molclaw-boltz2-affinity

What problem does it solve?

Predicts the binding affinity between a target protein sequence and a small molecule SMILES using Boltz-2, enabling rapid in silico evaluation during early drug discovery.

Core Features & Use Cases

• Predicts binding probability (binary) and the affinity value (log10 IC50) for protein–ligand pairs using Boltz-2.
• Supports end-to-end workflows: retrieve the target protein sequence if needed, run Boltz-2 affinity prediction, and obtain outputs including affinity_probability_binary, affinity_pred_value, and complex_cif_file.
• Useful in hit discovery and lead optimization pipelines to rank ligands by predicted binding strength.

Quick Start

Provide a target protein sequence (or retrieve it with the integrated skill) and a SMILES string for the ligand, then run the Boltz-2 affinity predictor to obtain the affinity metrics.