EnzyDiff: Sequence-based classification of mutation-induced enzyme activity direction using latent diffusion denoising
Science Progress · 2026
DOI: 10.1177/00368504261489697 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Science Progress, 2026. Verfasst von Hui Jin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, The First Affiliated hospital of Xi'an Medical University, Xi'an, Shaanxi Province, China. Hauptthemen laut MEDLINE: Enzymes, Software. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fundamental Research Funds for the Central Universities of China.
Abstract (Originalsprache)
Objective
Prediction of mutation-induced enzyme activity changes is important for protein engineering, drug response analysis, and precision medicine. Existing methods often depend on structural information or complex external pipelines, limiting reproducibility and practical use.
Methods
We developed EnzyDiff, a lightweight diffusion-based framework that encodes mutation-induced activity perturbations from enzyme sequences before and after mutation, together with mutation identity and position. The model was evaluated on the P450 deep mutational scanning dataset using five-fold cross-validation, with additional analyses of robustness, representation visualization, and case-based occlusion sensitivity. After preprocessing, 3,289 labeled mutation entries were retained, including 240 Increased samples and 3,049 Decreased samples.
Results
In five-fold cross-validation, EnzyDiff achieved an accuracy of 0.933, F1-score of 0.497, AUROC of 0.803, and PR-AUC of 0.495 on the P450 dataset. It remained stable under reversed mutation settings, showed clear class separation in learned representations, and highlighted mutation-relevant positions in interpretability analyses. However, the moderate F1-score also indicates that minority-class prediction remains challenging under strong class imbalance.
Conclusions
EnzyDiff is a lightweight, reproducible, and interpretable framework for enzyme activity direction classification. It offers a practical sequence-based solution for functional mutation assessment and downstream biological analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Neurosurgery, The First Affiliated hospital of Xi'an Medical University, Xi'an, Shaanxi Province, China.
- School of Medicine, School of Biomedical Engineering, Shanghai Mental Health Center, Shanghai Jiao Tong University, Shanghai Jiao Tong University, Shanghai, China.
- Shanghai Gener Arfysica Intelligent Healthcare & Brain Science Research Institute, Shanghai, China.
- Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China.
ORCID-Profile: Zhe Liu
Förderung
- Fundamental Research Funds for the Central Universities of China
Zitieren
APA
Jin, H., Liu, Z., & Jia, Z. (2026). EnzyDiff: Sequence-based classification of mutation-induced enzyme activity direction using latent diffusion denoising. Science Progress. https://doi.org/10.1177/00368504261489697
Vancouver
Jin H, Liu Z, Jia Z. EnzyDiff: Sequence-based classification of mutation-induced enzyme activity direction using latent diffusion denoising. Science Progress. 2026. doi:10.1177/00368504261489697
BibTeX
@article{Jin2026,
author = {Jin, Hui and Liu, Zhe and Jia, Zhuopeng},
title = {EnzyDiff: Sequence-based classification of mutation-induced enzyme activity direction using latent diffusion denoising},
journal = {Science Progress},
year = {2026},
doi = {10.1177/00368504261489697}
}
EUVIMED