Engineering highly active nuclease enzymes with machine learning and high-throughput screening
Cell Systems · 2025-03 · 16 (3) · 101236
DOI: 10.1016/j.cels.2025.101236 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cell Systems, 2025-03. Verfasst von Neil Thomas und 15 weiteren Autor:innen. Beteiligte Einrichtung: X, the Moonshot Factory, Mountain View, CA 94043, USA. Electronic address: thomas.a.neil@gmail.com. Hauptthemen laut MEDLINE: Machine Learning, High-Throughput Screening Assays, Protein Engineering. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 140 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Optimizing enzymes to function in novel chemical environments is a central goal of synthetic biology, but optimization is often hindered by a rugged fitness landscape and costly experiments. In this work, we present TeleProt, a machine learning (ML) framework that blends evolutionary and experimental data to design diverse protein libraries, and employ it to improve the catalytic activity of a nuclease enzyme that degrades biofilms that accumulate on chronic wounds. After multiple rounds of high-throughput experiments, TeleProt found a significantly better top-performing enzyme than directed evolution (DE), had a better hit rate at finding diverse, high-activity variants, and was even able to design a high-performance initial library using no prior experimental data. We have released a dataset of 55,000 nuclease variants, one of the most extensive genotype-phenotype enzyme activity landscapes to date, to drive further progress in ML-guided design. A record of this paper's transparent peer review process is included in the supplemental information.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- X, the Moonshot Factory, Mountain View, CA 94043, USA. Electronic address: thomas.a.neil@gmail.com.
- Google DeepMind, Cambridge, MA 02142, USA. Electronic address: dbelanger@google.com.
- Triplebar, Emeryville, CA 94608, USA.
- X, the Moonshot Factory, Mountain View, CA 94043, USA.
- Google Accelerated Sciences, Mountain View, CA 94043, USA.
- Google DeepMind, Cambridge, MA 02142, USA; Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, UK. Electronic address: lcolwell@google.com.
Zitieren
APA
Thomas, N., Belanger, D., Xu, C., Lee, H., Hirano, K., Iwai, K., Polic, V., Nyberg, K. D., Hoff, K. G., Frenz, L., Emrich, C. A., Kim, J. W., Chavarha, M., Ramanan, A., Agresti, J. J., & Colwell, L. J. (2025). Engineering highly active nuclease enzymes with machine learning and high-throughput screening. Cell Systems, 16(3), 101236. https://doi.org/10.1016/j.cels.2025.101236
Vancouver
Thomas N, Belanger D, Xu C, Lee H, Hirano K, Iwai K, et al. Engineering highly active nuclease enzymes with machine learning and high-throughput screening. Cell Systems. 2025;16(3):101236. doi:10.1016/j.cels.2025.101236
BibTeX
@article{Thomas2025,
author = {Thomas, Neil and Belanger, David and Xu, Chenling and Lee, Hanson and Hirano, Kathleen and Iwai, Kosuke and Polic, Vanja and Nyberg, Kendra D and Hoff, Kevin G and Frenz, Lucas and Emrich, Charlie A and Kim, Jun W and Chavarha, Mariya and Ramanan, Abi and Agresti, Jeremy J and Colwell, Lucy J},
title = {Engineering highly active nuclease enzymes with machine learning and high-throughput screening},
journal = {Cell Systems},
year = {2025},
volume = {16},
number = {3},
pages = {101236},
doi = {10.1016/j.cels.2025.101236}
}
EUVIMED