Skip to main content
DNA Base Contact Quality
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/dna_base_contact_quality_constraint.py
View source
Constraint contributors
Score protein-DNA base contact quality from a predicted complex PDB. Resolves (reuses or predicts) a protein-operator complex PDB per candidate tuple, then scores base-specific contact quality directly from heavy-atom geometry. The score is a weighted combination of bidentate deficit (0.35), base-contact deficit (0.30), unique-residue deficit (0.15), and a diversity deficit weighted by config.diversity_bonus_weight (default 0.3), all in [0, 1] where 0 is best.

​
API Reference

ConfigDNABaseContactQualityConfig Source
Config for geometry-based DNA base contact quality scoring.Scores protein-DNA complexes based on the quality of base-specific contacts, measured directly from heavy-atom distances in a predicted complex PDB without requiring Rosetta relaxation. Inherits the structure-prediction tool selection and per-tool configs from StructureBasedConstraintConfig.
​
number
default:"3.5"
Heavy-atom distance cutoff for base contacts.
​
integer
default:"2"
Target bidentate-contact count (one residue H-bonding 2+ atoms on a base); 0 component when met.
​
integer
default:"8"
Target number of polar sidechain-to-base contacts.
​
integer
default:"4"
Target number of unique protein residues contacting bases.
​
number
default:"0.3"
Weight of the diversity term rewarding base-specific readout over nonspecific ARG/LYS charge.
​
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_binder
​
ESMFoldConfig
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 contact-quality metadata (n_base_contacts, n_bidentate, n_unique_residues, n_specific_residues, pct_arg, diversity_score, per-component deficits, and pdb_path). Candidates whose structure could not be resolved, or whose PDB is empty/unparseable, receive MAX_ENERGY.

​
Usage

python

​
Metadata