Skip to main content
Boltz2 Binding Strength
License: Boltz-2 is open source and free for academic and commercial use under an MIT license. Please refer to the license for full terms.

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.

Go to Tool Page
evo-design/proto-language/proto_language/constraint/protein_structure/boltz_binding_strength_constraint.py
View source 
@article{passaro2025boltz2,
  title={Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction},
  author={Passaro, Saro and Corso, Gabriele and Wohlwend, Jeremy and Reveiz, Mateo and Thaler, Stephan and Somnath, Vignesh Ram and Getz, Noah and Portnoi, Tally and Roy, Julien and St{\"a}rk, Hannes and Kwabi-Addo, David and Beaini, Dominique and Jaakkola, Tommi and Barzilay, Regina},
  journal={bioRxiv},
  year={2025},
  doi={10.1101/2025.06.14.659707},
  publisher={Cold Spring Harbor Laboratory}
}

@article{wohlwend2024boltz1,
  title={Boltz-1: Democratizing Biomolecular Interaction Modeling},
  author={Wohlwend, Jeremy and Corso, Gabriele and Passaro, Saro and Reveiz, Mateo and Leidal, Ken and Swanson, Wojtek and Turnbull, Robert and Shuaibi, Muhammed and Ahdritz, Gustaf and Getz, Gad and Jaakkola, Tommi and Barzilay, Regina},
  journal={bioRxiv},
  year={2024},
  doi={10.1101/2024.11.19.624167},
  publisher={Cold Spring Harbor Laboratory}
}
Copy citation
Evaluate binding strength and quality using Boltz structure prediction. Boltz predicts protein-protein, protein-ligand, protein-DNA, and protein-RNA complex structures and returns confidence metrics (iptm, iplddt, ipde, plddt, ptm, confidence_score). Each metric is scored as a penalty in [0.0, 1.0] against configurable targets/tolerances and combined via weighted averaging; default weights are chosen by complex type.

​
API Reference

ConfigBoltzBindingStrengthConfig Source
Configuration for Boltz binding strength constraint.This class defines configuration parameters for evaluating protein-protein, protein-ligand, and protein-nucleic-acid (DNA/RNA) binding using Boltz, a biomolecular structure prediction model. A common use case is scoring a protein occupying a nucleic-acid target (e.g. a repressor bound to a DNA operator) via interface confidence. Boltz predicts complex structures and provides confidence metrics for binding quality, interface accuracy, and overall structure reliability. The constraint evaluates these metrics against target values to assess binding strength and quality.The constraint uses a penalty-based scoring system where each metric is evaluated against its target value and tolerance. Metrics are classified as “higher is better” (e.g., interface confidence scores) or “lower is better” (e.g., predicted distance errors). Penalties are combined using weighted averages, with default weights chosen by complex type (monomer, protein-ligand, or multi-chain — the latter covering both protein-protein and protein-nucleic-acid complexes).
Metric interpretation:
  • iptm/ligand_iptm/protein_iptm: Interface confidence (0-1). Higher = better binding prediction. Values >0.8 indicate confident binding interfaces.
  • complex_iplddt: Interface per-residue confidence (0-1). Higher = more reliable interface residue predictions.
  • complex_plddt: Overall structure confidence (0-1). Similar to ESMFold pLDDT.
  • ptm: Overall structural accuracy (0-1). Similar to ESMFold pTM.
  • complex_ipde/complex_pde: Predicted distance errors in Ångströms. Lower = more accurate structure. Values <3 Å indicate high accuracy.
  • confidence_score: Boltz’s aggregate confidence combining multiple factors.
​
desired_higher
object
Target values for ‘higher is better’ metrics.
​
desired_lower
object
default:"{'complex_ipde': 2.0, 'complex_pde': 2.0}"
Target values for ‘lower is better’ metrics.
​
tol_higher
object
Tolerances for higher-is-better metrics; once a value falls this far below target, penalty hits 1.0.
​
tol_lower
object
default:"{'complex_ipde': 2.0, 'complex_pde': 3.0}"
Tolerances for lower-is-better metrics (Å); once exceeding target by this much, penalty hits 1.0.
​
weights
object
Weights for combining penalties
​
include_confidence_score
boolean
default:"True"
Whether to include confidence_score in penalty calculation (adds weight 0.10)
​
return_component
enum
default:"total_penalty"
Component to return: ‘total_penalty’ (weighted combination) or specific metric nameOptions: total_penalty, iptm, ligand_iptm, protein_iptm, complex_iplddt, complex_plddt, complex_pde, complex_ipde, confidence_score, ptm
​
boltz2_config
Boltz2Config
Boltz2 configuration for structure prediction.
ReturnsConstraintOutput
Per-complex score in [0.0, 1.0] (0 = perfect binding). Predicted Boltz structure is attached to the first slot of each complex. metadata carries boltz2_binding (a list of dictionaries, one per evaluation):
  • penalty: Float overall constraint score (0.0-1.0)
  • metrics: Dictionary of all raw Boltz metrics (iptm, iplddt, etc.)
  • penalties: Dictionary of individual metric penalties before weighting

​
Usage

python
from proto_language.core import Constraint
from proto_language.constraint import boltz_binding_strength_constraint, BoltzBindingStrengthConfig

constraint = Constraint(
    inputs=[segment],
    function=boltz_binding_strength_constraint,
    function_config=BoltzBindingStrengthConfig(
        # Configure parameters here
    ),
)

scores = constraint.evaluate()

​
Metadata

PropertyValue
Keyboltz2-binding-strength
Functionboltz_binding_strength_constraint
Categoryprotein_structure
Modediscrete
Uses GPUTrue
Supported Typesdna, rna, protein, ligand