A new paradigm for applying deep learning to protein-ligand interaction prediction

doi:10.1093/bib/bbae145

	A new paradigm for applying deep learning to protein-ligand interaction prediction
	Wang, Zechen 1; Wang, Sheng 2; Li, Yangyang 1; Guo, Jingjing 3,4; Wei, Yanjie ; Mu, Yuguang 5; Zheng, Liangzhen 2,4; Li, Weifeng 1
	2024-04-05
发表期刊	BRIEFINGS IN BIOINFORMATICS
ISSN	1467-5463
卷号	25 期号:3 页码:12
摘要	Protein-ligand interaction prediction presents a significant challenge in drug design. Numerous machine learning and deep learning (DL) models have been developed to accurately identify docking poses of ligands and active compounds against specific targets. However, current models often suffer from inadequate accuracy or lack practical physical significance in their scoring systems. In this research paper, we introduce IGModel, a novel approach that utilizes the geometric information of protein-ligand complexes as input for predicting the root mean square deviation of docking poses and the binding strength (pKd, the negative value of the logarithm of binding affinity) within the same prediction framework. This ensures that the output scores carry intuitive meaning. We extensively evaluate the performance of IGModel on various docking power test sets, including the CASF-2016 benchmark, PDBbind-CrossDocked-Core and DISCO set, consistently achieving state-of-the-art accuracies. Furthermore, we assess IGModel's generalizability and robustness by evaluating it on unbiased test sets and sets containing target structures generated by AlphaFold2. The exceptional performance of IGModel on these sets demonstrates its efficacy. Additionally, we visualize the latent space of protein-ligand interactions encoded by IGModel and conduct interpretability analysis, providing valuable insights. This study presents a novel framework for DL-based prediction of protein-ligand interactions, contributing to the advancement of this field. The IGModel is available at GitHub repository https://github.com/zchwang/IGModel.
关键词	protein-ligand interaction scoring function deep learning graph neural network
DOI	10.1093/bib/bbae145
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2023YFA0915500] ; Natural Science Foundation of Shandong Province[ZR2020JQ04] ; Local Science and Technology Development Fund by the Central Government of Shandong Province[YDZX2022089] ; Singapore Ministry of Education (MOE)[RG97/22] ; Key Research and Development Project of Guangdong Province[2021B0101310002] ; National Science Foundation of China[62272449] ; Shenzhen Basic Research Fund[RCYX20200714114734194] ; Shenzhen Basic Research Fund[KQTD20200820113106007] ; Shenzhen Basic Research Fund[ZDSYS20220422103800001] ; Youth Innovation Promotion Association, CAS[Y2021101] ; Core Facility Sharing Platform of Shandong University ; National Demonstration Center for Experimental Physics Education (Shandong University)
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:001273737000005
出版者	OXFORD UNIV PRESS
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39678
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zheng, Liangzhen; Li, Weifeng
作者单位	1.Shandong Univ, Sch Phys, Jinan 250100, Shandong, Peoples R China 2.Shanghai Zelixir Biotech Ltd, Shanghai 200030, Peoples R China 3.Macao Polytech Univ, Ctr Artificial Intelligence Driven Drug Discovery, Fac Appl Sci, Rua Luis Gonzaga Gomes, Macau, Peoples R China 4.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen, Peoples R China 5.Nanyang Technol Univ, Sch Biol Sci, Singapore, Singapore
推荐引用方式 GB/T 7714	Wang, Zechen,Wang, Sheng,Li, Yangyang,et al. A new paradigm for applying deep learning to protein-ligand interaction prediction[J]. BRIEFINGS IN BIOINFORMATICS,2024,25(3):12.
APA	Wang, Zechen.,Wang, Sheng.,Li, Yangyang.,Guo, Jingjing.,Wei, Yanjie.,...&Li, Weifeng.(2024).A new paradigm for applying deep learning to protein-ligand interaction prediction.BRIEFINGS IN BIOINFORMATICS,25(3),12.
MLA	Wang, Zechen,et al."A new paradigm for applying deep learning to protein-ligand interaction prediction".BRIEFINGS IN BIOINFORMATICS 25.3(2024):12.