Improving de novo protein binder design with deep learning

Abstract

Recently it has become possible to de novo design high affinity protein binding proteins from target structural information alone. There is, however, considerable room for improvement as the overall design success rate is low. Here, we explore the augmentation 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.

Document Details

Document Type
Pub Defense Publication
Publication Date
May 06, 2023
Source ID
10.1038/s41467-023-38328-5

Entities

People

  • Aza Allen
  • Brian Coventry
  • Buwei Huang
  • David Baker
  • Dionne Vafeados
  • Frank DiMaio
  • Inna Goreshnik
  • J. Dauparas
  • Lance Stewart
  • Minkyung Baek
  • N. Bennett
  • Savvas N Savvides
  • Steven De Munck
  • Ying Po Peng

Organizations

  • Flanders Institute for Biotechnology
  • Howard Hughes Medical Institute
  • Microsoft
  • Research Foundation - Flanders
  • United States Department of Defense

Tags

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Molecular and Cellular Biochemistry
  • Reinforced Composite Materials

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks