Mfgnn: Multi‐Scale Feature‐Attentive Graph Neural Networks for Molecular Property Prediction
Journal of Computational Chemistry · 30.01.2025 · 46 (3)
DOI: 10.1002/jcc.70011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Chemistry, online erschienen am 22.01.2025. Verfasst von Weiting Ye und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, Guangdong, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
In the realm of artificial intelligence‐driven drug discovery (AIDD), accurately predicting the influence of molecular structures on their properties is a critical research focus. While deep learning models based on graph neural networks (GNNs) have made significant advancements in this area, prior studies have primarily concentrated on molecule‐level representations, often neglecting the impact of functional group structures and the potential relationships between fragments on molecular property predictions. To address this gap, we introduce the multi‐scale feature attention graph neural network (MfGNN), which enhances traditional atom‐based molecular graph representations by incorporating fragment‐level representations derived from chemically synthesizable BRICS fragments. MfGNN not only effectively captures both the structural information of molecules and the features of functional groups but also pays special attention to the potential relationships between fragments, exploring how they collectively influence molecular properties. This model integrates two core mechanisms: a graph attention mechanism that captures embeddings of molecules and functional groups, and a feature extraction module that systematically processes BRICS fragment‐level features to uncover relationships among the fragments. Our comprehensive experiments demonstrate that MfGNN outperforms leading machine learning and deep learning models, achieving state‐of‐the‐art performance in 8 out of 11 learning tasks across various domains, including physical chemistry, biophysics, physiology, and toxicology. Furthermore, ablation studies reveal that the integration of multi‐scale feature information and the feature extraction module enhances the richness of molecular features, thereby improving the model's predictive capabilities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, Guangdong, China.
Zitieren
APA
Ye, W., Li, J., & Cai, X. (2025). Mfgnn: Multi‐Scale Feature‐Attentive Graph Neural Networks for Molecular Property Prediction. Journal of Computational Chemistry, 46(3). https://doi.org/10.1002/jcc.70011
Vancouver
Ye W, Li J, Cai X. Mfgnn: Multi‐Scale Feature‐Attentive Graph Neural Networks for Molecular Property Prediction. Journal of Computational Chemistry. 2025;46(3). doi:10.1002/jcc.70011
BibTeX
@article{Ye2025,
author = {Ye, Weiting and Li, Jingcheng and Cai, Xianfa},
title = {Mfgnn: Multi‐Scale Feature‐Attentive Graph Neural Networks for Molecular Property Prediction},
journal = {Journal of Computational Chemistry},
year = {2025},
volume = {46},
number = {3},
doi = {10.1002/jcc.70011}
}
EUVIMED