forked from nf-core/rnaseq
-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow_schema.json
871 lines (871 loc) · 47.2 KB
/
nextflow_schema.json
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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/nf-core/rnaseq/master/nextflow_schema.json",
"title": "nf-core/rnaseq pipeline parameters",
"description": "RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.",
"type": "object",
"definitions": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["input", "outdir"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"schema": "assets/schema_input.json",
"description": "Path to comma-separated file containing information about the samples in the experiment.",
"help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row. See [usage docs](https://nf-co.re/rnaseq/usage#samplesheet-input).",
"fa_icon": "fas fa-file-csv"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
},
"multiqc_title": {
"type": "string",
"description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
"fa_icon": "fas fa-file-signature"
}
}
},
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Reference genome related files and options required for the workflow.",
"properties": {
"genome": {
"type": "string",
"description": "Name of iGenomes reference.",
"fa_icon": "fas fa-book",
"help_text": "If using a reference genome configured in the pipeline using iGenomes (not recommended), use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
},
"fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"description": "Path to FASTA genome file.",
"help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have the appropriate alignment index available this will be generated for you automatically. Combine with `--save_reference` to save alignment index for future runs.",
"fa_icon": "far fa-file-code"
},
"gtf": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.gtf(\\.gz)?$",
"description": "Path to GTF annotation file.",
"fa_icon": "fas fa-code-branch",
"help_text": "This parameter is *mandatory* if `--genome` is not specified."
},
"gff": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.gff(\\.gz)?$",
"fa_icon": "fas fa-code-branch",
"description": "Path to GFF3 annotation file.",
"help_text": "This parameter must be specified if `--genome` or `--gtf` are not specified."
},
"gene_bed": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"fa_icon": "fas fa-procedures",
"description": "Path to BED file containing gene intervals. This will be created from the GTF file if not specified."
},
"transcript_fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"fa_icon": "far fa-file-code",
"description": "Path to FASTA transcriptome file."
},
"additional_fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"fa_icon": "far fa-file-code",
"description": "FASTA file to concatenate to genome FASTA file e.g. containing spike-in sequences.",
"help_text": "If provided, the sequences in this file will get concatenated to the existing genome FASTA file, a GTF file will be automatically created using the entire sequence as the gene, transcript, and exon features, and any alignment index will get created from the combined FASTA and GTF. It is recommended to save the reference with `--save_reference` to re-use the index for future runs so you do not need to create it again."
},
"splicesites": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"fa_icon": "fas fa-hand-scissors",
"description": "Splice sites file required for HISAT2."
},
"star_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built STAR index."
},
"hisat2_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built HISAT2 index."
},
"rsem_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built RSEM index."
},
"salmon_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built Salmon index."
},
"kallisto_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built Kallisto index."
},
"hisat2_build_memory": {
"type": "string",
"default": "200.GB",
"fa_icon": "fas fa-memory",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"description": "Minimum memory required to use splice sites and exons in the HiSAT2 index build process.",
"help_text": "HiSAT2 requires a huge amount of RAM to build a genome index for larger genomes, if including splice sites and exons e.g. the human genome might typically require 200GB. If you specify less than this threshold for the `HISAT2_BUILD` process then the splice sites and exons will be ignored, meaning that the process will require a lot less memory. If you are working with a small genome, set this parameter to a lower value to reduce the threshold for skipping this check. If using a larger genome, consider supplying more memory to the `HISAT2_BUILD` process."
},
"gencode": {
"type": "boolean",
"fa_icon": "fas fa-code-branch",
"description": "Specify if your GTF annotation is in GENCODE format.",
"help_text": "If your GTF file is in GENCODE format and you would like to run Salmon i.e. `--pseudo_aligner salmon`, you will need to provide this parameter in order to build the Salmon index appropriately."
},
"gtf_extra_attributes": {
"type": "string",
"default": "gene_name",
"fa_icon": "fas fa-plus-square",
"description": "By default, the pipeline uses the `gene_name` field to obtain additional gene identifiers from the input GTF file when running Salmon.",
"help_text": "This behaviour can be modified by specifying `--gtf_extra_attributes` when running the pipeline. Note that you can also specify more than one desired value, separated by a comma e.g. `--gtf_extra_attributes gene_id,...`.\n"
},
"gtf_group_features": {
"type": "string",
"default": "gene_id",
"description": "Define the attribute type used to group features in the GTF file when running Salmon.",
"fa_icon": "fas fa-layer-group"
},
"featurecounts_group_type": {
"type": "string",
"default": "gene_biotype",
"fa_icon": "fas fa-layer-group",
"description": "The attribute type used to group feature types in the GTF file when generating the biotype plot with featureCounts."
},
"featurecounts_feature_type": {
"type": "string",
"default": "exon",
"description": "By default, the pipeline assigns reads based on the 'exon' attribute within the GTF file.",
"fa_icon": "fas fa-indent",
"help_text": "The feature type used from the GTF file when generating the biotype plot with featureCounts."
},
"igenomes_base": {
"type": "string",
"format": "directory-path",
"description": "Directory / URL base for iGenomes references.",
"default": "s3://ngi-igenomes/igenomes",
"fa_icon": "fas fa-cloud-download-alt",
"hidden": true
},
"igenomes_ignore": {
"type": "boolean",
"description": "Do not load the iGenomes reference config.",
"fa_icon": "fas fa-ban",
"hidden": true,
"help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
}
},
"required": ["fasta"]
},
"read_trimming_options": {
"title": "Read trimming options",
"type": "object",
"fa_icon": "fas fa-cut",
"description": "Options to adjust read trimming criteria.",
"properties": {
"trimmer": {
"type": "string",
"default": "trimgalore",
"description": "Specifies the trimming tool to use - available options are 'trimgalore' and 'fastp'.",
"fa_icon": "fas fa-cut",
"enum": ["trimgalore", "fastp"]
},
"extra_trimgalore_args": {
"type": "string",
"description": "Extra arguments to pass to Trim Galore! command in addition to defaults defined by the pipeline.",
"fa_icon": "fas fa-plus"
},
"extra_fastp_args": {
"type": "string",
"description": "Extra arguments to pass to fastp command in addition to defaults defined by the pipeline.",
"fa_icon": "fas fa-plus"
},
"min_trimmed_reads": {
"type": "integer",
"default": 10000,
"fa_icon": "fas fa-hand-paper",
"description": "Minimum number of trimmed reads below which samples are removed from further processing. Some downstream steps in the pipeline will fail if this threshold is too low."
}
}
},
"read_filtering_options": {
"title": "Read filtering options",
"type": "object",
"description": "Options for filtering reads prior to alignment",
"default": "",
"properties": {
"bbsplit_fasta_list": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"fa_icon": "fas fa-list-alt",
"description": "Path to comma-separated file containing a list of reference genomes to filter reads against with BBSplit. You have to also explicitly set `--skip_bbsplit false` if you want to use BBSplit.",
"help_text": "The file should contain 2 columns: short name and full path to reference genome(s) e.g. \n```\nmm10,/path/to/mm10.fa\necoli,/path/to/ecoli.fa\n```"
},
"bbsplit_index": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-bezier-curve",
"description": "Path to directory or tar.gz archive for pre-built BBSplit index.",
"help_text": "The BBSplit index will have to be built at least once with this pipeline (see `--save_reference` to save index). It can then be provided via `--bbsplit_index` for future runs."
},
"remove_ribo_rna": {
"type": "boolean",
"fa_icon": "fas fa-trash-alt",
"description": "Enable the removal of reads derived from ribosomal RNA using SortMeRNA.",
"help_text": "Any patterns found in the sequences defined by the '--ribo_database_manifest' parameter will be used."
},
"ribo_database_manifest": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"default": "${projectDir}/assets/rrna-db-defaults.txt",
"fa_icon": "fas fa-database",
"description": "Text file containing paths to fasta files (one per line) that will be used to create the database for SortMeRNA.",
"help_text": "By default, [rRNA databases](https://github.com/biocore/sortmerna/tree/master/data/rRNA_databases) defined in the SortMeRNA GitHub repo are used. You can see an example in the pipeline Github repository in `assets/rrna-default-dbs.txt`.\nPlease note that commercial/non-academic entities require [`licensing for SILVA`](https://www.arb-silva.de/silva-license-information) for these default databases."
}
},
"fa_icon": "fas fa-trash-alt"
},
"umi_options": {
"title": "UMI options",
"type": "object",
"description": "Options for processing reads with unique molecular identifiers",
"default": "",
"properties": {
"with_umi": {
"type": "boolean",
"fa_icon": "fas fa-barcode",
"description": "Enable UMI-based read deduplication."
},
"umitools_extract_method": {
"type": "string",
"default": "string",
"fa_icon": "fas fa-barcode",
"description": "UMI pattern to use. Can be either 'string' (default) or 'regex'.",
"help_text": "More details can be found in the [UMI-tools documentation](https://umi-tools.readthedocs.io/en/latest/reference/extract.html#extract-method).\n"
},
"umitools_bc_pattern": {
"type": "string",
"fa_icon": "fas fa-barcode",
"help_text": "More details can be found in the [UMI-tools documentation](https://umi-tools.readthedocs.io/en/latest/reference/extract.html#extract-method).",
"description": "The UMI barcode pattern to use e.g. 'NNNNNN' indicates that the first 6 nucleotides of the read are from the UMI."
},
"umitools_bc_pattern2": {
"type": "string",
"fa_icon": "fas fa-barcode",
"description": "The UMI barcode pattern to use if the UMI is located in read 2."
},
"umi_discard_read": {
"type": "integer",
"fa_icon": "fas fa-barcode",
"description": "After UMI barcode extraction discard either R1 or R2 by setting this parameter to 1 or 2, respectively."
},
"umitools_umi_separator": {
"type": "string",
"fa_icon": "fas fa-star-half-alt",
"description": "The character that separates the UMI in the read name. Most likely a colon if you skipped the extraction with UMI-tools and used other software."
},
"umitools_grouping_method": {
"type": "string",
"default": "directional",
"fa_icon": "far fa-object-ungroup",
"description": "Method to use to determine read groups by subsuming those with similar UMIs. All methods start by identifying the reads with the same mapping position, but treat similar yet nonidentical UMIs differently.",
"enum": ["unique", "percentile", "cluster", "adjacency", "directional"]
},
"umitools_dedup_stats": {
"type": "boolean",
"fa_icon": "fas fa-barcode",
"help_text": "It can be quite time consuming generating these output stats - see [#827](https://github.com/nf-core/rnaseq/issues/827).",
"description": "Generate output stats when running \"umi_tools dedup\"."
}
},
"fa_icon": "fas fa-barcode"
},
"alignment_options": {
"title": "Alignment options",
"type": "object",
"fa_icon": "fas fa-map-signs",
"description": "Options to adjust parameters and filtering criteria for read alignments.",
"properties": {
"aligner": {
"type": "string",
"default": "star_salmon",
"description": "Specifies the alignment algorithm to use - available options are 'star_salmon', 'star_rsem' and 'hisat2'.",
"fa_icon": "fas fa-map-signs",
"enum": ["star_salmon", "star_rsem", "hisat2"]
},
"pseudo_aligner": {
"type": "string",
"description": "Specifies the pseudo aligner to use - available options are 'salmon'. Runs in addition to '--aligner'.",
"fa_icon": "fas fa-hamburger",
"enum": ["salmon", "kallisto"]
},
"bam_csi_index": {
"type": "boolean",
"description": "Create a CSI index for BAM files instead of the traditional BAI index. This will be required for genomes with larger chromosome sizes.",
"fa_icon": "fas fa-sort-alpha-down"
},
"star_ignore_sjdbgtf": {
"type": "boolean",
"fa_icon": "fas fa-ban",
"description": "When using pre-built STAR indices do not re-extract and use splice junctions from the GTF file."
},
"salmon_quant_libtype": {
"type": "string",
"fa_icon": "fas fa-fast-forward",
"description": " Override Salmon library type inferred based on strandedness defined in meta object.",
"help_text": "See [Salmon docs](https://salmon.readthedocs.io/en/latest/library_type.html).",
"enum": [
"A",
"IS",
"ISF",
"ISR",
"IU",
"MS",
"MSF",
"MSR",
"MU",
"OS",
"OSF",
"OSR",
"OU",
"SF",
"SR",
"U"
]
},
"min_mapped_reads": {
"type": "number",
"default": 5.0,
"fa_icon": "fas fa-percentage",
"description": "Minimum percentage of uniquely mapped reads below which samples are removed from further processing.",
"help_text": "Some downstream steps in the pipeline will fail if this threshold is too low."
},
"seq_center": {
"type": "string",
"description": "Sequencing center information to be added to read group of BAM files.",
"fa_icon": "fas fa-synagogue"
},
"stringtie_ignore_gtf": {
"type": "boolean",
"description": "Perform reference-guided de novo assembly of transcripts using StringTie i.e. dont restrict to those in GTF file.",
"fa_icon": "fas fa-ban"
},
"extra_star_align_args": {
"type": "string",
"description": "Extra arguments to pass to STAR alignment command in addition to defaults defined by the pipeline. Only available for the STAR-Salmon route.",
"fa_icon": "fas fa-plus"
},
"extra_salmon_quant_args": {
"type": "string",
"description": "Extra arguments to pass to Salmon quant command in addition to defaults defined by the pipeline.",
"fa_icon": "fas fa-plus"
},
"extra_kallisto_quant_args": {
"type": "string",
"description": "Extra arguments to pass to Kallisto quant command in addition to defaults defined by the pipeline.",
"fa_icon": "fas fa-plus"
},
"kallisto_quant_fraglen": {
"type": "integer",
"description": "In single-end mode Kallisto requires an estimated fragment length. Specify a default value for that here. TODO: use existing RSeQC results to do this dynamically.",
"default": 200,
"fa_icon": "fas fa-ruler-horizontal"
},
"kallisto_quant_fraglen_sd": {
"type": "integer",
"description": "In single-end mode, Kallisto requires an estimated standard error for fragment length. Specify a default value for that here. TODO: use existing RSeQC results to do this dynamically.",
"default": 200,
"fa_icon": "fas fa-sort-amount-up-alt"
}
}
},
"optional_outputs": {
"title": "Optional outputs",
"type": "object",
"description": "Additional output files produces as intermediates that can be saved",
"default": "",
"properties": {
"save_merged_fastq": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "Save FastQ files after merging re-sequenced libraries in the results directory."
},
"save_umi_intermeds": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "If this option is specified, intermediate FastQ and BAM files produced by UMI-tools are also saved in the results directory."
},
"save_non_ribo_reads": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "If this option is specified, intermediate FastQ files containing non-rRNA reads will be saved in the results directory."
},
"save_bbsplit_reads": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "If this option is specified, FastQ files split by reference will be saved in the results directory."
},
"save_reference": {
"type": "boolean",
"description": "If generated by the pipeline save the STAR index in the results directory.",
"help_text": "If an alignment index is generated by the pipeline use this parameter to save it to your results folder. These can then be used for future pipeline runs, reducing processing times.",
"fa_icon": "fas fa-save"
},
"save_trimmed": {
"type": "boolean",
"description": "Save the trimmed FastQ files in the results directory.",
"help_text": "By default, trimmed FastQ files will not be saved to the results directory. Specify this flag (or set to true in your config file) to copy these files to the results directory when complete.",
"fa_icon": "fas fa-save"
},
"save_align_intermeds": {
"type": "boolean",
"description": "Save the intermediate BAM files from the alignment step.",
"help_text": "By default, intermediate BAM files will not be saved. The final BAM files created after the appropriate filtering step are always saved to limit storage usage. Set this parameter to also save other intermediate BAM files.",
"fa_icon": "fas fa-save"
},
"save_unaligned": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "Where possible, save unaligned reads from either STAR, HISAT2 or Salmon to the results directory.",
"help_text": "This may either be in the form of FastQ or BAM files depending on the options available for that particular tool."
}
}
},
"quality_control": {
"title": "Quality Control",
"type": "object",
"description": "Additional quality control options.",
"default": "",
"properties": {
"deseq2_vst": {
"type": "boolean",
"description": "Use vst transformation instead of rlog with DESeq2.",
"help_text": "See [DESeq2 docs](http://bioconductor.org/packages/devel/bioc/vignettes/DESeq2/inst/doc/DESeq2.html#data-transformations-and-visualization).",
"fa_icon": "fas fa-dolly",
"default": true
},
"rseqc_modules": {
"type": "string",
"default": "bam_stat,inner_distance,infer_experiment,junction_annotation,junction_saturation,read_distribution,read_duplication",
"fa_icon": "fas fa-chart-pie",
"description": "Specify the RSeQC modules to run."
}
}
},
"process_skipping_options": {
"title": "Process skipping options",
"type": "object",
"fa_icon": "fas fa-fast-forward",
"description": "Options to skip various steps within the workflow.",
"properties": {
"skip_gtf_filter": {
"type": "boolean",
"fa_icon": "fas fa-forward",
"description": "Skip filtering of GTF for valid scaffolds and/ or transcript IDs.",
"help_text": "If you're confident on the validity of the GTF with respect to the genome fasta file, or wish to disregard failures thriggered by the filtering module, activate this option."
},
"skip_gtf_transcript_filter": {
"type": "boolean",
"fa_icon": "fas fa-forward",
"description": "Skip the 'transcript_id' checking component of the GTF filtering script used in the pipeline."
},
"skip_bbsplit": {
"type": "boolean",
"default": true,
"fa_icon": "fas fa-fast-forward",
"description": "Skip BBSplit for removal of non-reference genome reads."
},
"skip_umi_extract": {
"type": "boolean",
"fa_icon": "fas fa-compress-alt",
"description": "Skip the UMI extraction from the read in case the UMIs have been moved to the headers in advance of the pipeline run."
},
"skip_trimming": {
"type": "boolean",
"description": "Skip the adapter trimming step.",
"help_text": "Use this if your input FastQ files have already been trimmed outside of the workflow or if you're very confident that there is no adapter contamination in your data.",
"fa_icon": "fas fa-fast-forward"
},
"skip_alignment": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip all of the alignment-based processes within the pipeline."
},
"skip_pseudo_alignment": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip all of the pseudoalignment-based processes within the pipeline."
},
"skip_markduplicates": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip picard MarkDuplicates step."
},
"skip_bigwig": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip bigWig file creation."
},
"skip_stringtie": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip StringTie."
},
"skip_fastqc": {
"type": "boolean",
"description": "Skip FastQC.",
"fa_icon": "fas fa-fast-forward"
},
"skip_preseq": {
"type": "boolean",
"description": "Skip Preseq.",
"fa_icon": "fas fa-fast-forward",
"default": true
},
"skip_dupradar": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip dupRadar."
},
"skip_qualimap": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip Qualimap."
},
"skip_rseqc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip RSeQC."
},
"skip_biotype_qc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip additional featureCounts process for biotype QC."
},
"skip_deseq2_qc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip DESeq2 PCA and heatmap plotting."
},
"skip_multiqc": {
"type": "boolean",
"description": "Skip MultiQC.",
"fa_icon": "fas fa-fast-forward"
},
"skip_qc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip all QC steps except for MultiQC."
}
}
},
"institutional_config_options": {
"title": "Institutional config options",
"type": "object",
"fa_icon": "fas fa-university",
"description": "Parameters used to describe centralised config profiles. These should not be edited.",
"help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
"properties": {
"custom_config_version": {
"type": "string",
"description": "Git commit id for Institutional configs.",
"default": "master",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"custom_config_base": {
"type": "string",
"description": "Base directory for Institutional configs.",
"default": "https://raw.githubusercontent.com/nf-core/configs/master",
"hidden": true,
"help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
"fa_icon": "fas fa-users-cog"
},
"config_profile_name": {
"type": "string",
"description": "Institutional config name.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_description": {
"type": "string",
"description": "Institutional config description.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_contact": {
"type": "string",
"description": "Institutional config contact information.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_url": {
"type": "string",
"description": "Institutional config URL link.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"test_data_base": {
"type": "string",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3",
"description": "Base path / URL for data used in the test profiles",
"help_text": "Warning: The `-profile test` samplesheet file itself contains remote paths. Setting this parameter does not alter the contents of that file.",
"hidden": true
}
}
},
"max_job_request_options": {
"title": "Max job request options",
"type": "object",
"fa_icon": "fab fa-acquisitions-incorporated",
"description": "Set the top limit for requested resources for any single job.",
"help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
"properties": {
"max_cpus": {
"type": "integer",
"description": "Maximum number of CPUs that can be requested for any single job.",
"default": 16,
"fa_icon": "fas fa-microchip",
"hidden": true,
"help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
},
"max_memory": {
"type": "string",
"description": "Maximum amount of memory that can be requested for any single job.",
"default": "128.GB",
"fa_icon": "fas fa-memory",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"hidden": true,
"help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
},
"max_time": {
"type": "string",
"description": "Maximum amount of time that can be requested for any single job.",
"default": "240.h",
"fa_icon": "far fa-clock",
"pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
"hidden": true,
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}
},
"generic_options": {
"title": "Generic options",
"type": "object",
"fa_icon": "fas fa-file-import",
"description": "Less common options for the pipeline, typically set in a config file.",
"help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
"properties": {
"help": {
"type": "boolean",
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"version": {
"type": "boolean",
"description": "Display version and exit.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"description": "Method used to save pipeline results to output directory.",
"help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
"fa_icon": "fas fa-copy",
"enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
"hidden": true
},
"email_on_fail": {
"type": "string",
"description": "Email address for completion summary, only when pipeline fails.",
"fa_icon": "fas fa-exclamation-triangle",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"max_multiqc_email_size": {
"type": "string",
"description": "File size limit when attaching MultiQC reports to summary emails.",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"hidden": true
},
"multiqc_config": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"multiqc_logo": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
"fa_icon": "fas fa-image",
"hidden": true
},
"multiqc_methods_description": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"description": "Custom MultiQC yaml file containing HTML including a methods description.",
"fa_icon": "fas fa-cog"
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"validationShowHiddenParams": {
"type": "boolean",
"fa_icon": "far fa-eye-slash",
"description": "Show all params when using `--help`",
"hidden": true,
"help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
},
"validationFailUnrecognisedParams": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters fails when an unrecognised parameter is found.",
"hidden": true,
"help_text": "By default, when an unrecognised parameter is found, it returns a warinig."
},
"validationLenientMode": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters in lenient more.",
"hidden": true,
"help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)."
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/reference_genome_options"
},
{
"$ref": "#/definitions/read_trimming_options"
},
{
"$ref": "#/definitions/read_filtering_options"
},
{
"$ref": "#/definitions/umi_options"
},
{
"$ref": "#/definitions/alignment_options"
},
{
"$ref": "#/definitions/optional_outputs"
},
{
"$ref": "#/definitions/quality_control"
},
{
"$ref": "#/definitions/process_skipping_options"
},
{
"$ref": "#/definitions/institutional_config_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}