clip_r1 = 0
three_prime_clip_r2 = 3
forwardStranded = true
reverseStranded = false
unStranded = false
}
// Validate inputs
if (params.aligner != 'star' && params.aligner != 'hisat2'){
exit 1, "Invalid aligner option: ${params.aligner}. Valid options: 'star', 'hisat2'"
}
if (params.pseudo_aligner && params.pseudo_aligner != 'salmon'){
exit 1, "Invalid pseudo aligner option: ${params.pseudo_aligner}. Valid options: 'salmon'"
}
if( params.star_index && params.aligner == 'star' && !params.skipAlignment ){
if (params.compressedReference){
star_index_gz = Channel
.fromPath(params.star_index, checkIfExists: true)
.ifEmpty { exit 1, "STAR index not found: ${params.star_index}" }
} else{
star_index = Channel
.fromPath(params.star_index, checkIfExists: true)
.ifEmpty { exit 1, "STAR index not found: ${params.star_index}" }
}
}
else if ( params.hisat2_index && params.aligner == 'hisat2' && !params.skipAlignment ){
if (params.compressedReference){
hs2_indices_gz = Channel
.fromPath("${params.hisat2_index}", checkIfExists: true)
.ifEmpty { exit 1, "HISAT2 index not found: ${params.hisat2_index}" }
} else {
hs2_indices = Channel
.fromPath("${params.hisat2_index}*", checkIfExists: true)
.ifEmpty { exit 1, "HISAT2 index not found: ${params.hisat2_index}" }
}
}
else if ( params.fasta && !params.skipAlignment){
if (params.compressedReference) {
Channel.fromPath(params.fasta, checkIfExists: true)
.ifEmpty { exit 1, "Genome fasta file not found: ${params.fasta}" }
.set { genome_fasta_gz }
} else {
Channel.fromPath(params.fasta, checkIfExists: true)
.ifEmpty { exit 1, "Genome fasta file not found: ${params.fasta}" }
.into { ch_fasta_for_star_index; ch_fasta_for_hisat_index }
}
} else if (params.skipAlignment){
println "Skipping alignment ..."
}
else {
exit 1, "No reference genome files specified!"
}
if( params.aligner == 'hisat2' && params.splicesites ){
Channel
.fromPath(params.bed12, checkIfExists: true)
.ifEmpty { exit 1, "HISAT2 splice sites file not found: $alignment_splicesites" }
.into { indexing_splicesites; alignment_splicesites }
}
// Separately check for whether salmon needs a genome fasta to extract
// transcripts from, or can use a transcript fasta directly
if ( params.pseudo_aligner == 'salmon' ) {
if ( params.salmon_index ) {
if (params.compressedReference) {
salmon_index_gz = Channel
.fromPath(params.salmon_index, checkIfExists: true)
.ifEmpty { exit 1, "Salmon index not found: ${params.salmon_index}" }
} else {
salmon_index = Channel
.fromPath(params.salmon_index, checkIfExists: true)
.ifEmpty { exit 1, "Salmon index not found: ${params.salmon_index}" }
}
} else if ( params.transcript_fasta ) {
if (params.compressedReference){
transcript_fasta_gz = Channel
.fromPath(params.transcript_fasta, checkIfExists: true)
.ifEmpty { exit 1, "Transcript fasta file not found: ${params.transcript_fasta}" }
} else {
ch_fasta_for_salmon_index = Channel
.fromPath(params.transcript_fasta, checkIfExists: true)
.ifEmpty { exit 1, "Transcript fasta file not found: ${params.transcript_fasta}" }
}
} else if ( params.fasta && (params.gff || params.gtf)){
log.info "Extracting transcript fastas from genome fasta + gtf/gff"
if (params.compressedReference) {
Channel.fromPath(params.fasta, checkIfExists: true)
.ifEmpty { exit 1, "Genome fasta file not found: ${params.fasta}" }
.set { genome_fasta_gz }
} else {
Channel.fromPath(params.fasta, checkIfExists: true)
.ifEmpty { exit 1, "Genome fasta file not found: ${params.fasta}" }
.set { ch_fasta_for_salmon_transcripts }
}
} else {
exit 1, "To use with `--pseudo_aligner 'salmon'`, must provide either --transcript_fasta or both --fasta and --gtf"
}
}
if( params.gtf ){
if ( params.gff ){
// Prefer gtf over gff
log.info "Prefer GTF over GFF, so ignoring provided GFF in favor of GTF"
}
if (params.compressedReference){
gtf_gz = Channel
.fromPath(params.gtf, checkIfExists: true)
.ifEmpty { exit 1, "GTF annotation file not found: ${params.gtf}" }
} else {
Channel
.fromPath(params.gtf, checkIfExists: true)
.ifEmpty { exit 1, "GTF annotation file not found: ${params.gtf}" }
.into { gtf_makeSTARindex; gtf_makeHisatSplicesites; gtf_makeHISATindex; gtf_makeSalmonIndex; gtf_makeBED12;
gtf_star; gtf_dupradar; gtf_qualimap; gtf_featureCounts; gtf_stringtieFPKM; gtf_salmon; gtf_salmon_merge }
}
} else if ( params.gff ){
if (params.compressedReference){
gff_gz = Channel.fromPath(params.gff, checkIfExists: true)
.ifEmpty { exit 1, "GFF annotation file not found: ${params.gff}" }
} else {
gffFile = Channel.fromPath(params.gff, checkIfExists: true)
.ifEmpty { exit 1, "GFF annotation file not found: ${params.gff}" }
}
} else {
exit 1, "No GTF or GFF3 annotation specified!"
}
if( params.bed12 ){
bed12 = Channel
.fromPath(params.bed12, checkIfExists: true)
.ifEmpty { exit 1, "BED12 annotation file not found: ${params.bed12}" }
.into { bed_rseqc }
}
if (params.gencode){
biotype = "gene_type"
} else {
biotype = params.fc_group_features_type
}
if (params.skipAlignment && !params.pseudo_aligner){
exit 1, "--skipAlignment specified without --pseudo_aligner .. did you mean to specify --pseudo_aligner salmon"
}
if( workflow.profile == 'uppmax' || workflow.profile == 'uppmax-devel' ){
if ( !params.project ) exit 1, "No UPPMAX project ID found! Use --project"
}
// Has the run name been specified by the user?
// this has the bonus effect of catching both -name and --name
custom_runName = params.name
if( !(workflow.runName ==~ /[a-z]+_[a-z]+/) ){
custom_runName = workflow.runName
}
if( workflow.profile == 'awsbatch') {
// AWSBatch sanity checking
if (!params.awsqueue || !params.awsregion) exit 1, "Specify correct --awsqueue and --awsregion parameters on AWSBatch!"
// Check outdir paths to be S3 buckets if running on AWSBatch
// related: https://github.com/nextflow-io/nextflow/issues/813
if (!params.outdir.startsWith('s3:')) exit 1, "Outdir not on S3 - specify S3 Bucket to run on AWSBatch!"
// Prevent trace files to be stored on S3 since S3 does not support rolling files.
if (workflow.tracedir.startsWith('s3:')) exit 1, "Specify a local tracedir or run without trace! S3 cannot be used for tracefiles."
}
// Stage config files
ch_multiqc_config = Channel.fromPath(params.multiqc_config, checkIfExists: true)
ch_output_docs = Channel.fromPath("$baseDir/docs/output.md", checkIfExists: true)
/*
* Create a channel for input read files
*/
if(params.readPaths){
if(params.singleEnd){
Channel
.from(params.readPaths)
.map { row -> [ row[0], [file(row[1][0])]] }
.ifEmpty { exit 1, "params.readPaths was empty - no input files supplied" }
.into { raw_reads_fastqc; raw_reads_trimgalore }
} else {
Channel
.from(params.readPaths)
.map { row -> [ row[0], [file(row[1][0]), file(row[1][1])]] }
.ifEmpty { exit 1, "params.readPaths was empty - no input files supplied" }
.into { raw_reads_fastqc; raw_reads_trimgalore }
}
} else {
Channel
.fromFilePairs( params.reads, size: params.singleEnd ? 1 : 2 )
.ifEmpty { exit 1, "Cannot find any reads matching: ${params.reads}\nNB: Path needs to be enclosed in quotes!\nNB: Path requires at least one * wildcard!\nIf this is single-end data, please specify --singleEnd on the command line." }
.into { raw_reads_fastqc; raw_reads_trimgalore }
}
// Header log info
log.info nfcoreHeader()
def summary = [:]
if(workflow.revision) summary['Pipeline Release'] = workflow.revision
summary['Run Name'] = custom_runName ?: workflow.runName
summary['Reads'] = params.reads
summary['Data Type'] = params.singleEnd ? 'Single-End' : 'Paired-End'
if(params.genome) summary['Genome'] = params.genome
summary['Gzipped Refs?'] = params.compressedReference
if(params.pico) summary['Library Prep'] = "SMARTer Stranded Total RNA-Seq Kit - Pico Input"
summary['Strandedness'] = ( unStranded ? 'None' : forwardStranded ? 'Forward' : reverseStranded ? 'Reverse' : 'None' )
summary['Trimming'] = "5'R1: $clip_r1 / 5'R2: $clip_r2 / 3'R1: $three_prime_clip_r1 / 3'R2: $three_prime_clip_r2 / NextSeq Trim: $params.trim_nextseq"
if(params.aligner == 'star'){
summary['Aligner'] = "STAR"
if(params.star_index) summary['STAR Index'] = params.star_index
else if(params.fasta) summary['Fasta Ref'] = params.fasta
} else if(params.aligner == 'hisat2') {
summary['Aligner'] = "HISAT2"
if(params.hisat2_index) summary['HISAT2 Index'] = params.hisat2_index
else if(params.fasta) summary['Fasta Ref'] = params.fasta
if(params.splicesites) summary['Splice Sites'] = params.splicesites
}
if(params.pseudo_aligner == 'salmon') {
summary['Pseudo Aligner'] = "Salmon"
if(params.transcript_fasta) summary['Transcript Fasta'] = params.transcript_fasta
}
if(params.gtf) summary['GTF Annotation'] = params.gtf
if(params.gff) summary['GFF3 Annotation'] = params.gff
if(params.bed12) summary['BED Annotation'] = params.bed12
if(params.gencode) summary['GENCODE'] = params.gencode
if(params.stringTieIgnoreGTF) summary['StringTie Ignore GTF'] = params.stringTieIgnoreGTF
if(params.fc_group_features_type) summary['Biotype GTF field'] = biotype
summary['Save prefs'] = "Ref Genome: "+(params.saveReference ? 'Yes' : 'No')+" / Trimmed FastQ: "+(params.saveTrimmed ? 'Yes' : 'No')+" / Alignment intermediates: "+(params.saveAlignedIntermediates ? 'Yes' : 'No')
summary['Max Resources'] = "$params.max_memory memory, $params.max_cpus cpus, $params.max_time time per job"
if(workflow.containerEngine) summary['Container'] = "$workflow.containerEngine - $workflow.container"
summary['Output dir'] = params.outdir
summary['Launch dir'] = workflow.launchDir
summary['Working dir'] = workflow.workDir
summary['Script dir'] = workflow.projectDir
summary['User'] = workflow.userName
if(workflow.profile == 'awsbatch'){
summary['AWS Region'] = params.awsregion
summary['AWS Queue'] = params.awsqueue
}
summary['Config Profile'] = workflow.profile
if(params.config_profile_description) summary['Config Description'] = params.config_profile_description
if(params.config_profile_contact) summary['Config Contact'] = params.config_profile_contact
if(params.config_profile_url) summary['Config URL'] = params.config_profile_url
if(params.email) {
summary['E-mail Address'] = params.email
summary['MultiQC maxsize'] = params.maxMultiqcEmailFileSize
}
log.info summary.collect { k,v -> "${k.padRight(18)}: $v" }.join("\n")
log.info "\033[2m----------------------------------------------------\033[0m"
// Check the hostnames against configured profiles
checkHostname()
def create_workflow_summary(summary) {
def yaml_file = workDir.resolve('workflow_summary_mqc.yaml')
yaml_file.text = """
id: 'nf-core-rnaseq-summary'
description: " - this information is collected when the pipeline is started."
section_name: 'nf-core/rnaseq Workflow Summary'
section_href: 'https://github.com/nf-core/rnaseq'
plot_type: 'html'
data: |
<dl class=\"dl-horizontal\">
${summary.collect { k,v -> " <dt>$k</dt><dd><samp>${v ?: '<span style=\"color:#999999;\">N/A</a>'}</samp></dd>" }.join("\n")}
</dl>
""".stripIndent()
return yaml_file
}
/*
* Parse software version numbers
*/
process get_software_versions {
publishDir "${params.outdir}/pipeline_info", mode: 'copy',
saveAs: {filename ->
if (filename.indexOf(".csv") > 0) filename
else null
}
output:
file 'software_versions_mqc.yaml' into software_versions_yaml
file "software_versions.csv"
script:
"""
echo $workflow.manifest.version &> v_ngi_rnaseq.txt
echo $workflow.nextflow.version &> v_nextflow.txt
fastqc --version &> v_fastqc.txt
cutadapt --version &> v_cutadapt.txt
trim_galore --version &> v_trim_galore.txt
STAR --version &> v_star.txt
hisat2 --version &> v_hisat2.txt
stringtie --version &> v_stringtie.txt
preseq &> v_preseq.txt
read_duplication.py --version &> v_rseqc.txt
echo \$(bamCoverage --version 2>&1) > v_deeptools.txt
featureCounts -v &> v_featurecounts.txt
salmon --version &> v_salmon.txt
picard MarkDuplicates --version &> v_markduplicates.txt || true
samtools --version &> v_samtools.txt
multiqc --version &> v_multiqc.txt
Rscript -e "library(edgeR); write(x=as.character(packageVersion('edgeR')), file='v_edgeR.txt')"
Rscript -e "library(dupRadar); write(x=as.character(packageVersion('dupRadar')), file='v_dupRadar.txt')"
unset DISPLAY && qualimap rnaseq > v_qualimap.txt 2>&1 || true
scrape_software_versions.py &> software_versions_mqc.yaml
"""
}
if (params.compressedReference){
// This complex logic is to prevent accessing the genome_fasta_gz variable if
// necessary indices for STAR, HiSAT2, Salmon already exist, or if
// params.transcript_fasta is provided as then the transcript sequences don't
// need to be extracted.
need_star_index = params.aligner == 'star' && !params.star_index
need_hisat2_index = params.aligner == 'hisat2' && !params.hisat2_index
need_aligner_index = need_hisat2_index || need_star_index
alignment_no_indices = !params.skipAlignment && need_aligner_index
psuedoalignment_no_indices = params.pseudo_aligner == "salmon" && !(params.transcript_fasta || params.salmon_index)
if (params.fasta && (alignment_no_indices || psuedoalignment_no_indices)){
process gunzip_genome_fasta {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from genome_fasta_gz
output:
file "${gz.baseName}" into ch_fasta_for_star_index, ch_fasta_for_hisat_index, ch_fasta_for_salmon_transcripts
script:
"""
gunzip -k --verbose --stdout --force ${gz} > ${gz.baseName}
"""
}
}
if (params.gtf){
process gunzip_gtf {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from gtf_gz
output:
file "${gz.baseName}" into gtf_makeSTARindex, gtf_makeHisatSplicesites, gtf_makeHISATindex, gtf_makeSalmonIndex, gtf_makeBED12,
gtf_star, gtf_dupradar, gtf_featureCounts, gtf_stringtieFPKM, gtf_salmon, gtf_salmon_merge, gtf_qualimap
script:
"""
gunzip -k --verbose --stdout --force ${gz} > ${gz.baseName}
"""
}
}
if (params.gff && !params.gtf){
process gunzip_gff {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from gff_gz
output:
file "${gz.baseName}" into gffFile
script:
"""
gunzip --verbose --stdout --force ${gz} > ${gz.baseName}
"""
}
}
if (params.transcript_fasta && params.pseudo_aligner == 'salmon' && !params.salmon_index){
process gunzip_transcript_fasta {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_transcriptome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from transcript_fasta_gz
output:
file "${gz.baseName}" into ch_fasta_for_salmon_index
script:
"""
gunzip --verbose --stdout --force ${gz} > ${gz.baseName}
"""
}
}
if (params.bed12){
process gunzip_bed12 {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from bed12_gz
output:
file "${gz.baseName}" into bed_rseqc
script:
"""
gunzip --verbose --stdout --force ${gz} > ${gz.baseName}
"""
}
}
if (!params.skipAlignment && params.star_index && params.aligner == "star"){
process gunzip_star_index {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome/star" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from star_index_gz
output:
file "${gz.simpleName}" into star_index
script:
// Use tar as the star indices are a folder, not a file
"""
tar -xzvf ${gz}
"""
}
}
if (!params.skipAlignment && params.hisat2_index && params.aligner == 'hisat2'){
process gunzip_hisat_index {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome/hisat2" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from hs2_indices_gz
output:
file "*.ht2*" into hs2_indices
script:
// Use tar as the hisat2 indices are a folder, not a file
"""
tar -xzvf ${gz}
"""
}
}
if (params.salmon_index && params.pseudo_aligner == 'salmon'){
process gunzip_salmon_index {
tag "$gz"
publishDir path: { params.saveReference ? "${params.outdir}/reference_transcriptome/hisat2" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gz from salmon_index_gz
output:
file "${gz.simpleName}" into salmon_index
script:
// Use tar as the hisat2 indices are a folder, not a file
"""
tar -xzvf ${gz}
"""
}
}
}
/*
* PREPROCESSING - Convert GFF3 to GTF
*/
if(params.gff && !params.gtf){
process convertGFFtoGTF {
tag "$gff"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gff from gffFile
output:
file "${gff.baseName}.gtf" into gtf_makeSTARindex, gtf_makeHisatSplicesites, gtf_makeHISATindex, gtf_makeSalmonIndex, gtf_makeBED12,
gtf_star, gtf_dupradar, gtf_featureCounts, gtf_stringtieFPKM, gtf_salmon, gtf_salmon_merge, gtf_qualimap
script:
"""
gffread $gff --keep-exon-attrs -F -T -o ${gff.baseName}.gtf
"""
}
} else {
log.info "Prefer GTF over GFF, so ignoring provided GFF in favor of GTF"
}
/*
* PREPROCESSING - Build BED12 file
*/
if(!params.bed12){
process makeBED12 {
tag "$gtf"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gtf from gtf_makeBED12
output:
file "${gtf.baseName}.bed" into bed_rseqc
script: // This script is bundled with the pipeline, in nfcore/rnaseq/bin/
"""
gtf2bed $gtf > ${gtf.baseName}.bed
"""
}
}
/*
* PREPROCESSING - Build STAR index
*/
if (!params.skipAlignment){
if(params.aligner == 'star' && !params.star_index && params.fasta){
process makeSTARindex {
label 'high_memory'
tag "$fasta"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file fasta from ch_fasta_for_star_index
file gtf from gtf_makeSTARindex
output:
file "star" into star_index
script:
def avail_mem = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : ''
"""
mkdir star
STAR \\
--runMode genomeGenerate \\
--runThreadN ${task.cpus} \\
--sjdbGTFfile $gtf \\
--genomeDir star/ \\
--genomeFastaFiles $fasta \\
$avail_mem
"""
}
}
/*
* PREPROCESSING - Build HISAT2 splice sites file
*/
if(params.aligner == 'hisat2' && !params.splicesites){
process makeHisatSplicesites {
tag "$gtf"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file gtf from gtf_makeHisatSplicesites
output:
file "${gtf.baseName}.hisat2_splice_sites.txt" into indexing_splicesites, alignment_splicesites
script:
"""
hisat2_extract_splice_sites.py $gtf > ${gtf.baseName}.hisat2_splice_sites.txt
"""
}
}
/*
* PREPROCESSING - Build HISAT2 index
*/
if(params.aligner == 'hisat2' && !params.hisat2_index && params.fasta){
process makeHISATindex {
tag "$fasta"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file fasta from ch_fasta_for_hisat_index
file indexing_splicesites from indexing_splicesites
file gtf from gtf_makeHISATindex
output:
file "${fasta.baseName}.*.ht2*" into hs2_indices
script:
if( !task.memory ){
log.info "[HISAT2 index build] Available memory not known - defaulting to 0. Specify process memory requirements to change this."
avail_mem = 0
} else {
log.info "[HISAT2 index build] Available memory: ${task.memory}"
avail_mem = task.memory.toGiga()
}
if( avail_mem > params.hisat_build_memory ){
log.info "[HISAT2 index build] Over ${params.hisat_build_memory} GB available, so using splice sites and exons in HISAT2 index"
extract_exons = "hisat2_extract_exons.py $gtf > ${gtf.baseName}.hisat2_exons.txt"
ss = "--ss $indexing_splicesites"
exon = "--exon ${gtf.baseName}.hisat2_exons.txt"
} else {
log.info "[HISAT2 index build] Less than ${params.hisat_build_memory} GB available, so NOT using splice sites and exons in HISAT2 index."
log.info "[HISAT2 index build] Use --hisat_build_memory [small number] to skip this check."
extract_exons = ''
ss = ''
exon = ''
}
"""
$extract_exons
hisat2-build -p ${task.cpus} $ss $exon $fasta ${fasta.baseName}.hisat2_index
"""
}
}
}
/*
* PREPROCESSING - Create Salmon transcriptome index
*/
if(params.pseudo_aligner == 'salmon' && !params.salmon_index){
if(!params.transcript_fasta) {
process transcriptsToFasta {
tag "$fasta"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
when:
!params.transcript_fasta
input:
file fasta from ch_fasta_for_salmon_transcripts
file gtf from gtf_makeSalmonIndex
output:
file "*.fa" into ch_fasta_for_salmon_index
script:
// filter_gtf_for_genes_in_genome.py is bundled in this package, in rnaseq/bin
"""
filter_gtf_for_genes_in_genome.py --gtf $gtf --fasta $fasta -o ${gtf.baseName}__in__${fasta.baseName}.gtf
gffread -F -w transcripts.fa -g $fasta ${gtf.baseName}__in__${fasta.baseName}.gtf
"""
}
}
process makeSalmonIndex {
label "salmon"
tag "$fasta"
publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.saveReference ? it : null }, mode: 'copy'
input:
file fasta from ch_fasta_for_salmon_index
output:
file 'salmon_index' into salmon_index
script:
def gencode = params.gencode ? "--gencode" : ""
"""
salmon index --threads $task.cpus -t $fasta $gencode -i salmon_index
"""
}
}
/*
* STEP 1 - FastQC
*/
process fastqc {
tag "$name"
publishDir "${params.outdir}/fastqc", mode: 'copy',
saveAs: {filename -> filename.indexOf(".zip") > 0 ? "zips/$filename" : "$filename"}
when:
!params.skipQC && !params.skipFastQC
input:
set val(name), file(reads) from raw_reads_fastqc
output:
file "*_fastqc.{zip,html}" into fastqc_results
script:
"""
fastqc -q $reads
"""
}
/*
* STEP 2 - Trim Galore!
*/
process trim_galore {
label 'low_memory'
tag "$name"
publishDir "${params.outdir}/trim_galore", mode: 'copy',
saveAs: {filename ->
if (filename.indexOf("_fastqc") > 0) "FastQC/$filename"
else if (filename.indexOf("trimming_report.txt") > 0) "logs/$filename"
else if (!params.saveTrimmed && filename == "where_are_my_files.txt") filename
else if (params.saveTrimmed && filename != "where_are_my_files.txt") filename
else null
}
input:
set val(name), file(reads) from raw_reads_trimgalore
file wherearemyfiles from ch_where_trim_galore.collect()
output:
set val(name), file("*fq.gz") into trimmed_reads_alignment, trimmed_reads_salmon
file "*trimming_report.txt" into trimgalore_results
file "*_fastqc.{zip,html}" into trimgalore_fastqc_reports
file "where_are_my_files.txt"
script:
c_r1 = clip_r1 > 0 ? "--clip_r1 ${clip_r1}" : ''
c_r2 = clip_r2 > 0 ? "--clip_r2 ${clip_r2}" : ''
tpc_r1 = three_prime_clip_r1 > 0 ? "--three_prime_clip_r1 ${three_prime_clip_r1}" : ''
tpc_r2 = three_prime_clip_r2 > 0 ? "--three_prime_clip_r2 ${three_prime_clip_r2}" : ''
nextseq = params.trim_nextseq > 0 ? "--nextseq ${params.trim_nextseq}" : ''
if (params.singleEnd) {
"""
trim_galore --fastqc --gzip $c_r1 $tpc_r1 $nextseq $reads
"""
} else {
"""
trim_galore --paired --fastqc --gzip $c_r1 $c_r2 $tpc_r1 $tpc_r2 $nextseq $reads
"""
}
}
/*
* STEP 3 - align with STAR
*/
// Function that checks the alignment rate of the STAR output
// and returns true if the alignment passed and otherwise false
skipped_poor_alignment = []
def check_log(logs) {
def percent_aligned = 0;
logs.eachLine { line ->
if ((matcher = line =~ /Uniquely mapped reads %\s*\|\s*([\d\.]+)%/)) {
percent_aligned = matcher[0][1]
}
}
logname = logs.getBaseName() - 'Log.final'
if(percent_aligned.toFloat() <= '5'.toFloat() ){
log.info "#################### VERY POOR ALIGNMENT RATE! IGNORING FOR FURTHER DOWNSTREAM ANALYSIS! ($logname) >> ${percent_aligned}% <<"
skipped_poor_alignment << logname
return false
} else {
log.info " Passed alignment > star ($logname) >> ${percent_aligned}% <<"
return true
}
}
if (!params.skipAlignment){
if(params.aligner == 'star'){
hisat_stdout = Channel.from(false)
process star {
label 'high_memory'
tag "$name"
publishDir "${params.outdir}/STAR", mode: 'copy',
saveAs: {filename ->
if (filename.indexOf(".bam") == -1) "logs/$filename"
else if (!params.saveAlignedIntermediates && filename == "where_are_my_files.txt") filename
else if (params.saveAlignedIntermediates && filename != "where_are_my_files.txt") filename
else null
}
input:
set val(name), file(reads) from trimmed_reads_alignment
file index from star_index.collect()
file gtf from gtf_star.collect()
file wherearemyfiles from ch_where_star.collect()
output:
set file("*Log.final.out"), file ('*.bam') into star_aligned
file "*.out" into alignment_logs
file "*SJ.out.tab"
file "*Log.out" into star_log
file "where_are_my_files.txt"
file "${prefix}Aligned.sortedByCoord.out.bam.bai" into bam_index_rseqc, bam_index_genebody
script:
prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
def star_mem = task.memory ?: params.star_memory ?: false
def avail_mem = star_mem ? "--limitBAMsortRAM ${star_mem.toBytes() - 100000000}" : ''
seqCenter = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter' 'SM:$prefix'" : "--outSAMattrRGline ID:$prefix 'SM:$prefix'"
"""
STAR --genomeDir $index \\
--sjdbGTFfile $gtf \\
--readFilesIn $reads \\
--runThreadN ${task.cpus} \\
--twopassMode Basic \\
--outWigType bedGraph \\
--outSAMtype BAM SortedByCoordinate $avail_mem \\
--readFilesCommand zcat \\
--runDirPerm All_RWX \\
--outFileNamePrefix $prefix $seqCenter
samtools index ${prefix}Aligned.sortedByCoord.out.bam
"""
}
// Filter removes all 'aligned' channels that fail the check
star_aligned
.filter { logs, bams -> check_log(logs) }
.flatMap { logs, bams -> bams }
.into { bam_count; bam_rseqc; bam_qualimap; bam_preseq; bam_markduplicates; bam_featurecounts; bam_stringtieFPKM; bam_forSubsamp; bam_skipSubsamp }
}
/*
* STEP 3 - align with HISAT2
*/
if(params.aligner == 'hisat2'){
star_log = Channel.from(false)
process hisat2Align {
label 'high_memory'
tag "$name"
publishDir "${params.outdir}/HISAT2", mode: 'copy',
saveAs: {filename ->
if (filename.indexOf(".hisat2_summary.txt") > 0) "logs/$filename"
else if (!params.saveAlignedIntermediates && filename == "where_are_my_files.txt") filename
else if (params.saveAlignedIntermediates && filename != "where_are_my_files.txt") filename
else null
}
input:
set val(name), file(reads) from trimmed_reads_alignment
file hs2_indices from hs2_indices.collect()
file alignment_splicesites from alignment_splicesites.collect()
file wherearemyfiles from ch_where_hisat2.collect()
output:
file "${prefix}.bam" into hisat2_bam
file "${prefix}.hisat2_summary.txt" into alignment_logs
file "where_are_my_files.txt"
script:
index_base = hs2_indices[0].toString() - ~/.\d.ht2l?/
prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
seqCenter = params.seqCenter ? "--rg-id ${prefix} --rg CN:${params.seqCenter.replaceAll('\\s','_')} SM:$prefix" : "--rg-id ${prefix} --rg SM:$prefix"
def rnastrandness = ''
if (forwardStranded && !unStranded){
rnastrandness = params.singleEnd ? '--rna-strandness F' : '--rna-strandness FR'
} else if (reverseStranded && !unStranded){
rnastrandness = params.singleEnd ? '--rna-strandness R' : '--rna-strandness RF'
}
if (params.singleEnd) {
"""
hisat2 -x $index_base \\
-U $reads \\
$rnastrandness \\
--known-splicesite-infile $alignment_splicesites \\
-p ${task.cpus} \\
--met-stderr \\