UniKineG: Unified-Coordinate Geometric Graphs Enable Robust Enzyme Kinetic Prediction
International Journal of Molecular Sciences · 2026
DOI: 10.3390/ijms27041731 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2026. Verfasst von Xueyu Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China. Hauptthemen laut MEDLINE: Enzymes, Molecular Docking Simulation. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Province-Local Collaborative Innovation Project, Zhejiang Province Local Collaborative Innovation Project.
Abstract (Originalsprache)
Enzyme kinetic parameters (kcat, Km, and kcat/Km) are fundamental for quantifying catalytic efficiency and substrate specificity in biochemistry and drug discovery. However, experimental determination is resource intensive, and accurate prediction remains a persistent challenge due to the complex spatial nature of catalysis. In this paper, we present UniKineG, a novel deep learning framework that redefines kinetic prediction by modeling the explicit spatial state of enzyme–substrate complexes. Unlike conventional methods that treat proteins and ligands as isolated modalities, UniKineG employs molecular docking to embed both entities into a unified 3D coordinate system. Within this shared geometric context, we utilize a heterogeneous graph neural network integrated with geometric vector perceptrons (GVPs) to capture intricate vector-based interactions, such as directional hydrogen bonds, hydrophobic contacts, and electrostatic complementarity. This structure-based approach confers exceptional robustness: UniKineG effectively overcomes the dependency on high-sequence homology, demonstrating superior generalization on out-of-distribution (OOD) datasets encompassing both unseen enzyme sequences and diverse substrate scaffolds. Consistently outperforming state-of-the-art predictors, UniKineG achieves high-precision predictions. This work establishes a solid foundation for understanding enzyme–small molecule interactions in 3D space and offers a transformative tool for computational enzymology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China.
- State Key Laboratory of Food Science and Resources, School of Food Science and Technology, Jiangnan University, Wuxi 214122, China.
- Shaoxing Key Laboratory of Traditional Fermentation Food and Human Health, Shaoxing Industrial Technology Research Institute, Jiangnan University, Shaoxing 312000, China.
Förderung
- National Natural Science Foundation of China
- Zhejiang Province-Local Collaborative Innovation Project
- Zhejiang Province Local Collaborative Innovation Project
- National Engineering Research Center of Solid-State Brewing
Zitieren
APA
Wang, X., Shi, P., Mao, J., Liu, K., & Liu, S. (2026). UniKineG: Unified-Coordinate Geometric Graphs Enable Robust Enzyme Kinetic Prediction. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms27041731
Vancouver
Wang X, Shi P, Mao J, Liu K, Liu S. UniKineG: Unified-Coordinate Geometric Graphs Enable Robust Enzyme Kinetic Prediction. International Journal of Molecular Sciences. 2026. doi:10.3390/ijms27041731
BibTeX
@article{Wang2026,
author = {Wang, Xueyu and Shi, Peiqin and Mao, Jian and Liu, Kai and Liu, Shuangping},
title = {UniKineG: Unified-Coordinate Geometric Graphs Enable Robust Enzyme Kinetic Prediction},
journal = {International Journal of Molecular Sciences},
year = {2026},
doi = {10.3390/ijms27041731}
}
EUVIMED