Boltz2 Binding Strength

Evaluate protein-protein/protein-ligand binding using Boltz2 structure prediction

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.

---

Tools Used Tools Used Source Source Cite Cite

Go to Tool Page

proto-bio/proto-language/proto_language/constraint/protein_structure/boltz_binding_strength_constraint.py

View source

@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, and protein-nucleic acid binding using Boltz, a biomolecular structure prediction model. 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 optimized for different complex types (monomers, protein-nucleic acid, protein-protein).

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 name

Options: 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

Property	Value
Key	boltz2-binding-strength
Function	boltz_binding_strength_constraint
Category	protein_structure
Mode	discrete
Uses GPU	True
Supported Types	dna, rna, protein, ligand