Article
Rapid directed evolution guided by protein language models and epistatic interactions.
Science (New York, N.Y.) - 7 May 2026
Tran Vincent Q, Nemeth Matthew, Bartie Liam J, Chandrasekaran Sita S, Fanton Alison, Moon Hyungseok C, Hie Brian L, Konermann Silvana, Hsu Patrick D
Abstract excerpt
Protein engineering is limited by the inefficient search through a high-dimensional sequence space to find combinations of synergistic mutations. Traditional approaches use stepwise mutation stacking, whereas machine learning methods require extensive datasets or multiple experimental rounds and are bottlenecked by costly, length-limited gene synthesis. We present MULTI-evolve (where MULTI stands for...
Read the complete abstract on PubMedTopics
Share this publication in a Topic to start or enrich a Post.