EUVIMEDEUVIMED entdecken
Open Access

Rapid directed evolution guided by protein language models and epistatic interactions

Vincent Q Tran iD, Matthew Nemeth iD, Liam J Bartie, Sita S Chandrasekaran, Alison Fanton iD, Hyungseok C Moon iD, Brian L Hie iD, Silvana Konermann iD, Patrick D Hsu iD

Science · 07.05.2026 · 392 (6798)

DOI: 10.1126/science.aea1820 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, erschienen am 07.05.2026. Verfasst von Vincent Q Tran und 8 weiteren Autor:innen. Beteiligte Einrichtung: Arc Institute, Palo Alto, CA, USA. Hauptthemen laut MEDLINE: Directed Molecular Evolution, Epistasis, Genetic, Protein Engineering, Proteins. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Science Foundation Graduate Research Fellowship Program, Arc Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 model-guided, universal, targeted installation of multimutants), a rapid evolution framework that systematically engineers multimutants. Our approach combines protein language models or existing functional data with epistatic modeling to predict synergistic combinations. Proposed multimutants are built through MULTI-assembly, a mutagenesis method enabling high-efficiency assembly across multikilobase sequences. Applying MULTI-evolve to three proteins achieved up to 10-fold improvements with a single round of machine learning–guided directed evolution. MULTI-evolve provides a streamlined approach for end-to-end, multimutant engineering for a broad range of protein types and functions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Directed Molecular EvolutionEpistasis, GeneticProtein EngineeringProteinsMachine LearningMutationMutagenesis

Substanzen

Proteins

Autor:innen und Institutionen

  • Arc Institute, Palo Alto, CA, USA.
  • Department of Chemistry, University of California, Berkeley, Berkeley, CA, USA.
  • Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA.
  • San Francisco Graduate Program in Bioengineering, University of California, Berkeley, Berkeley, CA, USA.
  • Department of Chemical Engineering, Stanford University, Stanford, CA, USA.
  • Stanford Data Science, Stanford University, Stanford, CA, USA.

ORCID-Profile: Vincent Q Tran, Matthew Nemeth, Alison Fanton, Hyungseok C Moon, Brian L Hie, Silvana Konermann, Patrick D Hsu

Förderung

  • NIGMS NIH HHS
  • National Science Foundation Graduate Research Fellowship Program
  • Arc Institute

Zitieren

APA

Tran, V. Q., Nemeth, M., Bartie, L. J., Chandrasekaran, S. S., Fanton, A., Moon, H. C., Hie, B. L., Konermann, S., & Hsu, P. D. (2026). Rapid directed evolution guided by protein language models and epistatic interactions. Science, 392(6798). https://doi.org/10.1126/science.aea1820

Vancouver

Tran VQ, Nemeth M, Bartie LJ, Chandrasekaran SS, Fanton A, Moon HC, et al. Rapid directed evolution guided by protein language models and epistatic interactions. Science. 2026;392(6798). doi:10.1126/science.aea1820

BibTeX
@article{Tran2026,
  author = {Tran, Vincent Q and Nemeth, Matthew and Bartie, Liam J and Chandrasekaran, Sita S and Fanton, Alison and Moon, Hyungseok C and Hie, Brian L and Konermann, Silvana and Hsu, Patrick D},
  title = {Rapid directed evolution guided by protein language models and epistatic interactions},
  journal = {Science},
  year = {2026},
  volume = {392},
  number = {6798},
  doi = {10.1126/science.aea1820}
}
Kostenlos starten →