License: This constraint can use multiple tools, each under its own license. See the Tools Used tab and each tool’s page for license details.
This constraint is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.
evo-design/proto-language/proto_language/constraint/protein_structure/dbp_design_metrics_constraint.py
[0, 1].
Resolves (reuses or predicts) one protein-operator complex PDB per candidate
tuple, scores it with the heavy dbp_design PyRosetta metric suite, and
converts the extracted metrics into a weighted-composite penalty where 0
is best and 1 is worst. When evaluation fails and fail_hard is
disabled, returns failure_score and records the error in metadata.
API Reference
Config for the dbp-design-metrics constraint.Predicts (or reuses) a protein-DNA complex and scores it with the heavy
dbp_design metric suite (PyRosetta H-bond typing, compactness, interface
ddG / CMS / shape complementarity / packstat / buried unsats /
RotamerBoltzmann, and notebook-aligned charge ratios). The score is the
weight-normalized sum of per-metric penalties clamped to [0, 1], where
0 means every threshold is satisfied and 1 means none are.string
default:""
Path to local dbp_design repository root; required (no default).
string
default:"2b_design_mpnn/count_hbond_types.py"
Relative path to count_hbond_types.py script.
string
default:"2b_design_mpnn/compactness_filter.py"
Relative path to compactness_filter.py script.
string
default:""
Optional site-packages path containing pyrosetta when not in the active env.
boolean
default:"False"
If true, raise on dbp metric tool failures instead of returning failure_score.
number
default:"1.0"
Penalty score returned when dbp metric evaluation fails in fail-soft mode.
string
Path to calibrated ddG/CMS sigmoid prefilter equation file; None skips the prefilter.
string
Path to prefilter log-prob cutoff file; used when prefilter_cut is None.
number
Explicit prefilter log-prob cutoff; when None it is loaded from prefilter_cut_path.
number
default:"-0.5"
HBond energy cutoff passed to count_hbond_types.
number
default:"10.0"
Minimum weighted base score required.
number
default:"0.0"
Minimum weighted phosphate score required.
number
default:"1.0"
Minimum weighted bidentate score required.
integer
default:"0"
Minimum backbone-phosphate H-bond contacts.
integer
default:"0"
Minimum per-SSE contacts from compactness filter (default makes this penalty component inactive).
integer
default:"1000000"
Maximum allowed loop length from compactness filter (default makes this penalty component inactive).
boolean
default:"False"
Require motif_in_rec_helix metric to be true.
boolean
default:"False"
Require rifres_in_rec_helix metric to be true.
number
default:"2.0"
Maximum allowed buried unsatisfied polar atoms at the interface.
number
default:"0.65"
Minimum interface shape complementarity score (Sc).
number
default:"0.55"
Minimum packstat score for foldability/packing quality.
number
default:"0.15"
Minimum max RotamerBoltzmann-style score over interface RKQE residues.
number
default:"0.1"
Minimum avg_top_two_rboltz score.
number
default:"-15.0"
Maximum allowed interface ddG (more negative is better).
number
default:"225.0"
Minimum required contact molecular surface (CMS).
number
default:"-10.0"
Lower bound of the allowed net_charge_over_sasa window.
number
default:"10.0"
Upper bound of the allowed net_charge_over_sasa window.
number
default:"-0.06"
Maximum allowed ddg/contact_molecular_surface ratio.
number
default:"0.5"
Normalized distance from threshold at which heavy penalties reach full penalty.
number
default:"1.0"
Weight for base score penalty component.
number
default:"1.0"
Weight for phosphate score penalty component.
number
default:"1.0"
Weight for bidentate score penalty component.
number
default:"1.0"
Weight for backbone phosphate contact penalty.
number
default:"1.0"
Weight for compactness contact penalty.
number
default:"1.0"
Weight for loop-length penalty component.
number
default:"1.0"
Weight for motif-in-recognition-helix check.
number
default:"1.0"
Weight for rifres-in-recognition-helix check.
number
default:"1.0"
Weight for buried-unsatisfied-polars penalty.
number
default:"1.0"
Weight for shape-complementarity penalty.
number
default:"1.0"
Weight for packstat penalty.
number
default:"1.0"
Weight for max-RKQE RotamerBoltzmann preorganization penalty.
number
default:"1.0"
Weight for avg-top-two RotamerBoltzmann preorganization penalty.
number
default:"2.0"
Weight for ddG notebook-alignment penalty.
number
default:"2.0"
Weight for CMS notebook-alignment penalty.
number
default:"2.0"
Weight for net_charge_over_sasa notebook-alignment penalty.
number
default:"2.0"
Weight for ddg_over_cms notebook-alignment penalty.
number
default:"2.0"
Maximum allowed MPNN score when available in candidate metadata.
number
default:"0.0"
Penalty used when MPNN score is unavailable in candidate metadata.
number
default:"1.0"
Weight for MPNN score threshold penalty.
enum
default:"alphafold3"
Predictor for the protein-DNA complex; must be DNA-capable (alphafold3/boltz2/protenix).Options:
esmfold, esmfold2, alphafold3, boltz2, chai1, protenix, alphafold2, alphafold2_binderESMFoldConfig
Configuration for ESMFold structure prediction.
ESMFold2Config
Configuration for ESMFold2 structure prediction.
AlphaFold3Config
Configuration for AlphaFold3 structure prediction.
Boltz2Config
Configuration for Boltz2 structure prediction.
Chai1Config
Configuration for Chai1 structure prediction.
ProtenixConfig
Configuration for Protenix structure prediction.
AlphaFold2Config
Configuration for the general AlphaFold2 multimer structure predictor.
AlphaFold2BinderStructureConfig
Configuration for the AF2 binder-design backend.
ReturnsConstraintOutput
Per-candidate score in [0, 1] (lower is
better) with dbp_metrics, dbp_penalties, pdb_path (and
dbp_metrics_error on soft failure) metadata.Usage
python