Inverse folding models can predict antibody-antigen binding affinities with higher accuracy by correcting with predictions from unbound state

Summary

Zero-shot prediction of antibody-antigen binding affinity by inverse folding models by correcting for predictions made of the antibody in the unbound state (PEGS Europe 2025, Paolo Marcatili).

See also

• Zero-shot protein stability prediction using inverse folding models can be improved by subtracting predictions from residue in isolation