An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph

doi:10.1093/bib/bbac073

	An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph
	Wan, Xiaozhe 1,2,3; Wu, Xiaolong 1,2,4; Wang, Dingyan 1,2,3; Tan, Xiaoqin 5; Liu, Xiaohong 6; Fu, Zunyun 1,2; Jiang, Hualiang2,3,7 ; Zheng, Mingyue 1,2,3; Li, Xutong 1,2,3
	2022-05-13
发表期刊	BRIEFINGS IN BIOINFORMATICS (IF:6.8[JCR-2023],7.9[5-Year])
ISSN	1467-5463
EISSN	1477-4054
卷号	23 期号:3
发表状态	已发表
DOI	10.1093/bib/bbac073
摘要	Identifying the potential compound-protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound-protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature.
关键词	compound-protein interaction prediction homogeneous graph end-to-end learning inductive graph neural network
URL	查看原文
收录类别	SCIE ; SCI
语种	英语
资助项目	National Natural Science Foundation of China[81773634]
WOS研究方向	Biochemistry & Molecular Biology ; Mathematical & Computational Biology
WOS类目	Biochemical Research Methods ; Mathematical & Computational Biology
WOS记录号	WOS:000808504500065
出版者	OXFORD UNIV PRESS
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/243290
专题	生命科学与技术学院免疫化学研究所_特聘教授组_蒋华良组
通讯作者	Zheng, Mingyue; Li, Xutong
作者单位	1.Shanghai Inst Mat Med, Shanghai, Peoples R China 2.Chinese Acad Sci, Drug Discovery & Design Ctr, Shanghai Inst Mat Med, State Key Lab Drug Res, 555 Zuchongzhi Rd, Shanghai 201203, Peoples R China 3.Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing 100049, Peoples R China 4.East China Univ Sci & Technol, Sch Pharm, Shanghai 200237, Peoples R China 5.ByteDance AI Lab, Shanghai 201103, Peoples R China 6.AlphaMa Inc, 108 Yuxin Rd,Suzhou Ind Pk, Suzhou 215128, Peoples R China 7.ShanghaiTech Univ, Sch Life Sci & Technol, 393 Huaxiazhong Rd, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Wan, Xiaozhe,Wu, Xiaolong,Wang, Dingyan,et al. An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph[J]. BRIEFINGS IN BIOINFORMATICS,2022,23(3).
APA	Wan, Xiaozhe.,Wu, Xiaolong.,Wang, Dingyan.,Tan, Xiaoqin.,Liu, Xiaohong.,...&Li, Xutong.(2022).An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph.BRIEFINGS IN BIOINFORMATICS,23(3).
MLA	Wan, Xiaozhe,et al."An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph".BRIEFINGS IN BIOINFORMATICS 23.3(2022).