All Competitors

Protein representation learning from cryo-EM density maps, transferring to flexibility, active-site, binding-affinity, and stability tasks.

Protein-ligand foundation model that maps coarse-grained structural representations directly to binding affinity, running ~26x faster than Boltz-2.

Structure-free protein-ligand binding affinity predictor built on OpenFold3 that scores potency from a protein sequence and a ligand SMILES string.

Open model that jointly predicts biomolecular structure and small-molecule binding affinity, approaching FEP+ accuracy in seconds on a single GPU.