-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain.nf
595 lines (466 loc) · 19 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
#! /usr/bin/env nextflow
nextflow.enable.dsl=2
include { bbduk_clean; samps_idtranslate } from './modules/rawfq_clean.nf'
//include { fastQC; multiQC_raw; multiQC_clean; multiQC_filt; multiQC_bowtie_amp } from './modules/seq_stats.nf'
include { fastQC; multiQC; multiQC_bowtie } from './modules/seq_stats.nf'
include { generate_index_bowtie; bowtie_amplicons_alignment; bowtie_amplicons_alignment_sg } from './modules/reads_align.nf'
include { megahit_assembly_all; metaspades_assembly} from './modules/reads_assembly.nf'
include { make_db_for_blast; do_blastn; do_tblastx; blast_sum_coverage; do_cov_on_viralcandidates } from './modules/contigs_align.nf'
include { kaiju_raw; discard_nonviral; kaiju_contigs; kaiju_summarize; extract_ids } from './modules/taxonomy.nf'
include { coverage_plots; align_counts_plot } from './modules/plots.nf'
include { handle_contamination_pr } from './modules/contamination.nf'
include { fill_html_report; make_summary_tbl } from './modules/sum_and_report.nf'
include { create_logd; create_filesys } from './modules/init.nf'
def samplesMap = [:]
SamplesDef = file(params.samp) // (samplestbl_file)
SamplesDef.eachLine {
line -> {
def sp = line.split('\t')
// ignore lines stating with "#"
if (!sp[0].startsWith("#")) {
samplesMap.(sp[0]) = (sp[1])
}
}
}
log.info """\
========================================
C A P T V R E D - N F P I P E L I N E
========================================
RUN : ${params.runID}
Samples : ${samplesMap}
SysInfo : ${workflow.userName} SID=${workflow.sessionId} NCPUs=${params.NCPUS} GITcid=${workflow.commitId}
========================================
"""
if ( params.help ) {
help = """main.nf: Start CAPTVRED pipeline for TES datasets sequences analyses.
|Required arguments:
| --samp Tabulated file with samples information.Templete named "samples_Definition_template.tbl" is provided with this repository.
| --fastq_dir Root directory for read fastq files.
| --runID Identification (name or code) of the run.
|
|
|Optional arguments:
|
| --help Print this help message
| --NCPUS Maximum number of threads available for the demanding steps of the pipeline. [default:32]
| --R1 Suffix for read 1 fastq files. [default: _R1_001]
| --R2 Suffix for read 2 fastq files. [default: _R2_001]
| --assembler megahit(default) or metaspades
| --taxalg Taxonomy algorithm. blastn(default), tblastx or kaiju
| --handle_contamination [default: false]. If true, fasta file must be provided.
| --do_cov_figures [default: true ]
"""
// Print the help with the stripped margin and exit
println(help)
exit(0)
}
workflow init_run() {
take:
fsys
logfl
main:
println "# INIT: $samplesMap"
// fsys.view()
create_filesys(fsys, logfl)
emit:
create_filesys.out
}
workflow fastqc_onrawseqs() {
take:
logfl
main:
def thysamples = samplesMap
def ids=[]
thysamples.each { sampleID, illuminaID ->
ids << illuminaID
}
def spstr=ids.join(",")
def regx="$params.fastq_dir/{$spstr}$params.rawfq_sfx"
println "### SAMPS STRING IS: $spstr ###"
spschan=Channel.fromPath("$regx")
fastQC(spschan, params.rawqc_dir, params.logs_dir)
sampsqual=fastQC.out.collect()
multiQC(sampsqual, params.reports_dir, params.logs_dir, "raw")
// multiQC_raw(sampsqual, params.reports_dir, params.logs_dir)
}
workflow reads_clean() {
take:
x
fastq_dir
clnfq_dir
main:
def paths_list=[]
//paths_list is a LoL: where first item is the raw fastq root
//for each sample and the second one is the new root for the cleanseqs.
def thysamples = samplesMap
thysamples.each { sampleID, illuminaID ->
def newsamp=["$fastq_dir/$illuminaID", "$clnfq_dir/$sampleID"]
paths_list << newsamp
}samps_idtranslate
def mychan=Channel.from(paths_list)
println "Total samples in mychan: ${paths_list.size()}"
// mychan.view()
if (params.trim_adapters == true ) {
bbduk_clean(x, mychan, params.logs_dir, params.bbdukREF)
cleansps=fastQC( bbduk_clean.out.mix(), params.rawqc_dir, params.logs_dir ).collect()
multiQC( cleansps, params.reports_dir, params.logs_dir, "clean")
// multiQC_clean( cleansps, params.reports_dir, params.logs_dir)
out1=bbduk_clean.out.outPE1
out2=bbduk_clean.out.outPE2
outS=bbduk_clean.out.outSGL
} else {
samps_idtranslate(x, Channel.from(paths_list))
out1=samps_idtranslate.out.outPE1
out2=samps_idtranslate.out.outPE2
outS=samps_idtranslate.out.outSGL
}
emit:
PE1=out1
PE2=out2
SGL=outS
}
workflow idtranslate() {
take:
x
fastq_dir
clnfq_dir
main:
def paths_list=[]
//paths_list is a LoL: where first item is the raw fastq root
//for each sample and the second one is the new root for the cleanseqs.
def thysamples = samplesMap
thysamples.each { sampleID, illuminaID ->
def newsamp=["$fastq_dir/$illuminaID", "$clnfq_dir/$sampleID"]
paths_list << newsamp
}
samps_idtranslate(x, Channel.from(paths_list))
emit:
PE1=samps_idtranslate.out.outPE1
PE2=samps_idtranslate.out.outPE2
SGL=samps_idtranslate.out.outSGL
}
workflow reads_filter_nonviral() {
//errorStrategy 'finish'
take:
samps
kdb_dir // Kaiju database directory (NR_EUK)
ncbi_dir // ncbi directory (for names.dmp and nodes.dmp)
tax_dir // taxnonomy directory
main:
kaiju_raw(samps, kdb_dir, ncbi_dir, tax_dir)
kaiju_raw.out.view()
discard_nonviral(kaiju_raw.out, params.clnfq_dir)
// discard_nonviral.out.SGLout.view()
sampsfilt=fastQC( discard_nonviral.out.mix(), params.rawqc_dir, params.logs_dir ).collect()
multiQC( sampsfilt, params.reports_dir, params.logs_dir, "filt")
emit:
discard_nonviral.out.PE1out
discard_nonviral.out.PE2out
discard_nonviral.out.SGLout
}
/*
workflow amplicon_sequences_dbinit() {
take:
x
refseqs
main:
generate_index_bowtie(refseqs)
emit:
generate_index_bowtie.out
}
*/
workflow reads_align_wf() {
take:
cluster_index_path
pe1
pe2
sgl
main:
bowtie_amplicons_alignment(cluster_index_path, pe1, pe2, sgl, params.ampaln_dir)
bowtie_amplicons_alignment_sg(cluster_index_path, pe1, pe2, sgl, params.ampaln_dir )
// samps_align=multiQC_bowtie_amp(bowtie_amplicons_alignment.out.mix(bowtie_amplicons_alignment_sg.out).collect())
peout=bowtie_amplicons_alignment.out.LOG.mix(bowtie_amplicons_alignment.out.STS)
sgout=bowtie_amplicons_alignment_sg.out.LOG.mix(bowtie_amplicons_alignment_sg.out.STS)
samps_align=peout.mix(sgout).collect()
// samps_align.view()
multiQC_bowtie( samps_align, params.reports_dir, params.logs_dir, "align")
emit:
ALL=samps_align
PE=bowtie_amplicons_alignment.out.bamPE
SG=bowtie_amplicons_alignment_sg.out.bamSG
}
workflow vizualise_results_flow() {
take:
pebam
sgbam
blasttbl
brh
bindir
repdir
dbdir
gffdir
main:
coverage_plots(pebam,
sgbam,
blasttbl,
brh,
bindir,
repdir,
dbdir,
gffdir
)
emit:
coverage_plots.out.ODIR
}
workflow direct_blast_n () {
take:
ref_fasta
all_contigs
main:
make_db_for_blast( ref_fasta, "FALSE")
do_blastn(all_contigs, make_db_for_blast.out.DB, params.subtax_dir)
if (params.handle_contamination == true ) {
handle_contamination_pr( params.cids,
params.cfaa,
do_blastn.out.OUT,
do_blastn.out.CONTIGS )
blastOut=handle_contamination_pr.out
} else {
blastOut=do_blastn.out.OUT
}
blast_sum_coverage(blastOut,
"F",
"F",
params.refdb_dir,
params.subasb_dir,
params.bindir,
params.reports_dir )
emit:
BY_R=blast_sum_coverage.out.BYR
BY_SQ=blast_sum_coverage.out.BYSQ
BY_SP=blast_sum_coverage.out.BYSP
S_SUM=blast_sum_coverage.out.SUM
CFA=all_contigs
DONE=blast_sum_coverage.out.SUM2
}
workflow direct_blast_tx () {
take:
ref_fasta
all_contigs
main:
make_db_for_blast( ref_fasta, "FALSE")
do_tblastx(all_contigs, make_db_for_blast.out.DB, params.taxtbxdir)
if (params.handle_contamination == true ) {
handle_contamination_pr( params.cids,
params.cfaa,
do_tblastx.out.OUT,
do_tblastx.out.CONTIGS )
blastOut=handle_contamination_pr.out
} else {
blastOut=do_tblastx.out.OUT
}
blast_sum_coverage(blastOut, "F", "F" )
emit:
BY_R=blast_sum_coverage.out.BYR
BY_SQ=blast_sum_coverage.out.BYSQ
BY_SP=blast_sum_coverage.out.BYSP
S_SUM=blast_sum_coverage.out.SUM
CFA=all_contigs
DONE=blast_sum_coverage.out.SUM2
}
workflow coverage_compute() {
take:
contigs_fa
assign_byr
reffa
main:
// reffa="${params.amplicon_refseqs_dir}/${params.amplicon_refseqs}"
make_db_for_blast( reffa, "FALSE") // FALSE refers to: not redo db if it already exists.
do_cov_on_viralcandidates("${params.refdb_dir}/${params.set_tax}",
make_db_for_blast.out.DB,
contigs_fa,
assign_byr,
params.bl_suffix,
params.bindir,
params.tmp_dir,
params.cov_dir
)
emit:
blastout=do_cov_on_viralcandidates.out.BLOUT
coverage=do_cov_on_viralcandidates.out.COV
}
// // // // // // MAIN // // // // // //
params.basedir = workflow.launchDir
params.ctvdir = workflow.projectDir
params.refseqs = "${params.ctvdir}/references"
params.bindir = "${params.ctvdir}/bin"
params.db_dir = "${params.refseqs}/db"
params.refdb_dir = "${params.db_dir}/${params.refdb_name}"
params.gff_dir = "${params.refdb_dir}/gff_refgenomes"
params.kaijudir = "${params.db_dir}/kaiju"
params.ncbidir = "${params.db_dir}/ncbi"
params.dbset_dir = "${params.refseqs}/${params.setname}"
params.bbdukREF = "${params.refseqs}/bbmap/resources/adapters.fa"
params.tmp_dir = "${params.basedir}/tmp"
params.rawqc_dir = "${params.basedir}/raw"
params.clnfq_dir = "${params.basedir}/clean"
params.ampaln_dir = "${params.basedir}/aln"
params.asbl_dir = "${params.basedir}/assembly"
params.taxdir = "${params.basedir}/taxonomy"
params.cov_dir = "${params.basedir}/coverage"
params.reports_dir = "${params.basedir}/reports"
params.logs_dir = "${params.basedir}/logs"
params.html_dir = "${params.basedir}/html"
if (params.assembler ==~ /(?i)MEGAHIT/){
params.subasb_dir="$params.asbl_dir/megahit"
}else if (params.assembler ==~ /(?i)METASPADES/ ) {
params.subasb_dir="$params.asbl_dir/metaspades"
}
if (params.taxalg ==~ /(?i)KAIJU/ ) {
params.subtax_dir="$params.taxdir/kaiju"
} else if (params.taxalg ==~ /(?)BLASTN/ ){
params.subtax_dir="$params.taxdir/blastn"
} else if (params.taxalg ==~ /(?)TBLASTX/ ){
params.subtax_dir="$params.taxdir/tblastx"
}
workflow () {
//check_params()
println "# Running : $workflow.scriptId - $workflow.scriptName"
println "# Project : $workflow.projectDir"
println "# Bdir : $workflow.launchDir"
println "# Starting : $workflow.userName $ZERO $workflow.start"
println "# Reading samples for $params.runID from $params.samp"
println " ### $workflow.launchDir ## $params.bindir ## $params.refseqs ## $params.tmp_dir ## $params.html_dir"
//set_dep_params() // | collect | init_run()
//Channel.of(set_dep_params.out).view()
// def d = set_dep_params.out.collect()
def filesystem = Channel.of( params.tmp_dir,
params.fastq_dir,
params.clnfq_dir,
params.ampaln_dir,
params.asbl_dir,
params.subasb_dir,
params.taxdir,
params.subtax_dir,
params.reports_dir)
create_logd(params.logs_dir)
init_run(filesystem, create_logd.out)
// 1 // Clean reads // //
fastqc_onrawseqs(init_run.out)
reads_clean(init_run.out, params.fastq_dir, params.clnfq_dir )
// 2 // Discard reads identified as nonviral // //
KDB=Channel.from(params.kaijuDBRAW)
CLNR=reads_clean.out.merge()
to_kaiju=KDB.combine(CLNR).merge()
// to_kaiju.view()
reads_filter_nonviral(to_kaiju, params.kaijudir, params.ncbidir, params.taxdir)
// 3 // Map reads on database // //
dbtobowtie="$params.refdb_dir/$params.fams_subset"
generate_index_bowtie(dbtobowtie)
reads_align_wf(generate_index_bowtie.out, reads_filter_nonviral.out)
// 4 // Assembly reads into contigs // //
if (params.assembler ==~ /(?i)MEGAHIT/){
megahit_assembly_all(reads_filter_nonviral.out,
params.subasb_dir,
params.logs_dir )
CNFA=megahit_assembly_all.out.CGSout
}else if (params.assembler ==~ /(?i)METASPADES/ ){
metaspades_assembly(reads_filter_nonviral.out,
params.subasb_dir
)
CNFA=metaspades_assembly.out.CGSout
}
// 5 // Taxonomic classification of contigs // //
if (params.taxalg ==~ /(?i)KAIJU/ ) {
// 5.1. FAST APPROACH//
// 5.1.1. Protein-level classification (KAIJU) //
KCDB=Channel.from(params.kaijudb)
to_kaiju_contigs=KCDB.combine(CNFA.merge()).merge()
kaiju_contigs(to_kaiju_contigs)
kaiju_summarize(kaiju_contigs.out.NM)
blOUT=""
covOUT=""
byreadfl=kaiju_summarize.out.BYR
byseqfl=kaiju_summarize.out.BYSQ
byspecfl=""
statssum=kaiju_summarize.out.SUM
kronaPT=kaiju_contigs.out.KP
FIN=kaiju_summarize.out.DONE.collect()
} else if (params.taxalg ==~ /(?)BLASTN/ ){
//Directly blast into database //
ref_fa="${params.refdb_dir}/${params.fams_subset}";
// blast_flow( ref_fa, CNFA.merge())
// direct_blast(ref_fa, CNFA.merge())
direct_blast_n(ref_fa, CNFA)
if ( params.do_cov_figures == true) {
ref_fasta="$params.refdb_dir/${params.set_seqs}"
coverage_compute(direct_blast_n.out.CFA,
direct_blast_n.out.BY_R,
ref_fasta
)
blOUT=coverage_compute.out.blastout
covOUT=coverage_compute.out.coverage
} else {
blOUT=""
covOUT=""
}
byreadfl=direct_blast_n.out.BY_R
byseqfl=direct_blast_n.out.BY_SQ
byspecfl=direct_blast_n.out.BY_SP
statssum=direct_blast_n.out.S_SUM
kronaPT=""
FIN=direct_blast_n.out.DONE.collect()
} else if (params.taxalg ==~ /(?)TBLASTX/ ){
// Directly blast into database //
ref_fa="${params.blast_refseqs_dir}/${params.blast_ref_db_name}";
direct_blast_tx(ref_fa, CNFA)
if ( params.do_cov_figures == true) {
coverage_compute(direct_blast_tx.out.CFA,
direct_blast_tx.out.BY_R
)
blOUT=coverage_compute.out.blastout
covOUT=coverage_compute.out.coverage
} else {
Channel.from("TAXONOMY APPROACH IS NOT AVAILABLE... please check your spelling!").view()
blOUT=""
covOUT=""
}
byreadfl=direct_blast_tx.out.BY_R
byseqfl=direct_blast_tx.out.BY_SQ
byspecfl=direct_blast_tx.out.BY_SP
statssum=direct_blast_tx.out.S_SUM
kronaPT=""
FIN=direct_blast_tx.out.DONE.collectFile(name: "${params.tmp_dir}/allstats.txt", newLine: true)
// collect()
}
// 6 // Reporting results
// 6.1. // Summary tables // //
sampdef="$params.samp"
make_summary_tbl(FIN, params.subasb_dir, params.reports_dir, params.bindir, sampdef)
// 6.2. // Plot coverage by genome (reads and contigs)
vizualise_results_flow(
reads_align_wf.out.PE,
reads_align_wf.out.SG,
blOUT,
covOUT,
params.bindir,
params.reports_dir,
params.refdb_dir,
params.gff_dir
)
figsDIR=vizualise_results_flow.out
// 6.3. // HTML report.
fill_html_report (make_summary_tbl.out,
sampdef,
params.bindir,
figsDIR,
params.reports_dir,
params.html_dir)
// 6.2 // Taxonomy summary
// taxon_outkaiju (*.rvdb.names.out file)
// blast_unc_x_cl.RPT
// blast_unc_x_cl.out.RPT
}
workflow.onComplete {
log.info ( workflow.success ? "\nDone! Open the reports in your browser...\n" : "Oops .. something went wrong: ${workflow.errorMessage}" )
}