Drug-target interactions prediction via graph isomorphic network and cyclic training method

doi:10.1016/j.eswa.2024.123730

IR > 计算机与通信学院

	Drug-target interactions prediction via graph isomorphic network and cyclic training method
	Du, Yuhong 1; Yao, Yabing1 ; Tang, Jianxin1 ; Zhao, Zhili 2; Gou, Zhuoyue 3
	2024-09-01
发表期刊	Expert Systems with Applications
ISSN	0957-4174
卷号	249
摘要	Predicting drug-target interactions through computational methods holds the potential to provide more reliable candidates for subsequent experimental validation and reduce associated costs. Most methods for Drug-target Interactions (DTIs) prediction have made advancements from two perspectives, improving the accuracy of drug and target representations, and seeking more precise mapping functions between the drug and target spaces. In this study, we propose a model called CT-GINDTI, which prioritizes the optimization of the model training process based on considering aforementioned improvement. CT-GINDTI represents drugs as graphs and utilizes graph isomorphism network to better capture the inherent structural and relational properties of drugs. Additionally, we introduce a cyclic training method to address the imbalance issue between positive and negative samples by selecting more reliable negative samples. To evaluate the performance of CT-GINDTI, we conducted extensive experiments and compared its results with seven state-of-the-art methods in the field. The experimental results demonstrate that our proposed CT-GINDTI outperforms these existing methods, showcasing its superior achievement in the prediction of DTIs. © 2024 Elsevier Ltd
关键词	Drug interactions Graph theory Associated costs Cyclic training method Drug-target interactions Experimental validations Graph isomorphic network Interaction prediction Mapping functions Negative samples Target representation Training methods
DOI	10.1016/j.eswa.2024.123730
收录类别	EI
语种	英语
出版者	Elsevier Ltd
EI入藏号	20241315816395
EI主题词	Forecasting
EI分类号	461.6 Medicine and Pharmacology ; 802.2 Chemical Reactions ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
原始文献类型	Journal article (JA)
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/170238
专题	计算机与通信学院
通讯作者	Du, Yuhong
作者单位	1.School of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China; 2.School of Information Science & Engineering, Lanzhou University, Lanzhou; 730000, China; 3.Northwest Institute of Nuclear Technology, Xian; 710024, China
第一作者单位	兰州理工大学
通讯作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Du, Yuhong,Yao, Yabing,Tang, Jianxin,et al. Drug-target interactions prediction via graph isomorphic network and cyclic training method[J]. Expert Systems with Applications,2024,249.
APA	Du, Yuhong,Yao, Yabing,Tang, Jianxin,Zhao, Zhili,&Gou, Zhuoyue.(2024).Drug-target interactions prediction via graph isomorphic network and cyclic training method.Expert Systems with Applications,249.
MLA	Du, Yuhong,et al."Drug-target interactions prediction via graph isomorphic network and cyclic training method".Expert Systems with Applications 249(2024).