-
Notifications
You must be signed in to change notification settings - Fork 3
/
nextflow_schema.json
1504 lines (1504 loc) · 84.6 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
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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/tanubrata/nfjabba/master/nextflow_schema.json",
"title": "tanubrata/nfjabba pipeline parameters",
"description": "An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing",
"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.",
"help_text": "Specify input samplesheet, step and output folder.",
"required": [
"step",
"outdir"
],
"properties": {
"input": {
"description": "Path to comma-separated file containing information about the samples in the experiment.",
"help_text": "A design file with information about the samples in your experiment. Use this parameter to specify the location of the input files. It has to be a comma-separated file with a header row. See [usage docs](https://nf-co.re/sarek/usage#input).\n\nIf no input file is specified, sarek will attempt to locate one in the `{outdir}` directory. If no input should be supplied, i.e. when --step is supplied or --build_from_index, then set --input false",
"fa_icon": "fas fa-file-csv",
"schema": "assets/schema_input.json",
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$"
},
"input_restart": {
"type": "string",
"description": "Automatic retrieval for restart",
"format": "file-path",
"exists": true,
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"hidden": true,
"schema": "assets/schema_input.json"
},
"step": {
"type": "string",
"default": "alignment",
"fa_icon": "fas fa-play",
"description": "Starting step",
"help_text": "The pipeline starts from this step and then runs through the possible subsequent steps.",
"enum": [
"alignment",
"markduplicates",
"prepare_recalibration",
"recalibrate",
"sv_calling",
"ascat",
"fragcounter",
"dryclean",
"hetpileups",
"jabba",
"variant_calling",
"annotate"
]
},
"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"
}
}
},
"main_options": {
"title": "Main options",
"type": "object",
"description": "Most common options used for the pipeline",
"default": "",
"properties": {
"split_fastq": {
"type": "integer",
"default": 50000000,
"fa_icon": "fas fa-clock",
"description": "Specify how many reads each split of a FastQ file contains. Set 0 to turn off splitting at all.",
"help_text": "Use the the tool FastP to split FASTQ file by number of reads. This parallelizes across fastq file shards speeding up mapping. "
},
"wes": {
"type": "boolean",
"fa_icon": "fas fa-dna",
"description": "Enable when exome or panel data is provided.",
"help_text": "With this parameter flags in various tools are set for targeted sequencing data. It is recommended to enable for whole-exome and panel data analysis."
},
"intervals": {
"type": "string",
"fa_icon": "fas fa-file-alt",
"help_text": "To speed up preprocessing and variant calling processes, the execution is parallelized across a reference chopped into smaller pieces.\n\nParts of preprocessing and variant calling are done by these intervals, the different resulting files are then merged.\nThis can parallelize processes, and push down wall clock time significantly.\n\nWe are aligning to the whole genome, and then run Base Quality Score Recalibration and Variant Calling on the supplied regions.\n\n**Whole Genome Sequencing:**\n\nThe (provided) intervals are chromosomes cut at their centromeres (so each chromosome arm processed separately) also additional unassigned contigs.\n\nWe are ignoring the `hs37d5` contig that contains concatenated decoy sequences.\n\nThe calling intervals can be defined using a .list or a BED file.\nA .list file contains one interval per line in the format `chromosome:start-end` (1-based coordinates).\nA BED file must be a tab-separated text file with one interval per line.\nThere must be at least three columns: chromosome, start, and end (0-based coordinates).\nAdditionally, the score column of the BED file can be used to provide an estimate of how many seconds it will take to call variants on that interval.\nThe fourth column remains unused.\n\n```\n|chr1|10000|207666|NA|47.3|\n```\nThis indicates that variant calling on the interval chr1:10001-207666 takes approximately 47.3 seconds.\n\nThe runtime estimate is used in two different ways.\nFirst, when there are multiple consecutive intervals in the file that take little time to compute, they are processed as a single job, thus reducing the number of processes that needs to be spawned.\nSecond, the jobs with largest processing time are started first, which reduces wall-clock time.\nIf no runtime is given, a time of 200000 nucleotides per second is assumed. See `--nucleotides_per_second` on how to customize this.\nActual figures vary from 2 nucleotides/second to 30000 nucleotides/second.\nIf you prefer, you can specify the full path to your reference genome when you run the pipeline:\n\n> **NB** If none provided, will be generated automatically from the FASTA reference\n> **NB** Use --no_intervals to disable automatic generation.\n\n**Targeted Sequencing:**\n\nThe recommended flow for targeted sequencing data is to use the workflow as it is, but also provide a `BED` file containing targets for all steps using the `--intervals` option. In addition, the parameter `--wes` should be set.\nIt is advised to pad the variant calling regions (exons or target) to some extent before submitting to the workflow.\n\nThe procedure is similar to whole genome sequencing, except that only BED file are accepted. See above for formatting description.\nAdding every exon as an interval in case of `WES` can generate >200K processes or jobs, much more forks, and similar number of directories in the Nextflow work directory. These are appropriately grouped together to reduce number of processes run in parallel (see above and `--nucleotides_per_second` for details). \nFurthermore, primers and/or baits are not 100% specific, (certainly not for MHC and KIR, etc.), quite likely there going to be reads mapping to multiple locations.\nIf you are certain that the target is unique for your genome (all the reads will certainly map to only one location), and aligning to the whole genome is an overkill, it is actually better to change the reference itself.",
"description": "Path to target bed file in case of whole exome or targeted sequencing or intervals file."
},
"nucleotides_per_second": {
"type": "number",
"fa_icon": "fas fa-clock",
"description": "Estimate interval size.",
"help_text": "Intervals are parts of the chopped up genome used to speed up preprocessing and variant calling. See `--intervals` for more info. \n\nChanging this parameter, changes the number of intervals that are grouped and processed together. Bed files from target sequencing can contain thousands or small intervals. Spinning up a new process for each can be quite resource intensive. Instead it can be desired to process small intervals together on larger nodes. \nIn order to make use of this parameter, no runtime estimate can be present in the bed file (column 5). ",
"default": 200000
},
"no_intervals": {
"type": "boolean",
"fa_icon": "fas fa-ban",
"description": "Disable usage of intervals.",
"help_text": "Intervals are parts of the chopped up genome used to speed up preprocessing and variant calling. See `--intervals` for more info. \n\nIf `--no_intervals` is set no intervals will be taken into account for speed up or data processing."
},
"tools": {
"type": "string",
"fa_icon": "fas fa-toolbox",
"description": "Tools to use for duplicate marking, variant calling and/or for annotation.",
"help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nGermline variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: DeepVariant, FreeBayes, GATK HaplotypeCaller, mpileup, Sentieon Haplotyper, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit\n\nTumor-only somatic variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, mpileup, Mutect2, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit, ControlFREEC\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka2\n- Structural variants: Manta, TIDDIT\n- Copy-Number: ASCAT, CNVKit, Control-FREEC\n- Microsatellite Instability: MSIsensorpro\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.",
"pattern": "^((ascat|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|manta|merge|mpileup|msisensorpro|mutect2|snpeff|strelka|tiddit|vep|svaba|gridss|fragcounter|dryclean|hetpileups|cbs|jabba)?,?)*(?<!,)$"
},
"skip_tools": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Disable specified tools.",
"help_text": "Multiple tools can be specified, separated by commas.\n\n> **NB** `--skip_tools baserecalibrator_report` is actually just not saving the reports.\n> **NB** `--skip_tools markduplicates_report` does not skip `MarkDuplicates` but prevent the collection of duplicate metrics that slows down performance.",
"pattern": "^((baserecalibrator|baserecalibrator_report|bcftools|documentation|fastqc|haplotypecaller_filter|haplotyper_filter|markduplicates|markduplicates_report|mosdepth|multiqc|samtools|vcftools|versions)?,?)*(?<!,)$"
}
},
"fa_icon": "fas fa-user-cog"
},
"fastq_preprocessing": {
"title": "FASTQ Preprocessing",
"type": "object",
"description": "Trim fastq file or handle UMIs",
"default": "",
"fa_icon": "fas fa-cut",
"properties": {
"trim_fastq": {
"type": "boolean",
"fa_icon": "fas fa-cut",
"description": "Run FastP for read trimming",
"help_text": "Use this to perform adapter trimming. Adapter are detected automatically by using the FastP flag `--detect_adapter_for_pe`. For more info see [FastP](https://github.com/OpenGene/fastp)."
},
"clip_r1": {
"type": "integer",
"default": 0,
"fa_icon": "fas fa-cut",
"description": "Remove bp from the 5' end of read 1",
"help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. Corresponds to the FastP flag `--trim_front1`.",
"hidden": true
},
"clip_r2": {
"type": "integer",
"default": 0,
"description": "Remove bp from the 5' end of read 2",
"help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. Corresponds to the FastP flag `--trim_front2`.",
"fa_icon": "fas fa-cut",
"hidden": true
},
"three_prime_clip_r1": {
"type": "integer",
"default": 0,
"fa_icon": "fas fa-cut",
"description": "Remove bp from the 3' end of read 1",
"help_text": "This may remove some unwanted bias from the 3'. Corresponds to the FastP flag `--three_prime_clip_r1`.",
"hidden": true
},
"three_prime_clip_r2": {
"type": "integer",
"default": 0,
"fa_icon": "fas fa-cut",
"description": "Remove bp from the 3' end of read 2",
"help_text": "This may remove some unwanted bias from the 3' end. Corresponds to the FastP flag `--three_prime_clip_r2`.",
"hidden": true
},
"trim_nextseq": {
"type": "integer",
"default": 0,
"fa_icon": "fas fa-cut",
"description": "Removing poly-G tails.",
"help_text": "DetectS polyG in read tails and trim them. Corresponds to the FastP flag `--trim_poly_g`.",
"hidden": true
},
"save_trimmed": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "Save trimmed FastQ file intermediates.",
"hidden": true
},
"save_split_fastqs": {
"type": "boolean",
"fa_icon": "fas fa-vial",
"description": "If set, publishes split FASTQ files. Intended for testing purposes.",
"hidden": true
}
}
},
"preprocessing": {
"title": "Preprocessing",
"type": "object",
"description": "Configure preprocessing tools",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"aligner": {
"type": "string",
"default": "bwa-mem",
"fa_icon": "fas fa-puzzle-piece",
"enum": [
"bwa-mem",
"bwa-mem2"
],
"description": "Specify aligner to be used to map reads to reference genome.",
"help_text": "Sarek will build missing indices automatically if not provided. Set `--bwa false` if indices should be (re-)built.\nIf DragMap is selected as aligner, it is recommended to skip baserecalibration with `--skip_tools baserecalibrator`. For more info see [here](https://gatk.broadinstitute.org/hc/en-us/articles/4407897446939--How-to-Run-germline-single-sample-short-variant-discovery-in-DRAGEN-mode)."
},
"save_mapped": {
"type": "boolean",
"fa_icon": "fas fa-download",
"description": "Save mapped files.",
"help_text": "If the parameter `--split-fastq` is used, the sharded bam files are merged and converted to CRAM before saving them."
},
"save_output_as_bam": {
"type": "boolean",
"description": "Saves output from mapping (if `--save_mapped`), Markduplicates & Baserecalibration as BAM file instead of CRAM",
"fa_icon": "fas fa-download"
}
}
},
"sv_calling": {
"title": "Structural Variant Calling",
"type": "object",
"description": "Configure SV calling tools",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"error_rate": {
"type": "number",
"default": 0.01,
"fa_icon": "fas fa-wrench",
"description": "Overwrite Svaba error rate",
"hidden": true,
"help_text": "Set an error rate between 0 and 1 for Svaba, by default it is 0.01"
},
"indel_mask": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Provide Indel Mask for SVABA based on hg19/hg38. Should be .bed file",
"hidden": true,
"help_text": "Provide the indel mask path that you want to use for SVABA"
},
"germ_sv_db": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Provide Germline SV file for reference for SVABA based on hg19/hg38. Should be .bed file",
"hidden": true,
"help_text": "Provide the Germline SV file path that you want to use for SVABA"
},
"simple_seq_db": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Provide file containing sites of simple DNA for SVABA based on hg19/hg38. Should be .bed file",
"hidden": true,
"help_text": "Provide the simple DNA file path that you want to use for SVABA"
},
"blacklist_gridss": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Provide file Blacklist for GRIDSS based on hg19/hg38. Should be .bed file",
"hidden": true,
"help_text": "Provide the Blacklist file path that you want to use for GRIDSS"
},
"pon_gridss": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Provide the PON directory for GRIDSS Somatic filter",
"hidden": true,
"help_text": "Provide the PON directory for GRIDSS. Must contain both .bed and .bedpe file."
}
}
},
"hetpileups": {
"title": "HetPileUps",
"type": "object",
"description": "",
"default": "",
"properties": {
"filter_hets": {
"type": "string",
"default": "TRUE",
"description": "Whether to perform filtering on low quality hets",
"help_text": "By default, it is TRUE so that it filters low quality calls",
"fa_icon": "fas fa-filter"
},
"max_depth": {
"type": "integer",
"default": 1000,
"description": "Bin size to do hetpileups",
"help_text": "By default it is set to 1000 to correspond with CBS/dryclean bin size",
"fa_icon": "fas fa-cut"
},
"hapmap_sites": {
"type": "string",
"default": "None",
"description": "Hapmap reference file based on genome",
"help_text": "Provide the population hapmap reference file based on genome version",
"fa_icon": "fas fa-file"
}
},
"fa_icon": "fas fa-suitcase"
},
"fragcounter": {
"title": "FragCounter",
"type": "object",
"description": "Configure coverage tools fragCounter",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"midpoint_frag": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option for counting method in fragCounter",
"help_text": "If TRUE only count midpoint if FALSE then count bin footprint of every fragment interval"
},
"paired_frag": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option to mention whether the dataset is paired or single ended for fragCounter",
"help_text": "If TRUE, will consider the dataset is paired ended, else single ended"
},
"exome_frag": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Bin counting method for fragCounter on whether it is exome or genome",
"help_text": "If TRUE, will consider the input the data as exome, else if FALSE will consider it genome",
"hidden": true
},
"windowsize_frag": {
"type": "number",
"default": 200,
"fa_icon": "fas fa-wrench",
"description": "Default bin size for fragCounter",
"help_text": "By default the bin size is 200, adjust as necessary."
},
"minmapq_frag": {
"type": "number",
"default": 1,
"fa_icon": "fas fa-wrench",
"description": "Minimal Mapping Quality for fragCounter",
"help_text": "By default the minimum mapping quality is 200, adjust as necessary."
},
"gcmapdir_frag": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "GC and Mappabilty directory for fragCounter",
"help_text": "Provide the directory containing .rds file for gc and mappability bias based on genome version"
}
}
},
"dryclean": {
"title": "Dryclean",
"type": "object",
"description": "Configure genome wide cleaning using Dryclean",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"pon_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Dryclean PON",
"help_text": "Provide the PON .rds file based on genome version"
},
"center_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option to specify whether the samples are centered",
"help_text": "are the samples centered",
"default": "TRUE"
},
"cbs_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option to specify whether to perform CBS",
"hidden": true,
"help_text": "if TRUE, perform cbs on the drycleaned coverage",
"default": "FALSE"
},
"cnsignif_dryclean": {
"type": "number",
"default": 0.00001,
"fa_icon": "fas fa-wrench",
"description": "Significance level for CBS",
"help_text": "the significance levels for the test to accept change-points in cbs"
},
"wholeGenome_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option to specify whether perform dryclean on whole genome",
"hidden": true,
"help_text": "if TRUE, it will process all chromosomes and parallelize it",
"default": "TRUE"
},
"blacklist_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Option to specify whether there are blacklisted makers",
"hidden": true,
"help_text": "if TRUE, will assume there is blacklisted makers",
"default": "FALSE"
},
"blacklist_path_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Dryclean blacklist path",
"help_text": "Provide the path to dryclean blacklist, default is null",
"default": "NA"
},
"germline_filter_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "If PON based germline filter is to be used for removing some common germline events",
"hidden": true,
"help_text": "If set to TRUE, give path to germline annotated file",
"default": "FALSE"
},
"germline_file_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Path to file annotated with germline calls, if germline.filter == TRUE",
"help_text": "Path to file annotated with germline calls, if germline.filter == TRUE",
"default": "NA"
},
"field_dryclean": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "Field name in GRanges metadata to use for drycleaning",
"help_text": "Specify Field name in GRanges metadata to use for drycleaning",
"default": "reads"
},
"build_dryclean": {
"type": "string",
"default": "hg19",
"description": "Mention whether it is hg19 or hg38",
"fa_icon": "fas fa-font"
}
}
},
"cbs": {
"title": "CBS",
"type": "object",
"description": "Input params to run CBS",
"default": "",
"properties": {
"cnsignif_cbs": {
"type": "number",
"default": 0.01,
"description": "Significance level to consider for CBS",
"help_text": "Default is set to 10% or 0.01",
"fa_icon": "fas fa-filter"
},
"field_cbs": {
"type": "string",
"default": "foreground",
"description": "Field to apply CBS on",
"help_text": "Defualt field is \"foreground\" if it comes from dryclean. Else, select the column to apply CBS on",
"fa_icon": "fas fa-font"
},
"name_cbs": {
"type": "string",
"default": "tumor",
"description": "Name of CBS run",
"fa_icon": "fas fa-font",
"hidden": true
}
},
"fa_icon": "fas fa-suitcase"
},
"ascat_seg": {
"title": "ASCAT SEG",
"type": "object",
"description": "Run ASCAT using Hetpileups and Segments files as inputs",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"field_ascat": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "field to use for ascat from coverage, default is ratio",
"help_text": "Provide the field from cbs cov",
"default": "foreground"
},
"hets_thresh_ascat": {
"type": "number",
"default": 0.2,
"fa_icon": "fas fa-wrench",
"description": "Significance level for CBS",
"help_text": "the significance levels for the test to accept change-points in cbs"
},
"penalty_ascat": {
"type": "number",
"default": 70,
"fa_icon": "fas fa-wrench",
"description": "Significance level for CBS",
"help_text": "the significance levels for the test to accept change-points in cbs"
},
"gc_correct_ascat": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "whether to perform gc correction on coverage",
"help_text": "By default it is true and should perform gc corrections",
"default": "TRUE"
},
"rebin_width_ascat": {
"type": "number",
"default": 50000,
"fa_icon": "fas fa-wrench",
"description": "Width of bins to do",
"help_text": "The bin size, default is 5e4"
},
"from_maf_ascat": {
"type": "string",
"fa_icon": "fas fa-forward",
"description": "whether to start from MAF stage",
"help_text": "By default it is FALSE and should not start from MAF stage",
"default": "FALSE",
"hidden": true
}
}
},
"jabba": {
"title": "JaBbA",
"type": "object",
"description": "Input params to run JaBbA",
"default": "",
"properties": {
"blacklist_junctions_jabba": {
"type": "string",
"description": "rearrangement junctions to be excluded from consideration",
"fa_icon": "fas fa-file"
},
"geno_jabba": {
"type": "string",
"default": "FALSE",
"description": "whether the junction has genotype information",
"hidden": true
},
"indel_jabba": {
"type": "string",
"default": "exclude",
"description": "character of the decision to 'exclude' or 'include' small(< min.nbins * coverage bin width) isolated INDEL-like events into the model."
},
"tfield_jabba": {
"type": "string",
"default": "tier",
"description": "tier confidence meta data field in ra. tiers are 1 = must use, 2 = may use, 3 = use only in iteration>1 if near loose end. Default 'tier'.",
"fa_icon": "fas fa-font"
},
"iter_jabba": {
"type": "integer",
"default": 2,
"description": "the number of extra re-iterations allowed, to rescue lower confidence junctions that are near loose end. Default 0. This requires junctions to be tiered via a metadata field tfield.",
"hidden": true,
"fa_icon": "fas fa-wrench"
},
"rescue_window_jabba": {
"type": "integer",
"default": 10000,
"description": "window size in bp within which to look for lower confidence junctions. Default 1000.",
"hidden": true,
"fa_icon": "fas fa-wrench"
},
"rescue_all_jabba": {
"type": "string",
"default": "TRUE",
"hidden": true,
"fa_icon": "fas fa-forward",
"description": "whether to rescue all lower confidence junctions within the window, or just the best one."
},
"nudgebalanced_jabba": {
"type": "string",
"default": "TRUE",
"description": "whether to attempt to add a small incentive for chains of quasi-reciprocal junctions.",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"strict_jabba": {
"type": "string",
"default": "FALSE",
"description": "if used will only include junctions that exactly overlap segs",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"edgenudge_jabba": {
"type": "number",
"default": 0.1,
"description": "numeric hyper-parameter of how much to nudge or reward aberrant junction incorporation. Default 0.1 (should be several orders of magnitude lower than average 1/sd on individual segments), a nonzero value encourages incorporation of perfectly balanced rearrangements which would be equivalently optimal with 0 copies or more copies.",
"hidden": true,
"fa_icon": "fas fa-wrench"
},
"allin_jabba": {
"type": "string",
"default": "FALSE",
"description": "if TRUE will put all tiers in the first round of iteration",
"hidden": true,
"fa_icon": "fas fa-wrench"
},
"field_jabba": {
"type": "string",
"default": "foreground",
"description": "name of the metadata column of coverage that contains the data. Default 'ratio' (coverage ratio between tumor and normal). If using dryclean, it is 'foreground'.",
"fa_icon": "fas fa-font"
},
"maxna_jabba": {
"type": "number",
"default": 0.9,
"description": "Any node with more NA than this fraction will be ignored",
"fa_icon": "fas fa-wrench"
},
"ploidy_jabba": {
"type": "string",
"default": "NA",
"description": "Ploidy guess, can be a length 2 range",
"fa_icon": "fas fa-wrench"
},
"purity_jabba": {
"type": "string",
"default": "NA",
"description": "Purity guess, can be a length 2 range",
"fa_icon": "fas fa-wrench"
},
"pp_method_jabba": {
"type": "string",
"default": "ppgrid",
"description": "select from 'ppgrid', 'ppurple', and 'sequenza' to infer purity and ploidy if not both given. Default, 'sequenza'.",
"fa_icon": "fas fa-calculator"
},
"cnsignif_jabba": {
"type": "number",
"default": 0.00001,
"description": "alpha value for CBS",
"fa_icon": "fas fa-wrench"
},
"slack_jabba": {
"type": "integer",
"default": 100,
"description": "Slack penalty to apply per loose end",
"fa_icon": "fas fa-wrench"
},
"linear_jabba": {
"type": "string",
"default": "TRUE",
"description": "if TRUE will use L1 loose end penalty",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"tilim_jabba": {
"type": "integer",
"default": 7200,
"description": "Time limit for JaBbA MIP",
"fa_icon": "fas fa-wrench"
},
"epgap_jabba": {
"type": "number",
"description": "threshold for calling convergence",
"fa_icon": "fas fa-wrench"
},
"fix_thres_jabba": {
"type": "integer",
"default": -1,
"fa_icon": "fas fa-wrench",
"description": "threshold for calling convergence"
},
"lp_jabba": {
"type": "string",
"default": "TRUE",
"description": "Run as LP",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"ism_jabba": {
"type": "string",
"default": "TRUE",
"description": "Include infinite sites constraints",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"filter_loose_jabba": {
"type": "string",
"default": "FALSE",
"description": "whether to filter loose ends",
"fa_icon": "fas fa-forward"
},
"gurobi_jabba": {
"type": "string",
"default": "FALSE",
"description": "Whether to run with GUROBI instead of CPLEX",
"hidden": true,
"fa_icon": "fas fa-tools"
},
"nonintegral_jabba": {
"type": "string",
"default": "FALSE",
"fa_icon": "fas fa-forward",
"description": "whether to allow non-integral solutions"
},
"verbose_jabba": {
"type": "string",
"default": "TRUE",
"description": "verbose output",
"hidden": true,
"fa_icon": "fas fa-forward"
},
"help_jabba": {
"type": "string",
"default": "FALSE",
"description": "Show this help message and exitsage: jba JUNCTIONS COVERAGE [options]",
"hidden": true,
"fa_icon": "fas fa-file"
},
"blacklist_coverage_jabba": {
"type": "string",
"default": "None",
"description": "File path to remove blacklisted positions from coverage",
"fa_icon": "fas fa-file"
}
},
"fa_icon": "fas fa-suitcase"
},
"variant_calling": {
"title": "Variant Calling",
"type": "object",
"description": "Configure variant calling tools",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"concatenate_vcfs": {
"type": "boolean",
"fa_icon": "fas fa-merge",
"description": "Option for concatenating germline vcf-files.",
"help_text": "Concatenating the germline vcf-files from each applied variant-caller into one vcf-file using bfctools concat."
},
"only_paired_variant_calling": {
"type": "boolean",
"fa_icon": "fas fa-forward",
"description": "If true, skips germline variant calling for matched normal to tumor sample. Normal samples without matched tumor will still be processed through germline variant calling tools.",
"help_text": "This can speed up computation for somatic variant calling with matched normal samples. If false, all normal samples are processed as well through the germline variantcalling tools. If true, only somatic variant calling is done."
},
"joint_germline": {
"type": "boolean",
"fa_icon": "fas fa-toolbox",
"description": "Turn on the joint germline variant calling for GATK haplotypecaller",
"help_text": "Uses all normal germline samples (as designated by `status` in the input csv) in the joint germline variant calling process."
},
"joint_mutect2": {
"type": "boolean",
"fa_icon": "fas fa-angle-double-right",
"description": "Runs Mutect2 in joint (multi-sample) mode for better concordance among variant calls of tumor samples from the same patient. Mutect2 outputs will be stored in a subfolder named with patient ID under `variant_calling/mutect2/` folder. Only a single normal sample per patient is allowed. Tumor-only mode is also supported."
},
"cf_chrom_len": {
"type": "string",
"fa_icon": "fas fa-ruler-horizontal",
"description": "Specify a custom chromosome length file.",
"help_text": "Control-FREEC requires a file containing all chromosome lenghts. By default the fasta.fai is used. If the fasta.fai file contains chromosomes not present in the intervals, it fails (see: https://github.com/BoevaLab/FREEC/issues/106).\n\nIn this case, a custom chromosome length can be specified. It must be of the same format as the fai, but only contain the relevant chromosomes.\n\n\n\n",
"hidden": true
},
"cf_coeff": {
"type": "number",
"default": 0.05,
"fa_icon": "fas fa-wrench",
"description": "Overwrite Control-FREEC coefficientOfVariation",
"hidden": true,
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
},
"cf_contamination_adjustment": {
"type": "boolean",
"fa_icon": "fas fa-broom",
"description": "Overwrite Control-FREEC contaminationAdjustement",
"hidden": true,
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
},
"cf_contamination": {
"type": "number",
"default": 0,
"fa_icon": "fas fa-broom",
"description": "Design known contamination value for Control-FREEC",
"hidden": true,
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
},
"cf_minqual": {
"type": "number",
"default": 0,
"fa_icon": "fas fa-greater-than",
"hidden": true,
"description": "Minimal sequencing quality for a position to be considered in BAF analysis.",
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
},
"cf_mincov": {
"type": "number",
"default": 0,
"fa_icon": "fas fa-align-center",
"hidden": true,
"description": "Minimal read coverage for a position to be considered in BAF analysis.",
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
},
"cf_ploidy": {
"type": "string",
"default": "2",
"fa_icon": "fas fa-bacon",
"help_text": "In case of doubt, you can set different values and Control-FREEC will select the one that explains most observed CNAs Example: ploidy=2 , ploidy=2,3,4. For more details, see the [manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html).",
"description": "Genome ploidy used by ControlFREEC",
"hidden": true
},
"cf_window": {
"type": "number",
"fa_icon": "fas fa-window-maximize",
"description": "Overwrite Control-FREEC window size.",
"help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html).",
"hidden": true
},
"cnvkit_reference": {
"type": "string",
"fa_icon": "fas fa-file",
"help_text": "https://cnvkit.readthedocs.io/en/stable/pipeline.html?highlight=reference.cnn#batch",
"description": "Copy-number reference for CNVkit",
"hidden": true
},
"ignore_soft_clipped_bases": {
"type": "boolean",
"fa_icon": "fas fa-ban",
"description": "Do not analyze soft clipped bases in the reads for GATK Mutect2.",
"help_text": "use the `--dont-use-soft-clipped-bases` params with GATK Mutect2.",
"hidden": true
},
"sentieon_haplotyper_emit_mode": {
"type": "string",
"default": "variant",
"fa_icon": "fas fa-toolbox",
"description": "Option for selecting output and emit-mode of Sentieon's Haplotyper.",
"help_text": "The option `--sentieon_haplotyper_emit_mode` can be set to the same string values as the Haplotyper's `--emit_mode`. To output both a vcf and a gvcf, specify both a vcf-option (currently, `all`, `confident` and `variant`) and `gvcf`. For example, to obtain a vcf and gvcf one could set `--sentieon_haplotyper_emit_mode` to `variant, gvcf`.",
"pattern": "^(all|confident|gvcf|variant|gvcf,all|gvcf,confident|gvcf,variant|all,gvcf|confident,gvcf|variant,gvcf)(?<!,)$"
},
"ascat_min_base_qual": {
"type": "number",
"default": 20,
"fa_icon": "fas fa-greater-than",
"description": "Overwrite Ascat min base quality required for a read to be counted.",
"hidden": true,
"help_text": "For more details see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)"
},
"ascat_min_counts": {
"type": "number",
"default": 10,
"fa_icon": "fas fa-align-center",
"description": "Overwrite Ascat minimum depth required in the normal for a SNP to be considered.",
"hidden": true,
"help_text": "For more details, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)."
},
"ascat_min_map_qual": {
"type": "number",
"default": 35,
"fa_icon": "fas fa-balance-scale-left",
"description": "Overwrite Ascat min mapping quality required for a read to be counted.",
"hidden": true,
"help_text": "For more details, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)."
},
"ascat_ploidy": {
"type": "number",
"fa_icon": "fas fa-bacon",
"help_text": "ASCAT: optional argument to override ASCAT optimization and supply psi parameter (expert parameter, do not adapt unless you know what you are doing). See [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)",
"hidden": true,
"description": "Overwrite ASCAT ploidy."
},
"ascat_purity": {
"type": "number",
"fa_icon": "fas fa-broom",
"description": "Overwrite ASCAT purity.",
"help_text": "Overwrites ASCAT's `rho_manual` parameter. Expert use only, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf) for details.\nRequires that `--ascat_ploidy` is set.",
"hidden": true
}
}
},
"annotation": {
"title": "Annotation",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-toolbox",
"properties": {
"vep_cache": {
"type": "string",
"fa_icon": "fas fa-file",
"default": "s3://annotation-cache/vep_cache/",
"description": "Path to VEP cache.",
"help_text": "Path to VEP cache which should contain the relevant species, genome and build directories at the path ${vep_species}/${vep_genome}_${vep_cache_version}",
"hidden": true
},
"snpeff_cache": {
"type": "string",
"fa_icon": "fas fa-file",
"default": "s3://annotation-cache/snpeff_cache/",
"description": "Path to snpEff cache.",
"help_text": "Path to snpEff cache which should contain the relevant genome and build directory in the path ${snpeff_species}.${snpeff_version}",
"hidden": true
},
"vep_include_fasta": {
"type": "boolean",
"fa_icon": "fas fa-file",
"description": "Allow usage of fasta file for annotation with VEP",
"hidden": true,
"help_text": "By pointing VEP to a FASTA file, it is possible to retrieve reference sequence locally. This enables VEP to retrieve HGVS notations (--hgvs), check the reference sequence given in input data, and construct transcript models from a GFF or GTF file without accessing a database.\n\nFor details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#fasta)."
},
"vep_dbnsfp": {
"type": "boolean",
"fa_icon": "fas fa-database",
"description": "Enable the use of the VEP dbNSFP plugin.",
"hidden": true,
"help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp)."
},
"dbnsfp": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to dbNSFP processed file.",
"help_text": "To be used with `--vep_dbnsfp`.\ndbNSFP files and more information are available at https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp and https://sites.google.com/site/jpopgen/dbNSFP/",
"hidden": true
},
"dbnsfp_tbi": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to dbNSFP tabix indexed file.",
"help_text": "To be used with `--vep_dbnsfp`.",
"hidden": true
},
"dbnsfp_consequence": {
"type": "string",
"fa_icon": "fas fa-arrow-alt-circle-right",
"description": "Consequence to annotate with",
"help_text": "To be used with `--vep_dbnsfp`.\nThis params is used to filter/limit outputs to a specific effect of the variant.\nThe set of consequence terms is defined by the Sequence Ontology and an overview of those used in VEP can be found here: https://www.ensembl.org/info/genome/variation/prediction/predicted_data.html\nIf one wants to filter using several consequences, then separate those by using '&' (i.e. 'consequence=3_prime_UTR_variant&intron_variant'.",
"hidden": true
},
"dbnsfp_fields": {
"type": "string",
"fa_icon": "fas fa-border-all",
"description": "Fields to annotate with",
"default": "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF",
"help_text": "To be used with `--vep_dbnsfp`.\nThis params can be used to retrieve individual values from the dbNSFP file. The values correspond to the name of the columns in the dbNSFP file and are separated by comma.\nThe column names might differ between the different dbNSFP versions. Please check the Readme.txt file, which is provided with the dbNSFP file, to obtain the correct column names. The Readme file contains also a short description of the provided values and the version of the tools used to generate them.\n\nDefault value are explained below:\n\nrs_dbSNP - rs number from dbSNP\nHGVSc_VEP - HGVS coding variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_transcriptid\nHGVSp_VEP - HGVS protein variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_proteinid\n1000Gp3_EAS_AF - Alternative allele frequency in the 1000Gp3 East Asian descendent samples\n1000Gp3_AMR_AF - Alternative allele counts in the 1000Gp3 American descendent samples\nLRT_score - Original LRT two-sided p-value (LRTori), ranges from 0 to 1\nGERP++_RS - Conservation score. The larger the score, the more conserved the site, ranges from -12.3 to 6.17\ngnomAD_exomes_AF - Alternative allele frequency in the whole gnomAD exome samples.",
"hidden": true
},
"vep_loftee": {
"type": "boolean",
"fa_icon": "fas fa-database",
"description": "Enable the use of the VEP LOFTEE plugin.",
"hidden": true,
"help_text": "For details, see [here](https://github.com/konradjk/loftee)."
},
"vep_spliceai": {
"type": "boolean",
"fa_icon": "fas fa-database",
"description": "Enable the use of the VEP SpliceAI plugin.",
"hidden": true,
"help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceai)."
},
"spliceai_snv": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to spliceai raw scores snv file.",
"help_text": "To be used with `--vep_spliceai`.",
"hidden": true
},
"spliceai_snv_tbi": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to spliceai raw scores snv tabix indexed file.",
"help_text": "To be used with `--vep_spliceai`.",
"hidden": true
},
"spliceai_indel": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to spliceai raw scores indel file.",
"help_text": "To be used with `--vep_spliceai`.",
"hidden": true
},
"spliceai_indel_tbi": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Path to spliceai raw scores indel tabix indexed file.",
"help_text": "To be used with `--vep_spliceai`.",
"hidden": true
},
"vep_spliceregion": {
"type": "boolean",
"fa_icon": "fas fa-database",
"description": "Enable the use of the VEP SpliceRegion plugin.",
"hidden": true,
"help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceregion) and [here](https://www.ensembl.info/2018/10/26/cool-stuff-the-vep-can-do-splice-site-variant-annotation/)."
},
"vep_custom_args": {
"type": "string",
"default": "--everything --filter_common --per_gene --total_length --offline --format vcf",
"fa_icon": "fas fa-toolbox",
"description": "Add an extra custom argument to VEP.",
"hidden": true,
"help_text": "Using this params you can add custom args to VEP."
},
"use_annotation_cache_keys": {
"type": "boolean",
"fa_icon": "fas fa-toolbox",
"description": "Use annotation cache keys for snpeff_cache and vep_cache.",