A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor

doi:10.1016/j.ejmech.2025.117602

	A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor
	Yang, Zhenyu 1; Wang, Kai 2,3; Zhang, Guo 2,3; Jiang, Yuanyuan 2,3; Zeng, Rui 2,3; Qiao, Jingxin 2,3; Li, Yueyue 2,3; Deng, Xinyue 2,3; Xia, Ziyi 2,3; Yao, Rui 2,3; Zeng, Xiaoxi 1; Zhang, Liyun 7; Zhao, Yi 4; Lei, Jian 2,3,6; Chen, Runsheng 1,5
	2025-07-05
发表期刊	EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY
ISSN	0223-5234
卷号	291 页码:16
摘要	Bioactivity optimization is a crucial and technical task in the early stages of drug discovery, traditionally carried out through iterative substituent optimization, a process that is often both time-consuming and expensive. To address this challenge, we present Pocket-StrMod, a deep-learning model tailored for structure-based bioactivity optimization. Pocket-StrMod employs an autoregressive flow-based architecture, optimizing molecules within a specific protein binding pocket while explicitly incorporating chemical expertise. It synchronously optimizes all substituents by generating atoms and covalent bonds at designated sites within a molecular scaffold nestled inside a protein pocket. We applied this model to optimize the bioactivity of Hit1, an inhibitor of the SARS-CoV-2 main protease (Mpro) with initially poor bioactivity (IC50 : 34.56 mu M). Following two rounds of optimization, six compounds were selected for synthesis and bioactivity testing. This led to the discovery of C5, a potent compound with an IC50 value of 33.6 nM, marking a remarkable 1028-fold improvement over Hit1. Furthermore, C5 demonstrated promising in vitro antiviral activity against SARS-CoV-2. Collectively, these findings underscore the great potential of deep learning in facilitating rapid and cost-effective bioactivity optimization in the early phases of drug development.
关键词	Structure-based bioactivity optimization Deep-learning model SARS-CoV-2 main protease Molecular scaffold Pocket-StrMod
DOI	10.1016/j.ejmech.2025.117602
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[32341019] ; National Natural Science Foundation of China[82130104] ; National Natural Science Foundation of China[82473844] ; National Natural Science Foundation of China[82404514] ; National Key R & D Program of China[2021YFF0702004] ; Natural Science Foundation of Sichuan Province[2024NSFSC1142]
WOS研究方向	Pharmacology & Pharmacy
WOS类目	Chemistry, Medicinal
WOS记录号	WOS:001471950500001
出版者	ELSEVIER FRANCE-EDITIONS SCIENTIFIQUES MEDICALES ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40599
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Yi; Lei, Jian; Chen, Runsheng
作者单位	1.Sichuan Univ, West China Hosp, West China Biomed Big Data Ctr, Chengdu 610041, Sichuan, Peoples R China 2.Sichuan Univ, Canc Ctr, Dept Biotherapy, Chengdu 610041, Sichuan, Peoples R China 3.Sichuan Univ, West China Hosp, State Key Lab Biotherapy, Chengdu 610041, Sichuan, Peoples R China 4.Chinese Acad Sci, Adv Comp Res Ctr, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Biophys, Ctr Big Data Res Hlth, Key Lab RNA Biol, Beijing 100101, Peoples R China 6.Sichuan Univ, West China Hosp, Natl Clin Res Ctr Geriatr, Chengdu 610041, Sichuan, Peoples R China 7.HitGen Inc, Lead Generat Unit, Tianfu Int Biotown, Chengdu 610200, Sichuan, Peoples R China
推荐引用方式 GB/T 7714	Yang, Zhenyu,Wang, Kai,Zhang, Guo,et al. A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor[J]. EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY,2025,291:16.
APA	Yang, Zhenyu.,Wang, Kai.,Zhang, Guo.,Jiang, Yuanyuan.,Zeng, Rui.,...&Chen, Runsheng.(2025).A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor.EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY,291,16.
MLA	Yang, Zhenyu,et al."A deep learning model for structure-based bioactivity optimization and its application in the bioactivity optimization of a SARS-CoV-2 main protease inhibitor".EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY 291(2025):16.