Accurate proteome-wide prediction of enzymes and catalytic sites using graph deep learning and protein language model
GigaScience · 21.01.2026 · 15
DOI: 10.1093/gigascience/giag056 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, online erschienen am 13.05.2026. Verfasst von Yui-Lun Ng und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Faculty of Engineering, The University of Hong Kong, Pok Fu Lam, Hong Kong. Hauptthemen laut MEDLINE: Deep Learning, Catalytic Domain, Proteome, Enzymes. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Grants Council, Health and Medical Research Fund, National Natural Science Foundation of China.
Abstract (Originalsprache)
Identifying the enzyme functions of proteins and their catalytic residues is vital to our understanding of diverse cellular processes. However, existing frameworks that can concurrently determine the enzymatic functions and active sites of proteins are scarce, and still have much room for improvement in prediction performance. In this study, we present EC-LMGraph, a protein language model- and graph convolutional network-based framework to predict enzyme commission (EC) numbers from protein sequence features and structures, and saliency mapping to score representative residues attribute to the enzymatic functions. EC-LMGraph attained an average F1 score of 0.77 in 3rd-level EC number prediction, and 0.76 in 4th-level prediction, outperforming numerous other algorithms that were either sequence-based only, or additionally incorporated structural information. Benchmarking on the Mechanism and Catalytic Site Atlas dataset and a set of Parkinson’s disease-related proteins, we showed that EC-LMGraph showed a stronger emphasis on catalytic sites than the current state-of-the-art algorithm DeepFRI. Combining EC-LMGraph with AlphaFold2, our framework correctly determined the 3rd-level EC numbers of 229,160 proteins based purely on their predicted structures. We show that EC-LMGraph is capable of accurately predicting the 3rd/4th-level EC numbers, and pinpointing the key amino acid residues for many enzymes. EC-LMGraph is implemented and freely available at https://github.com/ngyuilun/EC-LMGraph.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Mechanical Engineering, Faculty of Engineering, The University of Hong Kong, Pok Fu Lam, Hong Kong.
- Division of Neurology, Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong.
- Li Ka Shing Institute of Health Sciences, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong.
- Margaret K. L. Cheung Research Centre for Management of Parkinsonism, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong.
- Gerald Choa Neuroscience Institute, The Chinese University of Hong Kong, Shatin, Hong Kong.
- Department of Psychiatry, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong.
ORCID-Profile: Yui-Lun Ng, Yingqi Li, Ka-Wai Kwok
Förderung
- Research Grants Council
- Health and Medical Research Fund
- National Natural Science Foundation of China
Zitieren
APA
Ng, Y. L., Wang, X., Li, Y., Huang, J., Lai, H. M., Chan, J. Y., Ng, B. W., Ko, H., & Kwok, K. W. (2026). Accurate proteome-wide prediction of enzymes and catalytic sites using graph deep learning and protein language model. GigaScience, 15. https://doi.org/10.1093/gigascience/giag056
Vancouver
Ng YL, Wang X, Li Y, Huang J, Lai HM, Chan JY, et al. Accurate proteome-wide prediction of enzymes and catalytic sites using graph deep learning and protein language model. GigaScience. 2026;15. doi:10.1093/gigascience/giag056
BibTeX
@article{Ng2026,
author = {Ng, Yui-Lun and Wang, Xiaomei and Li, Yingqi and Huang, Junzhe and Lai, Hei Ming and Chan, Jason Ying-Kuen and Ng, Billy Wai-Lung and Ko, Ho and Kwok, Ka-Wai},
title = {Accurate proteome-wide prediction of enzymes and catalytic sites using graph deep learning and protein language model},
journal = {GigaScience},
year = {2026},
volume = {15},
doi = {10.1093/gigascience/giag056}
}
EUVIMED