Improving <i>de novo</i> Protein Binder Design with Deep Learning
Nathaniel R. Bennett(University of Washington), Brian Coventry(Howard Hughes Medical Institute), Inna Goreshnik(University of Washington), Buwei Huang(University of Washington), Aza Allen(University of Washington), Dionne Vafeados(University of Washington), Ying Po Peng(University of Washington), Justas Dauparas(University of Washington), Minkyung Baek(University of Washington), Lance Stewart(University of Washington), Frank DiMaio(University of Washington), Steven De Munck(Ghent University), Savvas N. Savvides(Ghent University), David Baker(Howard Hughes Medical Institute)
Cited by 12Open Access
Abstract
Abstract 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.
Related Papers
No related papers found
Powered by citation graph analysis