Treffer: Rapid in silico directed evolution by a protein language model with EVOLVEpro.

Title:
Rapid in silico directed evolution by a protein language model with EVOLVEpro.
Authors:
Jiang K; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA.; Department of Bioengineering Massachusetts Institute of Technology, Cambridge, MA, USA., Yan Z; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA., Di Bernardo M; Whitehead Institute Massachusetts Institute of Technology, Cambridge, MA, USA., Sgrizzi SR; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA., Villiger L; Department of Dermatology and Allergology Kantonspital St. Gallen, St. Gallen, Switzerland., Kayabolen A; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA., Kim BJ; Koch Institute for Integrative Cancer Research at MIT Massachusetts Institute of Technology, Cambridge, MA, USA., Carscadden JK; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA., Hiraizumi M; Department of Chemistry and Biotechnology, Graduate School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan., Nishimasu H; Department of Chemistry and Biotechnology, Graduate School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan.; Structural Biology Division, Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo, Japan.; Inamori Research Institute for Science, 620 Suiginya-cho, Shimogyo-ku, Kyoto, Japan., Gootenberg JS; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA., Abudayyeh OO; Department of Medicine Division of Engineering in Medicine Brigham and Women's Hospital Harvard Medical School, Boston, MA, USA.; Gene and Cell Therapy Institute Mass General Brigham, Cambridge, MA, USA.; Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School, Boston, MA, USA.
Source:
Science (New York, N.Y.) [Science] 2025 Jan 24; Vol. 387 (6732), pp. eadr6006. Date of Electronic Publication: 2025 Jan 24.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: American Association for the Advancement of Science Country of Publication: United States NLM ID: 0404511 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1095-9203 (Electronic) Linking ISSN: 00368075 NLM ISO Abbreviation: Science Subsets: MEDLINE
Imprint Name(s):
Publication: : Washington, DC : American Association for the Advancement of Science
Original Publication: New York, N.Y. : [s.n.] 1880-
MeSH Terms:
Directed Molecular Evolution*/methods , Proteins*/genetics , Proteins*/chemistry , Deep Learning*, Computer Simulation ; Gene Editing ; Protein Engineering/methods ; Software
Grant Information:
R21 AI149694 United States AI NIAID NIH HHS; R01 EB031957 United States EB NIBIB NIH HHS; R01 AG074932 United States AG NIA NIH HHS; R01 GM148745 United States GM NIGMS NIH HHS; R56 HG011857 United States HG NHGRI NIH HHS
Substance Nomenclature:
0 (Proteins)
Entry Date(s):
Date Created: 20241121 Date Completed: 20250123 Latest Revision: 20250722
Update Code:
20250722
DOI:
10.1126/science.adr6006
PMID:
39571002
Database:
MEDLINE

Weitere Informationen

Directed protein evolution is central to biomedical applications but faces challenges such as experimental complexity, inefficient multiproperty optimization, and local maxima traps. Although in silico methods that use protein language models (PLMs) can provide modeled fitness landscape guidance, they struggle to generalize across diverse protein families and map to protein activity. We present EVOLVEpro, a few-shot active learning framework that combines PLMs and regression models to rapidly improve protein activity. EVOLVEpro surpasses current methods, yielding up to 100-fold improvements in desired properties. We demonstrate its effectiveness across six proteins in RNA production, genome editing, and antibody binding applications. These results highlight the advantages of few-shot active learning with minimal experimental data over zero-shot predictions. EVOLVEpro opens new possibilities for artificial intelligence-guided protein engineering in biology and medicine.