EUVIMEDEUVIMED entdecken
Crossref

Benchmarking and Experimental Validation of Machine Learning Strategies for Enzyme Engineering

Zishuo Zeng, Jiao Jin, Rufang Xu, Yuzhen Wu, Xiaozhou Luo iD

Journal of Chemical Information and Modeling · 09.11.2026 · 66 (21) · 14038-14052

DOI: 10.1021/acs.jcim.6c01200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 28.10.2026. Verfasst von Zishuo Zeng und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Quantitative Synthetic Biology, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese …. Hauptthemen laut MEDLINE: Machine Learning, Protein Engineering, Enzymes. Die Arbeit nennt 62 Literaturangaben. Gefördert von: Guangdong S&T Program, National Key R&D Program of China, National Natural Science Foundation of China (NSFC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enzyme-directed evolution increasingly relies on computational tools to prioritize mutations, yet their practical value is difficult to assess because kinetic data are often aggregated across heterogeneous assay conditions, inflating apparent generalization. Here we introduce EnzyArena, a curated benchmark in which kinetic parameters (kcat, Km, or kcat/Km) are grouped by experimental campaign and measured under matched conditions, thereby minimizing confounders such as pH, temperature, reaction, and batch. Using EnzyArena, we systematically evaluate 20 models spanning four widely used strategies for guiding enzyme evolution: protein–ligand binding affinity prediction, protein stability prediction, zero-shot fitness prediction and enzyme kinetic parameters prediction. Across subsets derived from public databases and 25 literature-derived mutagenesis data sets, most models exhibit weak, fragile, or inconsistent correlation with measured functional outcomes. Kinetic-parameter predictors perform strongly on database-derived subsets but lose their advantage on literature-derived mutagenesis data sets, whereas zero-shot predictors show more consistent generalization. A simple consensus of multiple zero-shot models further improves the precision of identifying beneficial mutants in retrospective analyses. We prospectively validated these findings in a wet-lab campaign (150 mutants) comparing random mutants, UniKP-prioritized mutants, and ESM-1v-prioritized mutants (representing supervised kinetic parameters prediction and zero-shot fitness prediction, respectively), where ESM-1v achieved the highest utility and UniKP underperformed the random baseline. Together, this study establishes realistic baselines for computational mutant prioritization and indicates that zero-shot strategies provide the most consistent, although still modest, performance among the approaches evaluated.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningProtein EngineeringEnzymesKineticsBenchmarkingMutation

Substanzen

Enzymes

Autor:innen und Institutionen

  • State Key Laboratory of Quantitative Synthetic Biology, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen518055, China.
  • Synceres Biosciences Co. Ltd. , 1100 Huanli Road, Guangming District, Shenzhen, Guangdong518083, China.
  • School of Biomedical and Pharmaceutical Sciences, Guangdong University of Technology, Guangzhou510006, China.

ORCID-Profile: Xiaozhou Luo

Förderung

  • Guangdong S&T Program
  • National Key R&D Program of China
  • National Natural Science Foundation of China (NSFC)
  • Shenzhen Medical Research Fund
  • SlAT Distinguished Young Scholars
  • Shenzhen Science and Technology Program

Zitieren

APA

Zeng, Z., Jin, J., Xu, R., Wu, Y., & Luo, X. (2026). Benchmarking and Experimental Validation of Machine Learning Strategies for Enzyme Engineering. Journal of Chemical Information and Modeling, 66(21), 14038-14052. https://doi.org/10.1021/acs.jcim.6c01200

Vancouver

Zeng Z, Jin J, Xu R, Wu Y, Luo X. Benchmarking and Experimental Validation of Machine Learning Strategies for Enzyme Engineering. Journal of Chemical Information and Modeling. 2026;66(21):14038-14052. doi:10.1021/acs.jcim.6c01200

BibTeX
@article{Zeng2026,
  author = {Zeng, Zishuo and Jin, Jiao and Xu, Rufang and Wu, Yuzhen and Luo, Xiaozhou},
  title = {Benchmarking and Experimental Validation of Machine Learning Strategies for Enzyme Engineering},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {21},
  pages = {14038--14052},
  doi = {10.1021/acs.jcim.6c01200}
}
Kostenlos starten →