Fingerprint-enhanced hierarchical molecular graph neural networks for property prediction
10.1016/j.jpha.2025.101242
- Author:
Shuo LIU
1
;
Mengyun CHEN
;
Xiaojun YAO
;
Huanxiang LIU
Author Information
1. School of Pharmacy,Lanzhou University,Lanzhou,730000,China;Huawei Technologies Co.,Ltd.,Hangzhou,310000,China
- Publication Type:Journal Article
- Keywords:
Deep learning;
Hierarchical molecular graph;
Molecular fingerprint;
Molecular property prediction;
Directed message-passing neural network
- From:
Journal of Pharmaceutical Analysis
2025;15(6):1311-1320
- CountryChina
- Language:English
-
Abstract:
Accurate prediction of molecular properties is crucial for selecting compounds with ideal properties and reducing the costs and risks of trials.Traditional methods based on manually crafted features and graph-based methods have shown promising results in molecular property prediction.However,traditional methods rely on expert knowledge and often fail to capture the complex structures and interactions within molecules.Similarly,graph-based methods typically overlook the chemical structure and function hidden in molecular motifs and struggle to effectively integrate global and local molecular information.To address these limitations,we propose a novel fingerprint-enhanced hierarchical graph neural network(FH-GNN)for molecular property prediction that simultaneously learns information from hierarchical molecular graphs and fingerprints.The FH-GNN captures diverse hierarchical chemical information by applying directed message-passing neural networks(D-MPNN)on a hierarchical molecular graph that integrates atomic-level,motif-level,and graph-level information along with their relationships.Addi-tionally,we used an adaptive attention mechanism to balance the importance of hierarchical graphs and fingerprint features,creating a comprehensive molecular embedding that integrated hierarchical mo-lecular structures with domain knowledge.Experiments on eight benchmark datasets from MoleculeNet showed that FH-GNN outperformed the baseline models in both classification and regression tasks for molecular property prediction,validating its capability to comprehensively capture molecular informa-tion.By integrating molecular structure and chemical knowledge,FH-GNN provides a powerful tool for the accurate prediction of molecular properties and aids in the discovery of potential drug candidates.
