forked from PapenfussLab/proteindj
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathnextflow_schema.json
More file actions
880 lines (880 loc) · 41.9 KB
/
nextflow_schema.json
File metadata and controls
880 lines (880 loc) · 41.9 KB
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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com//master/nextflow_schema.json",
"title": " pipeline parameters",
"description": "",
"type": "object",
"definitions": {
"essential_parameters": {
"title": "Essential Parameters",
"type": "object",
"description": "These parameters are required for ProteinDJ and are used by every mode.",
"default": "",
"properties": {
"design_mode": {
"type": "string",
"description": "Pipeline mode. Choose from 'bindcraft_denovo' to use BindCraft or 'binder_denovo', 'binder_foldcond', 'binder_motifscaff', 'binder_partialdiff', 'monomer_denovo', 'monomer_foldcond', 'monomer_motifscaff', or 'monomer_partialdiff' to use RFdiffusion."
},
"num_designs": {
"type": "integer",
"default": 8,
"description": "Number of designs to generate using RFdiffusion or Bindcraft."
},
"seqs_per_design": {
"type": "integer",
"default": 8,
"description": "Number of sequences to generate per design."
},
"out_dir": {
"type": "string",
"default": "${projectDir}/pdj_results",
"description": "Output directory for results.",
"format": "directory-path"
}
},
"required": [
"design_mode",
"num_designs",
"seqs_per_design",
"out_dir"
]
},
"mode_specific_parameters": {
"title": "Mode-Specific Parameters",
"type": "object",
"description": "These parameters are used for some of the ProteinDJ modes.",
"default": "",
"properties": {
"design_length": {
"type": "string",
"description": "Design length. One or two dash separated values for min-max design length e.g. '60', '60-70'. Pipeline will randomly sample different sizes between these values.",
"pattern": "^\\d+(-\\d+)?$"
},
"input_pdb": {
"type": "string",
"pattern": ".*\\.pdb$",
"format": "file-path",
"description": "Path to an input PDB file. e.g. 'target.pdb'"
},
"hotspot_residues": {
"type": "string",
"description": "Specifies hotspot residues for binding. e.g. 'A56,A115,A123'",
"pattern": "^[A-Z]\\d+(,[A-Z]\\d+)*$"
},
"rfd_contigs": {
"type": "string",
"description": "Contigs specification strings for residues to include from input PDB and/or design length, e.g. `[A17-145/0 50-100]`. See docs for examples. Optional for multiple modes, required by `binder_motifscaff` and `monomer_motifscaff`. If null, contigs will be auto generated from input PDB (all residues) and/or `design_length`.",
"pattern": "^\\[[A-Z0-9\\-\\/ \\[\\]]+\\]$"
},
"rfd_scaffold_dir": {
"type": "string",
"format": "directory-path",
"description": "Path to directory containing scaffold files. e.g. 'binderscaffolds/scaffolds_assorted'"
},
"rfd_mask_loops": {
"type": "boolean",
"default": true,
"description": "Whether to ignore loop regions when applying secondary structure constraints from scaffolds (default=true). Recommended to set to false for binder design as the scaffold sets have enough diversity"
},
"rfd_inpaint_seq": {
"type": "string",
"description": "Residues that will have their sequence masked when diffusing. e.g. '[A17-19/A143-145]'",
"pattern": "^\\[([A-Z]?\\d+(?:-\\d+)?(?:\\/\\d+)?)(?:\\/([A-Z]?\\d+(?:-\\d+)?(?:\\/\\d+)?))*\\]$"
},
"rfd_length": {
"type": "string",
"description": "Length of diffused chain when performing motif scaffolding e.g. 100-120",
"pattern": "^\\d+-\\d+$"
},
"rfd_partial_diffusion_timesteps": {
"type": "integer",
"description": "Number of timesteps for partial diffusion. e.g. 20"
}
}
},
"workflow_advanced_parameters": {
"title": "Mode-Specific Parameters",
"type": "object",
"description": "These parameters are used for some of the ProteinDJ modes.",
"default": "",
"properties": {
"seq_method": {
"type": "string",
"default": "mpnn",
"description": "Sequence design method. Choose from 'mpnn' (ProteinMPNN Fast-Relax) or 'fampnn' (Full-Atom MPNN).",
"enum": [
"mpnn",
"fampnn"
]
},
"pred_method": {
"type": "string",
"default": "af2",
"description": "Structure prediction method. Choose from 'af2' (AlphaFold2 Initial-Guess) or 'boltz' (Boltz-2).",
"enum": [
"af2",
"boltz"
]
},
"zip_pdbs": {
"type": "boolean",
"description": "Whether to compress output final designs in a tar.gz archive. If false, results will be output as uncompressed PDB files.",
"default": true,
"hidden": true
},
"rank_designs": {
"type": "boolean",
"description": "Whether to rank final designs by prediction quality metrics and output ranked_designs.",
"default": true,
"hidden": true
},
"ranking_metric": {
"type": "string",
"description": "Structure prediction metric to use for ranking designs (e.g., 'af2_pae_interaction', 'boltz_ipSAE_min', 'boltz_ptm_interface'). Must match the prediction method prefix (af2_* for AlphaFold2, boltz_* for Boltz-2). If null, defaults to 'af2_pae_interaction' for AlphaFold2 or 'boltz_ipSAE_min' for Boltz-2.",
"hidden": true
},
"max_designs": {
"type": "integer",
"description": "Maximum number of top-ranked designs to output (null = output all ranked designs)",
"hidden": true
},
"max_seqs_per_fold": {
"type": "integer",
"description": "Maximum number of sequences per fold to keep after ranking (null = no limit). Helps increase fold diversity.",
"hidden": true
},
"run_fold_only": {
"type": "boolean",
"description": "Whether to run fold design only and skip downstream stages (i.e. sequence design, prediction, and analysis)",
"hidden": true
},
"skip_fold": {
"type": "boolean",
"description": "Skip Fold Design and run Sequence Design, Structure Prediction, and Analysis only. Must provide 'skip_input_dir' directory below containing PDB and JSON files with metadata. Binder design PDBs must have binder as chain A and target as chain B.",
"hidden": true
},
"skip_fold_seq": {
"type": "boolean",
"description": "Skip Fold Design and Sequence Design, and run Structure Prediction and Analysis only. Must provide 'skip_input_dir' directory below containing PDB and JSON files with metadata. Binder design PDBs must have binder as chain A and target as chain B.",
"hidden": true
},
"skip_fold_seq_pred": {
"type": "boolean",
"description": "Skip Fold Design, Sequence Design, and Structure Prediction, and run Analysis only. Must provide 'skip_input_dir' directory below containing PDB and JSON files with metadata. Binder design PDBs must have binder as chain A and target as chain B.",
"hidden": true
},
"skip_input_dir": {
"type": "string",
"description": "Path to input files when skipping stages e.g. './rfd_results'",
"format": "directory-path",
"hidden": true
}
}
},
"bindcraft_advanced_parameters": {
"title": "BindCraft Advanced Parameters",
"type": "object",
"description": "Advanced parameters to control the behaviour of BindCraft.",
"default": "",
"properties": {
"bc_chains": {
"type": "string",
"description": "Input PDB chains to target. Can be one or multiple, in a comma-separated format e.g. 'A,C'. Other chains will be ignored during design.",
"pattern": "^[A-Z](,[A-Z])*$",
"hidden": true
},
"bc_design_protocol": {
"type": "string",
"description": "Which binder design protocol to run? 'default' is recommended. 'betasheet' promotes the design of more beta sheeted proteins, but requires more sampling. 'peptide' is optimised for helical peptide binders.",
"enum": [
"default",
"betasheet",
"peptide"
],
"default": "default",
"hidden": true
},
"bc_template_protocol": {
"type": "string",
"description": "What target template protocol to use? 'default' allows for limited amount of flexibility. 'flexible' allows for greater target flexibility on both sidechain and backbone level.",
"enum": [
"default",
"flexible"
],
"default": "default",
"hidden": true
},
"bc_omit_AAs": {
"type": "string",
"description": "Residue types to avoid during sequence design (comma separated list, one letter case-insensitive) (default: 'C') e.g. 'C,H'. These residue types can still occur if no other options are possible in the position.",
"pattern": "^[A-Z](,[A-Z])*$",
"default": "C",
"hidden": true
},
"bc_fix_interface_residues": {
"type": "boolean",
"description": "Whether to preserve/fix the interface residues of the binder designed by BindCraft during the subsequent sequence design stage (Recommended to leave as true).",
"hidden": true
},
"bc_advanced_json": {
"type": "string",
"description": "Path to a custom advanced settings json file. Not recommended unless you know what you are doing. Some parameters will be ignored as they apply to BindCraft routines downstream of fold design that are not implemented here e.g. MPNN parameters.",
"hidden": true,
"format": "file-path",
"pattern": "\\.json$"
}
}
},
"rfdiffusion_advanced_parameters": {
"title": "RFdiffusion Advanced Parameters",
"type": "object",
"description": "Advanced parameters to control the behaviour of RFdiffusion.",
"default": "",
"properties": {
"rfd_ckpt_override": {
"type": "string",
"description": "Override the diffusion model checkpoint used by RFdiffusion. Choose from: 'active_site', 'base', 'base_epoch8', 'complex_base', 'complex_beta', 'complex_fold_base', 'inpaint_seq', 'inpaint_seq_fold'. RFdiffusion will automatically select a checkpoint. Not recommended to override except for 'binder_denovo' mode i.e. 'complex_beta'",
"enum": [
"active_site",
"base",
"base_epoch8",
"complex_base",
"complex_beta",
"complex_fold_base",
"inpaint_seq",
"inpaint_seq_fold"
],
"hidden": true
},
"rfd_noise_scale": {
"type": "number",
"description": "Scale of noise for RFdiffusion translations (C-alpha) and rotations (frames). 1 (default) is recommended for monomer modes to increase diversity. 0-0.5 is recommended for binder modes to increase success rates.",
"minimum": 0,
"maximum": 1,
"hidden": true
},
"rfd_extra_config": {
"type": "string",
"description": "Additional configuration parameters to pass to RFdiffusion. e.g. 'contigmap.inpaint_str=[B165-178]'",
"hidden": true
}
}
},
"proteinmpnn_fastrelax_parameters": {
"title": "ProteinMPNN-FastRelax Parameters",
"type": "object",
"description": "Advanced parameters to control the behaviour of ProteinMPNN-FastRelax. Used for binder design modes only.",
"default": "",
"properties": {
"mpnn_omitAAs": {
"type": "string",
"default": "CX",
"pattern": "^[A-Za-z]*$",
"description": "A string of all residue types (one letter case-insensitive) to avoid for design. Default: CX",
"hidden": true
},
"mpnn_temperature": {
"type": "number",
"default": 0.1,
"description": "Temperature for sequence sampling. Higher values increase sequence diversity.",
"hidden": true
},
"mpnn_checkpoint_type": {
"type": "string",
"default": "soluble",
"enum": [
"vanilla",
"soluble",
"hyper"
],
"description": "Checkpoint type to use for ProteinMPNN. Choose from 'vanilla', 'soluble' or 'hyper' (default = 'soluble').",
"hidden": true
},
"mpnn_checkpoint_model": {
"type": "string",
"default": "v_48_020",
"description": "Checkpoint model to use for ProteinMPNN. Indicates noise level used during training for backbone atoms. Choose from 'v_48_002','v_48_010,'v_48_020','v_48_030'. (default = 'v_48_020', noised with 0.20Å Gaussian noise)",
"enum": [
"v_48_002",
"v_48_010",
"v_48_020",
"v_48_030"
],
"hidden": true
},
"mpnn_backbone_noise": {
"type": "number",
"default": 0,
"description": "Standard deviation of Gaussian noise to add to backbone atoms. 0 = no change to backbone, 0.1-0.3 = allows mild perturbation of backbone.",
"hidden": true
},
"mpnn_relax_max_cycles": {
"type": "integer",
"default": 0,
"description": "Maximum number of fast relax cycles to run on each sequence. Set to zero to disable.",
"hidden": true
},
"mpnn_relax_seqs_per_cycle": {
"type": "integer",
"default": 1,
"description": "Number of sequences to generate between relaxation steps. The sequence with the best score will be kept.",
"hidden": true
},
"mpnn_relax_output": {
"type": "boolean",
"description": "Whether to run a relaxation cycle before saving output.",
"hidden": true
},
"mpnn_relax_convergence_rmsd": {
"type": "number",
"default": 0.2,
"description": "Design is considered converged if the C-alpha RMSD (Å) between cycles is <= this threshold.",
"hidden": true
},
"mpnn_relax_convergence_score": {
"type": "number",
"default": 0.1,
"description": "Design is considered converged if the improvement in score between cycles is <= this threshold.",
"hidden": true
},
"mpnn_relax_convergence_max_cycles": {
"type": "integer",
"default": 1,
"description": "Design is considered converged if it meets both convergence criteria for n consecutive cycles.",
"hidden": true
},
"mpnn_extra_config": {
"type": "string",
"description": "Additional configuration parameters to pass to ProteinMPNN-FastRelax that are not externalised in Nextflow. e.g. '-protein_features=\"full\"'",
"hidden": true
}
}
},
"full_atom_mpnn_parameters": {
"title": "Full-Atom MPNN Parameters",
"type": "object",
"description": "Advanced parameters to control the behaviour of Full-Atom MPNN",
"default": "",
"properties": {
"fampnn_fix_target_sidechains": {
"type": "boolean",
"default": false,
"description": "Fix target side-chain positions when performing binder sequence design (default: false)",
"hidden": true
},
"fampnn_psce_threshold": {
"type": "number",
"default": 0.3,
"description": "Only keep sidechains below this PSCE threshold during design; null to keep all.",
"hidden": true
},
"fampnn_temperature": {
"type": "number",
"default": 0.1,
"description": "Temperature for sequence sampling. Higher values increase sequence diversity.",
"hidden": true
},
"fampnn_exclude_cys": {
"type": "boolean",
"default": true,
"description": "Exclude cysteine residues from sequence design.",
"hidden": true
},
"fampnn_extra_config": {
"type": "string",
"description": "Additional configuration parameters to pass to Full-Atom MPNN that are not externalised in Nextflow. e.g. 'timestep_schedule.num_steps=100 seq_only=true'",
"hidden": true
}
}
},
"prediction_advanced_parameters": {
"title": "Structure Prediction Advanced Parameters",
"type": "object",
"description": "Parameters for AlphaFold2 Initial-Guess and Boltz-2",
"default": "",
"properties": {
"uncropped_target_pdb": {
"type": "string",
"description": "Path to uncropped target PDB file to use in structure prediction e.g. 'benchmarkdata/5o45_pd-l1_uncropped.pdb'",
"hidden": true,
"format": "file-path",
"pattern": "\\.pdb$"
},
"af2_initial_guess": {
"type": "boolean",
"default": true,
"description": "Use an initial-guess of the target chain(s) when performing binder structure prediction. When false, AF2 will not use an initial guess. Default = true",
"hidden": true
},
"af2_extra_config": {
"type": "string",
"hidden": true,
"description": "Additional configuration parameters to pass to AlphaFold2 Initial-Guess that are not externalised in Nextflow. e.g. '-recycle 3'"
},
"boltz_recycling_steps": {
"type": "integer",
"default": 3,
"description": "The number of recycling steps to use for prediction.",
"minimum": 1,
"hidden": true
},
"boltz_diffusion_samples": {
"type": "integer",
"default": 1,
"description": "The number of diffusion samples to use for prediction.",
"minimum": 1,
"hidden": true
},
"boltz_sampling_steps": {
"type": "integer",
"default": 200,
"description": "The number of sampling steps to use for prediction.",
"minimum": 1,
"hidden": true
},
"boltz_use_potentials": {
"type": "boolean",
"default": false,
"description": "Use physics-based potentials during inference to improve physical plausibility of predictions (also known as Boltz-2x). Increases prediction time. Default = false",
"hidden": true
},
"boltz_use_templates": {
"type": "boolean",
"default": true,
"description": "Whether to use template structures to guide Boltz-2 predictions. Template is generated from input design structure. For monomer modes: uses chain A as template. For binder modes: uses chain B (target) as template only, similar to AlphaFold2 Initial-Guess.",
"hidden": true
},
"boltz_template_force": {
"type": "boolean",
"default": false,
"description": "Whether to enforce template structure using a potential (force constraint). Only applies if boltz_use_templates=true.",
"hidden": true
},
"boltz_template_threshold": {
"type": "number",
"description": "Distance threshold in Angstroms that the prediction can deviate from the template e.g. 1. Only applies if boltz_use_templates=true. If null, no distance threshold is applied.",
"hidden": true
},
"boltz_input_msa": {
"type": "string",
"description": "Path to a multiple sequence alignment (.a3m format) for the input PDB. Applies to chain B in binder modes or chain A in monomer modes. If null, single-sequence mode is used.",
"format": "file-path",
"pattern": "\\.a3m$",
"hidden": true
},
"boltz_extra_config": {
"type": "string",
"hidden": true,
"description": "Additional configuration parameters to pass to Boltz-2 that are not externalised in Nextflow. e.g. '--msa_pairing_strategy complete'"
}
}
},
"filtering_parameters": {
"title": "Filtering Parameters",
"type": "object",
"description": "Metrics are calculated on the binder chain only in binder design modes, otherwise all chains are used in calculations.",
"default": "",
"properties": {
"fold_min_helices": {
"type": "integer",
"description": "Minimum number of alpha-helices required. e.g. 3",
"hidden": true
},
"fold_max_helices": {
"type": "integer",
"description": "Maximum number of alpha-helices allowed. e.g. 6",
"hidden": true
},
"fold_min_strands": {
"type": "integer",
"description": "Minimum number of beta-strands required. e.g. 2",
"hidden": true
},
"fold_max_strands": {
"type": "integer",
"description": "Maximum number of beta-strands allowed. e.g. 6",
"hidden": true
},
"fold_min_ss": {
"type": "integer",
"description": "Minimum number of secondary structure elements (α-helices + β-strands). e.g. 4",
"hidden": true
},
"fold_max_ss": {
"type": "integer",
"description": "Maximum number of secondary structure elements (α-helices + β-strands). e.g. 8",
"hidden": true
},
"fold_min_rog": {
"type": "number",
"description": "Minimum radius of gyration (Å). e.g. 10",
"hidden": true
},
"fold_max_rog": {
"type": "number",
"description": "Maximum radius of gyration (Å). e.g. 20",
"hidden": true
},
"mpnn_max_score": {
"type": "number",
"description": "Maximum MPNN score (negative log likelihood). A lower score means ProteinMPNN is more confident in the sequence.",
"hidden": true
},
"fampnn_max_psce": {
"type": "number",
"description": "Max PSCE score for designed side-chains. A lower score means FAMPNN is more confident in the sequence.",
"hidden": true
},
"af2_max_pae_interaction": {
"type": "number",
"description": "Max predicted aligned error for interactions e.g. 10",
"hidden": true
},
"af2_max_pae_overall": {
"type": "number",
"description": "Max predicted aligned error for all chains e.g. 10",
"hidden": true
},
"af2_max_pae_binder": {
"type": "number",
"description": "Max predicted aligned error for binder e.g. 5",
"hidden": true
},
"af2_max_pae_target": {
"type": "number",
"description": "Max predicted aligned error for target e.g. 5",
"hidden": true
},
"af2_min_plddt_overall": {
"type": "number",
"description": "Min average pLDDT score for target and binder chains e.g. 90",
"hidden": true
},
"af2_min_plddt_binder": {
"type": "number",
"description": "Min pLDDT score required for binder e.g. 85",
"hidden": true
},
"af2_min_plddt_target": {
"type": "number",
"description": "Min pLDDT score required for target e.g 90",
"hidden": true
},
"af2_max_rmsd_overall": {
"type": "number",
"description": "Max RMSD when all chains are aligned e.g. 2",
"hidden": true
},
"af2_max_rmsd_binder_bndaln": {
"type": "number",
"description": "Max binder RMSD when binder chains are aligned e.g. 1",
"hidden": true
},
"af2_max_rmsd_binder_tgtaln": {
"type": "number",
"description": "Max binder RMSD when target chains are aligned e.g. 2",
"hidden": true
},
"af2_max_rmsd_target": {
"type": "number",
"description": "Max target RMSD when target chains are aligned e.g. 2",
"hidden": true
},
"boltz_max_rmsd_overall": {
"type": "number",
"description": "Max RMSD between all chains of Boltz-2 prediction and input design. e.g. 2",
"hidden": true
},
"boltz_max_rmsd_binder": {
"type": "number",
"description": "Max RMSD between binder chains of Boltz-2 prediction and input design. e.g. 1",
"hidden": true
},
"boltz_max_rmsd_target": {
"type": "number",
"description": "Max RMSD between target chains of Boltz-2 prediction and input design. e.g. 1",
"hidden": true
},
"boltz_min_conf_score": {
"type": "number",
"description": "Minimum confidence score e.g. 0.85",
"hidden": true
},
"boltz_min_ptm": {
"type": "number",
"description": "Minimum predicted TM-score e.g. 0.7",
"hidden": true
},
"boltz_min_ptm_binder": {
"type": "number",
"description": "Minimum predicted TM-score of binder chain e.g. 0.8",
"hidden": true
},
"boltz_min_ptm_target": {
"type": "number",
"description": "Minimum predicted TM-score of target chain e.g. 0.9",
"hidden": true
},
"boltz_min_ptm_interface": {
"type": "number",
"description": "Minimum predicted TM-score of binder-target interface e.g. 0.65",
"hidden": true
},
"boltz_min_plddt": {
"type": "number",
"description": "Minimum pLDDT score e.g. 0.85",
"hidden": true
},
"boltz_min_plddt_interface": {
"type": "number",
"description": "Minimum pLDDT score of the binder-target interface e.g. 0.8",
"hidden": true
},
"boltz_max_pde": {
"type": "number",
"description": "Maximum predicted distance error e.g. 10",
"hidden": true
},
"boltz_max_pde_interface": {
"type": "number",
"description": "Maximum predicted distance error for the binder-target interface e.g 12",
"hidden": true
},
"boltz_min_ipSAE_min": {
"type": "number",
"description": "Minimum value allowed for the minimum interaction Prediction Score from Aligned Errors (ipSAE) of target and binder chains (0 to 1)",
"hidden": true
},
"boltz_min_LIS": {
"type": "number",
"description": "Minimum Local Interaction Score (LIS)",
"hidden": true
},
"boltz_min_pDockQ2_min": {
"type": "number",
"description": "Minimum value allowed for the minimum predicted DockQ Score v2 of target and binder chains (0 to 1)",
"hidden": true
},
"boltz_max_pae_interaction": {
"type": "number",
"description": "Maximum predicted aligned error at interaction interfaces (0 to ~30 Angstroms)",
"hidden": true
},
"pr_min_helices": {
"type": "integer",
"description": "Minimum number of alpha-helices in predicted structure",
"hidden": true
},
"pr_max_helices": {
"type": "integer",
"description": "Maximum number of alpha-helices in predicted structure",
"hidden": true
},
"pr_min_strands": {
"type": "integer",
"description": "Minimum number of beta-strands in predicted structure",
"hidden": true
},
"pr_max_strands": {
"type": "integer",
"description": "Maximum number of beta-strands in predicted structure",
"hidden": true
},
"pr_min_total_ss": {
"type": "integer",
"description": "Minimum total secondary structure elements (α-helices + β-strands) in predicted structure",
"hidden": true
},
"pr_max_total_ss": {
"type": "integer",
"description": "Maximum total secondary structure elements (α-helices + β-strands) in predicted structure",
"hidden": true
},
"pr_min_rog": {
"type": "number",
"description": "Minimum radius of gyration (Å) of predicted structure",
"hidden": true
},
"pr_max_rog": {
"type": "number",
"description": "Maximum radius of gyration (Å) of predicted structure",
"hidden": true
},
"pr_min_intface_bsa": {
"type": "number",
"description": "Minimum buried surface area (Ų) at the binding interface",
"hidden": true
},
"pr_min_intface_shpcomp": {
"type": "number",
"description": "Minimum shape complementarity of interface (0-1 scale; 1 is optimal)",
"hidden": true
},
"pr_min_intface_hbonds": {
"type": "integer",
"description": "Minimum number of hydrogen bonds at the interface",
"hidden": true
},
"pr_max_intface_unsat_hbonds": {
"type": "integer",
"description": "Maximum number of buried, unsatisfied hydrogen bonds at the interface",
"hidden": true
},
"pr_max_intface_deltag": {
"type": "number",
"description": "Maximum solvation free energy gain at interface (Rosetta Energy Units; lower is better)",
"hidden": true
},
"pr_max_intface_deltagtobsa": {
"type": "number",
"description": "Maximum ratio of delta-G to buried surface area",
"hidden": true
},
"pr_min_intface_packstat": {
"type": "number",
"description": "Minimum packing quality of the interface (0-1 scale; higher is better)",
"hidden": true
},
"pr_max_tem": {
"type": "number",
"description": "Maximum total energy metric score (Rosetta Energy Units; lower indicates more stable designs)",
"hidden": true
},
"pr_max_surfhphobics": {
"type": "number",
"description": "Maximum percentage of hydrophobic residues exposed on the surface",
"hidden": true
},
"pr_max_sap": {
"type": "number",
"description": "Maximum mean residue Spatial Aggregation Propensity for monomer/binder (solubility prediction; lower is better)",
"hidden": true
},
"pr_max_sap_complex": {
"type": "number",
"description": "Maximum mean residue Spatial Aggregation Propensity for binder in complex (solubility prediction; lower is better)",
"hidden": true
},
"seq_min_ext_coef": {
"type": "number",
"description": "Minimum extinction coefficient at 280nm (M⁻¹cm⁻¹)",
"hidden": true
},
"seq_max_ext_coef": {
"type": "number",
"description": "Maximum extinction coefficient at 280nm (M⁻¹cm⁻¹)",
"hidden": true
},
"seq_min_pi": {
"type": "number",
"description": "Minimum isoelectric point (pI) of the sequence",
"hidden": true
},
"seq_max_pi": {
"type": "number",
"description": "Maximum isoelectric point (pI) of the sequence",
"hidden": true
}
}
},
"cluster_parameters": {
"title": "Cluster Parameters",
"type": "object",
"description": "The cluster parameters may need adjusting depending on your HPC setup and available hardware. You must ensure that the paths to the containers and models for RFdiffusion, AlphaFold2 and Boltz-2 are valid and contain the expected files.",
"default": "",
"properties": {
"rfd_models": {
"type": "string",
"format": "directory-path",
"description": "Path to the RFdiffusion model checkpoints.",
"hidden": true
},
"af2_models": {
"type": "string",
"format": "directory-path",
"description": "Path to the AlphaFold2 databases.",
"hidden": true
},
"boltz_models": {
"type": "string",
"format": "directory-path",
"description": "Path to the Boltz-2 models.",
"hidden": true
},
"gpu_model": {
"type": "string",
"default": "A30",
"description": "GPU model to request, e.g., 'A30'.",
"hidden": true
},
"gpu_queue": {
"type": "string",
"description": "GPU queue name or partition (if applicable, e.g. 'gpuq')",
"hidden": true
},
"gpus": {
"type": "integer",
"default": 4,
"description": "Number of GPUs to request.",
"hidden": true
},
"cpus": {
"type": "integer",
"default": 24,
"description": "Number of CPUs requested for CPU-only jobs",
"hidden": true
},
"cpus_per_gpu": {
"type": "integer",
"default": 8,
"description": "Number of CPUs requested per GPU",
"hidden": true
},
"memory_gpu": {
"type": "string",
"default": "24GB",
"description": "Memory requested for GPU jobs",
"hidden": true
},
"memory_cpu": {
"type": "string",
"default": "24GB",
"description": "Memory requested for CPU-only jobs",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/essential_parameters"
},
{
"$ref": "#/definitions/mode_specific_parameters"
},
{
"$ref": "#/definitions/workflow_advanced_parameters"
},
{
"$ref": "#/definitions/bindcraft_advanced_parameters"
},
{
"$ref": "#/definitions/rfdiffusion_advanced_parameters"
},
{
"$ref": "#/definitions/proteinmpnn_fastrelax_parameters"
},
{
"$ref": "#/definitions/full_atom_mpnn_parameters"
},
{
"$ref": "#/definitions/prediction_advanced_parameters"
},
{
"$ref": "#/definitions/filtering_parameters"
},
{
"$ref": "#/definitions/cluster_parameters"
}
]
}