北京大学学报（自然科学版） ›› 2026, Vol. 62 ›› Issue (2): 286-296.DOI: 10.13209/j.0479-8023.2025.093

上一篇    下一篇

基于异质生物图动态表示学习的药物–靶标关系预测

郭延哺1, 李维华2,†, 曹进德3,4, 周冬明2,5   

  1. 1. 郑州轻工业大学软件学院, 郑州 450001 2. 云南大学信息学院, 昆明 650500 3 东南大学数学学院, 南京 211189 4. 紫金山实验室, 南京 211111 5. 湖南信息学院电子科学与工程学院, 长沙 410100
  • 收稿日期:2025-03-05 修回日期:2025-08-20 出版日期:2026-03-20 发布日期:2026-03-20
  • 基金资助:
    国家自然科学基金(62403437, 62576098)、河南省重点研发与推广专项(242102211039)和郑州轻工业大学校级青年骨干教师培养项目(13502010009)资助

Drug-target Interaction Prediction Based on Dynamic Representation Learning of Heterogeneous Biological Graphs

GUO Yanbu1, LI Weihua2,†, CAO Jinde3,4, ZHOU Dongming2,5   

  1. 1. College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001 2. School of Information Science and Engineering, Yunnan University, Kunming 650500 3. School of Mathematics, Southeast University, Nanjing 211189 4. Purple Mountain Laboratories, Nanjing 211111 5. School of Electronic Science and Engineering, Hunan University of Information Technology, Changsha 410100
  • Received:2025-03-05 Revised:2025-08-20 Online:2026-03-20 Published:2026-03-20

PDF

摘要：

针对药物和靶标等生物分子的复杂关系, 融合多源异质图和异质门图卷积, 设计一种异质生物图动态表示学习方法HGGCN。该方法利用异质图门卷积的门控通道和特征通道, 自适应建模异质生物图中的互作用模式, 融合增强复杂网络的拓扑结构和语义信息, 实现药物与靶标的知识表示以及药物–靶标互作用信息挖掘。实验结果表明, 所提模型的性能优于现有药物–靶标互作用预测方法, 是一种精准的药物–靶标关联预测工具, 可以支持复杂生物数据建模和疾病精准治疗。

关键词: 复杂生物网络, 多源异质图, 神经网络, 药物–靶标互作用

Abstract:

To extract the complex relationships between drugs and targets, this paper designs a dynamic representation learning algorithm based on deep heterogeneous graph gated convolutional networks (HGGCN) for biological graph modeling and representation learning. The algorithm combines the merits of the gated channels and feature channels to adaptively model interaction patterns of heterogeneous graphs, enhance the topological structure and semantic information of complex networks based on the fusion, and obtain the discriminative representation of drugs and targets for drug-target interaction mining. Experimental results show that the proposed model outperforms existing drug target interaction prediction methods, and is also an accurate drug target association prediction tool, which could provide the technical support for the precision treatment of complex diseases and network information mining.

Key words: complex biological networks, multi-source heterogeneous graph, neural networks, drug-target interaction

版权所有 © 《北京大学学报（自然科学版）》编辑部
技术支持：北京玛格泰克科技发展有限公司