Accurate and task-agnostic modeling of enzymatic reactions through multimodal relational learning
Acta Pharmaceutica Sinica B · 2026-07 · 16 (7) · 4051-4066
DOI: 10.1016/j.apsb.2026.03.052 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Pharmaceutica Sinica B, 2026-07. Verfasst von Yuansheng Huang und 11 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Research Grants Council, University Grants Committee, National Natural Science Foundation of China.
Abstract (Originalsprache)
Enzymatic reactions play an emerging role in a broad spectrum of scientific and industrial applications. The inherent complexity of enzymes, such as their substrate specificity, conformational flexibility, and the vast diversity of reactions involved, poses substantial challenges for the advanced computational prediction of enzymatic reactions with desirable accuracy. Moreover, existing approaches are mostly tailored for a specific sub-task, such as substrate prediction or binding site annotation, which limits their applicability. In this study, we introduce ERAM, a task-agnostic multimodal learning framework capable of addressing a broad range of downstream applications with both accuracy and efficiency. ERAM aligns pre-trained molecular representations from Protein Language Model with the knowledge of enzyme catalysis by modeling enzymatic reactions as multi-relational data. In enzyme retrieval tasks, ERAM achieves an improvement of 28.31% in mean average precision compared with the state-of-the-art (SOTA) method, CREEP. In substrate prediction tasks, ERAM outperforms the SOTA method ESP, achieving average improvements of 35.53% and 22.97% in Matthews correlation coefficient across two datasets. Additionally, ERAM exhibits commendable interpretability by assigning higher attention weights to binding sites, resulting in lower false-positive rates (42.36%) and higher overlap scores (70.59%) in the unsupervised binding site prediction task compared to RXNAA Mapper. By learning embeddings of substrates, enzymes, and products within a unified knowledge graph latent space, ERAM demonstrates its potential as a versatile and effective tool for enzyme catalysis research.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
- Research Center for Life Sciences Computing, Zhejiang Lab, Hangzhou 311121, China.
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong 999077, China.
- School of Computing, National University of Singapore, Singapore 117417, Singapore.
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA 98195-2350, USA.
Förderung
- Research Grants Council, University Grants Committee
- National Natural Science Foundation of China
Zitieren
APA
Huang, Y., Li, L., Qian, W., Yu, J., Zhao, H., Wang, X., Zhang, O., Chen, G., Gu, S., Heng, P. A., Hou, T., & Kang, Y. (2026). Accurate and task-agnostic modeling of enzymatic reactions through multimodal relational learning. Acta Pharmaceutica Sinica B, 16(7), 4051-4066. https://doi.org/10.1016/j.apsb.2026.03.052
Vancouver
Huang Y, Li L, Qian W, Yu J, Zhao H, Wang X, et al. Accurate and task-agnostic modeling of enzymatic reactions through multimodal relational learning. Acta Pharmaceutica Sinica B. 2026;16(7):4051-4066. doi:10.1016/j.apsb.2026.03.052
BibTeX
@article{Huang2026,
author = {Huang, Yuansheng and Li, Lanqing and Qian, Wenjia and Yu, Jiahui and Zhao, Huifeng and Wang, Xiaorui and Zhang, Odin and Chen, Guangyong and Gu, Shukai and Heng, Pheng-Ann and Hou, Tingjun and Kang, Yu},
title = {Accurate and task-agnostic modeling of enzymatic reactions through multimodal relational learning},
journal = {Acta Pharmaceutica Sinica B},
year = {2026},
volume = {16},
number = {7},
pages = {4051--4066},
doi = {10.1016/j.apsb.2026.03.052}
}
EUVIMED