Justas Dauparas; Ivan Anishchenko; Nathaniel R. Bennett; Hua Bai; Robert J. Ragotte; Lukas F. Milles; Basile I. M. Wicky; Alexis Courbet; Robbert J. de Haas; Neville P. Bethel; Philip J. Y. Leung; Timothy F. Huddy; Samuel J. Pellock; Doug Tischer; F. Chan; Brian Koepnick; Hannah Nguyen; Alex Kang; Banumathi Sankaran; Asim K. Bera; Neil P. King; David Baker · 2022 · Science
Paper
Although deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Here, we describe a deep learning-based protein sequence design method, ProteinMPNN, that has outstanding performance in both in silico and experimental tests. On native protein backbones, ProteinMPNN has a sequence recovery of 52.4% compared with 32.9% for Rosetta. The amino acid sequence at different positions can be coupled between single or multiple chains, enabling application to a wide range of current protein design challenges. We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo-electron microscopy, and functional studies by rescuing previously failed designs, which were made using Rosetta or AlphaFold, of protein monomers, cyclic homo-oligomers, tetrahedral nanoparticles, and target-binding proteins.
Analysis
ProteinMPNN is a deep learning method for protein sequence design that outperforms traditional methods like Rosetta in sequence recovery and is applicable to diverse design challenges.
Discovery
Hoda M. Hammad; Anna M. Duraj‐Thatte
Jakob Agamia; Martin Zacharias
Yap V; Xu P; Mak FS; Foo K; Kang C; Anbazhagan P; Xu W
Hun Hee Cho; Tae Hyung Kim; Seung Gyu Hwang; Hongchul Shin
Bruce J. Wittmann; Tessa Alexanian; Craig Bartling; Jacob Beal; Adam Clore; James Diggans; Kevin Flyangolts; Bryan T. Gemler; Tom Mitchell; Steven T. Murphy; Nicole E. Wheeler; Eric Horvitz
Guohao Zhang; Chuanyang Liu; Jiajie Lu; Shaowei Zhang; Lingyun Zhu
Source record