Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction
Journal of Chemical Information and Modeling · 11.08.2025 · 65 (15) · 7887-7900
DOI: 10.1021/acs.jcim.5c00456 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 24.07.2025. Verfasst von Tianyi Jiang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China. Hauptthemen laut MEDLINE: Cheminformatics. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Key Research and Development Program of Zhejiang Province, National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province.
Abstract (Originalsprache)
Molecular property prediction plays a crucial role in cheminformatics, yet existing methods are constrained by data scarcity and molecular structural heterogeneity. The Mixture of Experts (MoE) framework adopts a divide-and-conquer approach by partitioning the input space and employing expert models. However, current methods primarily rely on scaffold or atomic-level information, often neglecting fine-grained features such as functional groups. Moreover, existing MoE models lack effective mechanisms to filter redundant and noisy information, limiting prediction accuracy and generalization. To address these challenges, we propose a novel Expert-Guided Substructure Information Bottleneck (ESIB-Mol) framework that integrates MoE learning with the Information Bottleneck (IB) principle to optimize molecular representation learning. ESIB-Mol employs substructure-specific experts to focus on key molecular scaffolds and functional groups, which play a crucial role in determining molecular properties such as bioactivity and pharmacokinetics. Meanwhile, the IB principle is leveraged to filter out redundant and irrelevant information, thereby enhancing prediction accuracy and interpretability. Additionally, a dynamic gating mechanism adaptively assigns molecules to the most relevant expert, optimizing computational efficiency. Extensive experiments on benchmark data sets demonstrate the effectiveness of ESIB-Mol, highlighting its superior performance in molecular property prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China.
- Binjiang Institute of Artificial Intelligence, Zhejiang University of Technology, Hangzhou 310056, China.
- The College of Pharmaceutical Science & Collaborative Innovation Center of Yangtze River Delta Region Green Pharmaceuticals, Zhejiang University of Technology, Hangzhou 310014, China.
ORCID-Profile: Tianyi Jiang, Zeyu Wang, Xiaoze Bao
Förderung
- Key Research and Development Program of Zhejiang Province
- National Natural Science Foundation of China
- Natural Science Foundation of Zhejiang Province
- Key Technology Research and Development Program Project of Hangzhou
Zitieren
APA
Jiang, T., Yao, Q., Wang, Z., Bao, X., Yu, S., & Xuan, Q. (2025). Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction. Journal of Chemical Information and Modeling, 65(15), 7887-7900. https://doi.org/10.1021/acs.jcim.5c00456
Vancouver
Jiang T, Yao Q, Wang Z, Bao X, Yu S, Xuan Q. Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction. Journal of Chemical Information and Modeling. 2025;65(15):7887-7900. doi:10.1021/acs.jcim.5c00456
BibTeX
@article{Jiang2025,
author = {Jiang, Tianyi and Yao, Qiang and Wang, Zeyu and Bao, Xiaoze and Yu, Shanqing and Xuan, Qi},
title = {Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {15},
pages = {7887--7900},
doi = {10.1021/acs.jcim.5c00456}
}
EUVIMED