CatESO: Differentiable Enzyme Sequence Optimization Guided by Substrate-Aware K cat Prediction
Journal of the American Chemical Society · 2026
DOI: 10.1021/jacs.6c14365 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Chemical Society, 2026. Verfasst von Zhenjia Gan und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Chemistry and Molecular Engineering, East China Normal University, Shanghai200062, China. Hauptthemen laut MEDLINE: Enzymes. Die Arbeit nennt 117 Literaturangaben. Gefördert von: The National Key Research and Development Program of China for Young Scientists, The Strategic Priority Research Program of the Chinese Academy of Sciences.
Abstract (Originalsprache)
Enzymes drive biological chemistry and offer greener routes to chemicals, materials, and medicines, yet their broader use as biocatalysts is often limited by insufficient catalytic turnover. Improving turnover is hard: measured rate constants are scarce and protein sequence space is vast. Deep learning models now predict the turnover number, Kcat, with growing accuracy, but they are typically applied after sequence generation to score or filter candidates, which separates the kinetic objective from the design itself. To bridge the gap between sequence generation and kinetic evaluation, we introduce CatESO, a differentiable sequence optimizer that enables direct, gradient-guided design of substrate-specific catalytic turnover. By backpropagating through a cross-modal Kcat predictor under continuous sequence relaxation, CatESO co-optimizes predicted catalytic activity, evolutionary plausibility, and structural integrity in one end-to-end framework, using ESM-2 and ESMFold to keep designs evolutionarily plausible and foldable. Across seven stringent, out-of-distribution enzymes spanning EC classes 1–7, CatESO raised model-predicted Kcat for many designs, with a median predicted fold change of 1.52, while every variant retained a pLDDT above 70. Against the RFdiffusion3-LigandMPNN pipeline and ZymCtrl, CatESO struck a better balance between predicted activity and structural confidence. By making substrate-conditioned kinetic objectives differentiable, CatESO carries differentiable protein design beyond structure- and binding-centered goals to enzyme catalytic function, giving a general route to function-oriented enzyme engineering.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Chemistry and Molecular Engineering, East China Normal University, Shanghai200062, China.
- NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai200062, China.
- Department of Chemistry, New York University, New York, New York10003, United States.
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR999077, China.
- College of Computer Science and Technology, Zhejiang University, Hangzhou310027, China.
- Shanghai Institute for Biomedical and Pharmaceutical Technologies, Fudan University, Shanghai200237, China.
ORCID-Profile: John Z H Zhang
Förderung
- The National Key Research and Development Program of China for Young Scientists
- The Strategic Priority Research Program of the Chinese Academy of Sciences
Zitieren
APA
Gan, Z., Xu, Y., Xu, J., Wu, Z., Huang, J., Yin, J., Chen, G., & Zhang, J. Z. H. (2026). CatESO: Differentiable Enzyme Sequence Optimization Guided by Substrate-Aware K cat Prediction. Journal of the American Chemical Society. https://doi.org/10.1021/jacs.6c14365
Vancouver
Gan Z, Xu Y, Xu J, Wu Z, Huang J, Yin J, et al. CatESO: Differentiable Enzyme Sequence Optimization Guided by Substrate-Aware K cat Prediction. Journal of the American Chemical Society. 2026. doi:10.1021/jacs.6c14365
BibTeX
@article{Gan2026,
author = {Gan, Zhenjia and Xu, Yuzhi and Xu, Junde and Wu, Zhihao and Huang, Juping and Yin, Jiabin and Chen, Guangyong and Zhang, John Z H},
title = {CatESO: Differentiable Enzyme Sequence Optimization Guided by Substrate-Aware K cat Prediction},
journal = {Journal of the American Chemical Society},
year = {2026},
doi = {10.1021/jacs.6c14365}
}
EUVIMED