Improving de novo Protein Binder Design with Deep Learning

We explore the improvement of energy-based protein binder design using deep learning. We find that using AlphaFold2 or RoseTTAFold to assess the probability that a designed sequence adopts the designed monomer structure, and the probability that this structure binds the target as designed, increases design success rates nearly 10-fold. We find further that sequence design using ProteinMPNN rather than Rosetta considerably increases computational efficiency. ### Competing Interest Statement N.B., B.C., I.G., L.S., D.B., A.A., and D.V. are co-inventors on a provisional patent application (application not yet submitted) that incorporates discoveries described in this manuscript.