forked from nf-core/raredisease
-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow_schema.json
943 lines (943 loc) · 49.2 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
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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/raredisease/master/nextflow_schema.json",
"title": "nf-core/raredisease pipeline parameters",
"description": "call and score variants from WGS/WES of rare disease patients",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["outdir"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"schema": "assets/schema_input.json",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"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 3 columns, and a header row. See [usage docs](https://nf-co.re/raredisease/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})$",
"hidden": true
},
"multiqc_title": {
"type": "string",
"description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
"fa_icon": "fas fa-file-signature",
"hidden": true
}
}
},
"reference_file_options": {
"title": "Reference file options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Reference genome related files and options required for the workflow.",
"properties": {
"bait_padding": {
"type": "integer",
"default": 100,
"fa_icon": "fas fa-align-center",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"description": "The amount to pad each end of the target intervals to create bait intervals."
},
"bwa": {
"type": "string",
"exists": true,
"format": "directory-path",
"description": "Directory for pre-built bwa index.",
"help_text": "If none provided, will be generated automatically from the FASTA reference.",
"fa_icon": "fas fa-folder-open"
},
"bwamem2": {
"type": "string",
"exists": true,
"format": "directory-path",
"description": "Directory for pre-built bwamem2 index.",
"help_text": "If none provided, will be generated automatically from the FASTA reference.",
"fa_icon": "fas fa-folder-open"
},
"bwameme": {
"type": "string",
"exists": true,
"format": "directory-path",
"description": "Directory for pre-built bwameme's learned index.",
"help_text": "If none provided, will be generated automatically from the FASTA reference.",
"fa_icon": "fas fa-folder-open"
},
"cadd_resources": {
"type": "string",
"exists": true,
"format": "directory-path",
"fa_icon": "fas fa-file",
"description": "Path to the directory containing cadd annotations.",
"help_text": "This folder contains the uncompressed files that would otherwise be in data/annotation folder as described in https://github.com/kircherlab/CADD-scripts/#manual-installation."
},
"fai": {
"type": "string",
"exists": true,
"format": "file-path",
"help_text": "If none provided, will be generated automatically from the FASTA reference",
"description": "Path to FASTA genome index file.",
"pattern": "^\\S+\\.fn?a(sta)?\\.fai$",
"fa_icon": "fas fa-file"
},
"fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"description": "Path to FASTA genome file.",
"help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
"fa_icon": "fas fa-file"
},
"gcnvcaller_model": {
"type": "string",
"exists": true,
"fa_icon": "fas fa-file",
"description": "A file containing the path to models produced by GATK4 GermlineCNVCaller cohort.",
"format": "file-path",
"help_text": "This model is required for generating a cnv calls when using GermlineCNVCaller."
},
"genome": {
"type": "string",
"description": "Name of iGenomes reference.",
"fa_icon": "fas fa-align-center",
"help_text": "If using a reference genome configured in the pipeline using iGenomes, 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.",
"default": "GRCh38",
"enum": ["GRCh37", "GRCh38"]
},
"gens_gnomad_pos": {
"type": "string",
"exists": true,
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Path to a list of common SNP locations for Gens.",
"help_text": "Locations of gnomad SNPs with a high enough BAF.",
"hidden": true
},
"gens_interval_list": {
"type": "string",
"exists": true,
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Path to interval list for Gens.",
"help_text": "This file contains the binning intervals used for CollectReadCounts.",
"hidden": true
},
"gens_pon_female": {
"type": "string",
"exists": true,
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Path to female panel of normals for Gens.",
"help_text": "The female panel used to run DenoiseReadCounts.",
"hidden": true
},
"gens_pon_male": {
"type": "string",
"exists": true,
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Path to male panel of normals for Gens.",
"help_text": "The male panel used to run DenoiseReadCounts.",
"hidden": true
},
"gnomad_af": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.tab(\\.gz)?$",
"description": "Path to the gnomad tab file with allele frequencies.",
"help_text": "Path to the gnomad tab file with CHR/START/REF,ALT/AF. Can be generated from the gnomad annotations vcf."
},
"gnomad_af_idx": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.bed(\\.gz)?\\.idx$",
"description": "Path to the index file for the gnomad tab file with allele frequencies.",
"help_text": "Path to the index of gnomad tab file with CHR/START/REF,ALT/AF"
},
"igenomes_base": {
"type": "string",
"format": "directory-path",
"description": "The base path to the igenomes reference files",
"fa_icon": "fas fa-ban",
"hidden": true,
"default": "s3://ngi-igenomes/igenomes/"
},
"igenomes_ignore": {
"type": "boolean",
"description": "Do not load the iGenomes reference config.",
"fa_icon": "fas fa-ban",
"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`."
},
"intervals_wgs": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.intervals?(_list)?$",
"description": "Path to the interval list of the genome (autosomes, sex chromosomes, and mitochondria).",
"help_text": "Path to the interval list of the genome. This is used to calculate genome-wide coverage statistics."
},
"intervals_y": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.intervals?(_list)?$",
"description": "Path to the interval list of the Y chromosome.",
"help_text": "Path to the interval list of the Y chromosome. This is used to calculate coverage statistics for the Y chromosome."
},
"known_dbsnp": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.vcf(\\.gz)?$",
"description": "Path to known dbSNP file."
},
"known_dbsnp_tbi": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.vcf(\\.gz)?\\.tbi$",
"description": "Path to known dbSNP file index."
},
"local_genomes": {
"type": "string",
"format": "directory-path",
"fa_icon": "fas fa-map-marker-alt",
"description": "Local directory base for genome references that map to the config.",
"help_text": "This folder is a flat structure with file names that map to the config."
},
"mito_name": {
"type": "string",
"description": "Name of the mitochondrial contig in the reference fasta file",
"help_text": "Used to extract relevant information from the references to analyse mitochondria",
"fa_icon": "fas fa-align-center",
"default": "chrM"
},
"mobile_element_references": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "File with mobile element references",
"help_text": "Path to tsv file listing mobile element references. \nFormat: <mobile element type>\\t<path to bed file>",
"pattern": "^\\S+\\.tsv$",
"format": "file-path",
"schema": "assets/mobile_element_references_schema.json"
},
"mobile_element_svdb_annotations": {
"type": "string",
"description": "File with mobile element allele frequency references",
"help_text": "Path to csv file listing files containing mobile element allele frequencies in reference populations. \nFormat: <vcf file path>,<in_freq_info_key>,<in_allele_count_info_key>,<out_freq_info_key>,<out_allele_count_info_key>",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.csv$",
"mimetype": "text/csv",
"schema": "assets/svdb_query_vcf_schema.json"
},
"ml_model": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"description": "Path to sentieon machine learning model file."
},
"mt_fasta": {
"type": "string",
"exists": true,
"format": "file-path",
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"description": "Path to mitochondrial FASTA genome file.",
"fa_icon": "fas fa-file"
},
"par_bed": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"description": "Path to a BED file containing PAR regions (used by deepvariant)."
},
"ploidy_model": {
"type": "string",
"exists": true,
"fa_icon": "fas fa-folder-open",
"description": "Directory containing the ploidy model files",
"format": "directory-path",
"help_text": "Produced in GATK4 DetermineGermlineContigPloidy cohort, this model is required for generating a cnv model when using GermlineCNVCaller."
},
"readcount_intervals": {
"type": "string",
"exists": true,
"fa_icon": "fas fa-file",
"description": "Interval list file containing the intervals over which read counts are tabulated for CNV calling",
"format": "file-path",
"help_text": "Generated by GATK4 preprocessintervals. It needs to be the same as the intervals used to generate the ploidy and cnv models."
},
"reduced_penetrance": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file-csv",
"description": "File with gene ids that have reduced penetrance. For use with genmod"
},
"rtg_truthvcfs": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Vcf used for evaluating variant calls.",
"fa_icon": "fas fa-file-csv",
"help_text": "Path to comma-separated file containing information about the truth vcf files used by vcfeval.",
"pattern": "^\\S+\\.csv$",
"mimetype": "text/csv",
"schema": "assets/rtg_truthvcfs_schema.json"
},
"save_reference": {
"type": "boolean",
"description": "If generated by the pipeline save the required indices/references in the results directory.",
"help_text": "The saved references can be used for future pipeline runs, reducing processing times.",
"fa_icon": "fas fa-save"
},
"score_config_mt": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"description": "MT rank model config file for genmod."
},
"score_config_snv": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"description": "SNV rank model config file for genmod."
},
"score_config_sv": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"description": "SV rank model config file for genmod."
},
"sdf": {
"type": "string",
"exists": true,
"format": "directory-path",
"description": "Directory for pre-built sdf index. Used by rtg/vcfeval",
"help_text": "If none provided, will be generated automatically from the FASTA reference.",
"fa_icon": "fas fa-folder-open"
},
"sequence_dictionary": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.dict$",
"description": "Path to the genome dictionary file"
},
"svdb_query_bedpedbs": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Databases used for structural variant annotation in chrA-posA-chrB-posB-type-count-frequency format.",
"fa_icon": "fas fa-file-csv",
"help_text": "Path to comma-separated file containing information about the databases used for structural variant annotation.",
"pattern": "^\\S+\\.csv$",
"mimetype": "text/csv",
"schema": "assets/svdb_query_bedpe_schema.json"
},
"svdb_query_dbs": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Databases used for structural variant annotation in vcf format.",
"fa_icon": "fas fa-file-csv",
"help_text": "Path to comma-separated file containing information about the databases used for structural variant annotation.",
"pattern": "^\\S+\\.csv$",
"mimetype": "text/csv",
"schema": "assets/svdb_query_vcf_schema.json"
},
"target_bed": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"description": "Path to directory for target bed file.",
"help_text": "If you would like to limit your analysis to specific regions of the genome, you can pass those regions in a bed file using this option"
},
"variant_catalog": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Path to variant catalog file",
"help_text": "Should be Stranger's extended JSON as described at https://github.com/Clinical-Genomics/stranger/blob/master/stranger/resources/variant_catalog_grch37.json. This file is used by both ExpansionHunter and Stranger",
"fa_icon": "fas fa-file"
},
"sample_id_map": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Path to a file containing internal ids and customer ids in csv format.",
"fa_icon": "fas fa-file-csv",
"mimetype": "text/csv",
"schema": "assets/sample_id_map.json",
"help_text": "Optional file to rename sample ids in the vcf2cytosure vcf",
"pattern": "^\\S+\\.csv$"
},
"vcf2cytosure_blacklist": {
"type": "string",
"help_text": "Optional file to blacklist regions for VCF2cytosure",
"pattern": "^\\S+\\.bed$",
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Path to vcf2cytosure blacklist file"
},
"vcfanno_extra_resources": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Path to a VCF file containing annotations.",
"help_text": "Can be used to supply case-specific annotations in addition to those provided using --vcfanno_resources",
"fa_icon": "fas fa-file"
},
"vcfanno_resources": {
"type": "string",
"exists": true,
"description": "Path to a file containing the absolute paths to resources defined within the vcfanno toml file. One line per resource.",
"help_text": "If no file is passed, default configurations will be used according to genome build within the context of the pipeline.",
"fa_icon": "fas fa-file"
},
"vcfanno_toml": {
"type": "string",
"exists": true,
"description": "Path to the vcfanno toml file.",
"pattern": "^\\S+\\.toml$",
"help_text": "If no toml is passed, default configurations will be used according to genome build within the context of the pipeline.",
"fa_icon": "fas fa-file"
},
"vcfanno_lua": {
"type": "string",
"exists": true,
"description": "Path to the vcfanno lua file.",
"pattern": "^\\S+\\.lua$",
"help_text": "Custom operations file (lua). For use when the built-in ops don't supply the needed reduction.",
"fa_icon": "fas fa-file"
},
"vep_cache": {
"type": "string",
"exists": true,
"description": "Path to vep's cache directory.",
"help_text": "If no directory path is passed, vcf files will not be annotated by vep.",
"fa_icon": "fas fa-folder-open"
},
"vep_plugin_files": {
"type": "string",
"exists": true,
"format": "file-path",
"description": "Databases used by both named and custom plugins to annotate variants.",
"fa_icon": "fas fa-file-csv",
"help_text": "Path to a file containing the absolute paths to databases and their indices used by VEP's custom and named plugins resources defined within the vcfanno toml file. One line per resource.",
"pattern": "^\\S+\\.csv$",
"mimetype": "text/csv",
"schema": "assets/vep_plugin_files_schema.json"
},
"vep_filters": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-file-csv",
"description": "Path to the file containing HGNC_IDs of interest on separate lines."
},
"vep_filters_scout_fmt": {
"type": "string",
"exists": true,
"format": "path",
"fa_icon": "fas fa-table",
"description": "Path to a bed-like file exported by scout, which contains HGNC_IDs to be used in filter_vep."
}
},
"required": ["fasta", "intervals_wgs", "intervals_y"]
},
"analysis_options": {
"title": "Analysis options",
"type": "object",
"fa_icon": "fas fa-user-cog",
"description": "Options used to steer the direction of the pipeline.",
"properties": {
"analysis_type": {
"type": "string",
"default": "wgs",
"description": "Specifies which analysis type for the pipeline- either 'wgs', 'wes' or 'mito'. This changes resources consumed and tools used.",
"fa_icon": "fas fa-align-center",
"enum": ["wgs", "wes", "mito"]
},
"bwa_as_fallback": {
"type": "boolean",
"description": "Specifies whether or not to use bwa as a fallback aligner in case bwamem2 throws an error.",
"help_text": "errorStrategy needs to be set to ignore for the bwamem2 process for the fallback to work. Turned off by default.",
"fa_icon": "fas fa-toggle-on"
},
"extract_alignments": {
"type": "boolean",
"default": "false",
"description": "After aligning the reads to a reference, extract alignments from specific regions/contigs and restrict the analysis to those regions/contigs.",
"help_text": "Set this to true, and specify the contig(s) using `restrict_to_contigs` parameter",
"fa_icon": "fas fa-toggle-on"
},
"platform": {
"type": "string",
"default": "illumina",
"description": "Specifies the platform on which the reads were sequenced.",
"fa_icon": "fas fa-align-center"
},
"ngsbits_samplegender_method": {
"type": "string",
"default": "xy",
"description": "Method selection for ngs-bits samplegender",
"fa_icon": "fas fa-align-center",
"enum": ["xy", "hetx", "sry"]
},
"restrict_to_contigs": {
"type": "string",
"description": "Can be specified as RNAME[:STARTPOS[-ENDPOS]]. Multiple regions should be seperated by space",
"fa_icon": "fas fa-align-center"
},
"run_mt_for_wes": {
"type": "boolean",
"description": "Specifies whether to run mitochondrial analysis for wes samples",
"fa_icon": "fas fa-toggle-on"
},
"run_rtgvcfeval": {
"type": "boolean",
"description": "Specifies whether to run rtgtools' vcfeval",
"fa_icon": "fas fa-toggle-on"
},
"save_mapped_as_cram": {
"type": "boolean",
"description": "Specifies whether to generate and publish alignment files as cram instead of bam",
"fa_icon": "fas fa-toggle-on"
},
"scatter_count": {
"type": "integer",
"default": 20,
"description": "Number of intervals to split your genome into (used to parallelize annotations)",
"fa_icon": "fas fa-less-than"
},
"skip_fastp": {
"type": "boolean",
"description": "Specifies whether or not to skip trimming with fastp.",
"fa_icon": "fas fa-toggle-on"
},
"skip_gens": {
"type": "boolean",
"description": "Specifies whether or not to skip gens preprocessing subworkflow.",
"fa_icon": "fas fa-toggle-on"
},
"skip_germlinecnvcaller": {
"type": "boolean",
"description": "Specifies whether or not to skip CNV calling using GATK's GermlineCNVCaller",
"fa_icon": "fas fa-toggle-on"
},
"skip_peddy": {
"type": "boolean",
"description": "Specifies whether or not to skip peddy.",
"fa_icon": "fas fa-toggle-on"
},
"skip_me_calling": {
"type": "boolean",
"description": "Specifies whether or not to skip calling mobile elements, and the subsequent annotation step.",
"fa_icon": "fas fa-toggle-on"
},
"skip_me_annotation": {
"type": "boolean",
"description": "Specifies whether or not to skip annotation of mobile elements.",
"fa_icon": "fas fa-toggle-on"
},
"skip_mt_annotation": {
"type": "boolean",
"description": "Specifies whether or not to skip annotation of mitochondrial variants.",
"fa_icon": "fas fa-toggle-on"
},
"skip_mt_subsample": {
"type": "boolean",
"description": "Specifies whether or not to subsample mt alignment.",
"fa_icon": "fas fa-toggle-on"
},
"skip_repeat_annotation": {
"type": "boolean",
"description": "Specifies whether or not to skip annotation of repeat expansions.",
"fa_icon": "fas fa-toggle-on"
},
"skip_repeat_calling": {
"type": "boolean",
"description": "Specifies whether or not to skip calling of repeat expansions.",
"fa_icon": "fas fa-toggle-on"
},
"skip_smncopynumbercaller": {
"type": "boolean",
"description": "Specifies whether or not to skip smncopynumbercaller.",
"fa_icon": "fas fa-toggle-on"
},
"skip_snv_annotation": {
"type": "boolean",
"description": "Specifies whether or not to skip annotate SNV subworkflow.",
"fa_icon": "fas fa-toggle-on"
},
"skip_snv_calling": {
"type": "boolean",
"description": "Specifies whether or not to skip nuclear and mitochondrial SNV calling and annotation.",
"fa_icon": "fas fa-toggle-on"
},
"skip_sv_annotation": {
"type": "boolean",
"description": "Specifies whether or not to skip annotate structural variant subworkflow.",
"fa_icon": "fas fa-toggle-on"
},
"skip_sv_calling": {
"type": "boolean",
"description": "Specifies whether or not to skip nuclear and mitochondrial SV calling and annotation.",
"fa_icon": "fas fa-toggle-on"
},
"skip_vcf2cytosure": {
"type": "boolean",
"default": true,
"description": "Specifies whether or not to skip the vcf2cytosure subworkflow",
"help_text": "vcf2cytosure can generate CGH files from a structural variant VCF file that can be analysed in the CytoSure interpretation software. Cut-offs for allele frequencies and bin sizes can be modified in the config file. Turned off by default.",
"fa_icon": "fas fa-toggle-on"
},
"skip_vep_filter": {
"type": "boolean",
"description": "Specifies whether or not to filter results based on a list of candidate genes specified in 'vep_filters'.",
"fa_icon": "fas fa-toggle-on"
}
}
},
"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": "bwamem2",
"description": "Specifies the alignment algorithm to use - available options are 'bwamem2', 'bwa', 'bwameme' and 'sentieon'.",
"fa_icon": "fas fa-align-center",
"enum": ["bwa", "bwamem2", "bwameme", "sentieon"]
},
"mt_aligner": {
"type": "string",
"default": "bwamem2",
"description": "Specifies the alignment algorithm to use - available options are 'bwamem2', 'bwa' and 'sentieon'.",
"fa_icon": "fas fa-align-center",
"enum": ["bwa", "bwamem2", "sentieon"]
},
"samtools_sort_threads": {
"type": "integer",
"default": 4,
"description": "Number of threads allocated for sorting alignment files (used only by bwameme)",
"help_text": "To know more about this parameter check [bwameme](https://github.com/kaist-ina/BWA-MEME?tab=readme-ov-file#building-pipeline-with-samtools) documentation.",
"fa_icon": "fas fa-less-than"
},
"mbuffer_mem": {
"type": "integer",
"default": 3072,
"description": "Memory allocated for mbuffer in megabytes (used only by bwameme)",
"help_text": "To know more about this parameter check [bwameme](https://github.com/kaist-ina/BWA-MEME?tab=readme-ov-file#building-pipeline-with-samtools) documentation.",
"fa_icon": "fas fa-less-than"
},
"min_trimmed_length": {
"type": "integer",
"default": 40,
"description": "Discard trimmed reads shorter than the given value",
"help_text": "Minimum length of reads after adapter trimming. Shorter reads are discarded.",
"fa_icon": "fas fa-less-than"
},
"mt_subsample_rd": {
"type": "integer",
"default": 150,
"description": "Expected coverage to subsample mt alignment to.",
"help_text": "To know more about this parameter check [samtools' view](https://www.htslib.org/doc/samtools-view.html) documentation.",
"fa_icon": "fas fa-less-than"
},
"mt_subsample_seed": {
"type": "integer",
"default": 30,
"description": "Subsampling seed used to influence which subset of mitochondrial reads is kept. ",
"help_text": "To know more about this parameter check [samtools' view](https://www.htslib.org/doc/samtools-view.html) documentation.",
"fa_icon": "fas fa-less-than"
},
"rmdup": {
"type": "boolean",
"description": "Specifies whether duplicates reads should be removed prior to variant calling.",
"fa_icon": "fas fa-toggle-on"
}
}
},
"variant_calling_options": {
"title": "Variant calling options",
"type": "object",
"fa_icon": "fas fa-map-signs",
"description": "Options to adjust parameters and filtering criteria for variant calling.",
"properties": {
"call_interval": {
"type": "string",
"format": "path",
"fa_icon": "fas fa-align-center",
"description": "Interval in the reference that will be used in the software. Used only by sentieon."
},
"cnvnator_binsize": {
"type": "integer",
"description": "Bin size for CNVnator",
"default": 1000,
"fa_icon": "fas fa-align-center"
},
"sentieon_dnascope_pcr_indel_model": {
"type": "string",
"default": "CONSERVATIVE",
"fa_icon": "fas fa-bacon",
"description": "Option for selecting the PCR indel model used by Sentieon Dnascope.",
"help_text": "PCR indel model used to weed out false positive indels more or less aggressively. The possible MODELs are: NONE (used for PCR free samples), and HOSTILE, AGGRESSIVE and CONSERVATIVE, in order of decreasing aggressiveness. The default value is CONSERVATIVE.",
"enum": ["NONE", "HOSTILE", "AGGRESSIVE", "CONSERVATIVE"]
},
"variant_caller": {
"type": "string",
"default": "deepvariant",
"description": "Specifies the variant caller to use - available options are 'deepvariant' and 'sentieon'.",
"fa_icon": "fas fa-random",
"enum": ["deepvariant", "sentieon"]
},
"variant_type": {
"type": "string",
"default": "snp,indel",
"description": "Specifies the variant types for sentieon variant caller.",
"fa_icon": "fas fa-align-center",
"enum": ["snp", "indel", "snp,indel"]
}
}
},
"annotation_options": {
"title": "Annotation options",
"type": "object",
"fa_icon": "fas fa-user-cog",
"description": "Options used to facilitate the annotation of the variants.",
"properties": {
"variant_consequences_snv": {
"type": "string",
"description": "File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs.",
"help_text": "For more information check https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html",
"fa_icon": "fas fa-file-csv"
},
"variant_consequences_sv": {
"type": "string",
"description": "File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SVs.",
"help_text": "For more information check https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html",
"fa_icon": "fas fa-file-csv"
},
"vep_cache_version": {
"type": "integer",
"default": 112,
"description": "Specify the version of the VEP cache provided to the `--vep_cache` option.",
"fa_icon": "fas fa-align-center"
}
}
},
"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"
}
}
},
"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": {
"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})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"max_multiqc_email_size": {
"type": "string",
"description": "File size limit when attaching MultiQC reports to summary emails.",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"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,
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"multiqc_logo": {
"type": "string",
"format": "file-path",
"exists": true,
"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,
"description": "Custom MultiQC yaml file containing HTML including a methods description.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"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
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/reference_file_options"
},
{
"$ref": "#/$defs/analysis_options"
},
{
"$ref": "#/$defs/alignment_options"
},
{
"$ref": "#/$defs/variant_calling_options"
},
{
"$ref": "#/$defs/annotation_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}