中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 上海药物研究所
  3. 中国科学院上海药物研究所
  4. 国家级研究中心
  5. 原创新药研究全国重点实验室
Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol

文献类型：期刊论文

作者Li, Mingyu2,3,4; Song, Kun5; He, Jixiao2,3; Zhao, Mingzhu2,3; You, Gengshu5; Zhong, Jie2,3; Zhao, Mengxi6; Li, Arong6; Chen, Yu6; Li, Guobin6
刊名NATURE MACHINE INTELLIGENCE
出版日期2025-08-01
卷号7期号:8页码:19
DOI10.1038/s42256-025-01095-7
英文摘要Generative drug design opens avenues for discovering novel compounds within the vast chemical space rather than conventional screening against limited libraries. However, the practical utility of the generated molecules is frequently constrained, as many designs prioritize a narrow range of pharmacological properties and neglect physical reliability, which hinders the success rate of subsequent wet-laboratory evaluations. Here, to address this, we propose ED2Mol, a deep learning-based approach that leverages fundamental electron density information to improve de novo molecular generation and optimization. The extensive evaluations across multiple benchmarks demonstrate that ED2Mol surpasses existing methods in terms of the generation success rate and >97% physical reliability. It also facilitates automated hit optimization that is not fully implemented by other methods using fragment-based strategies. Furthermore, ED2Mol exhibits generalizability to more challenging, unseen allosteric pocket benchmarks, attaining consistent performance. More importantly, ED2Mol has been applied to various real-world essential targets, successfully identifying wet-laboratory-validated bioactive compounds, ranging from FGFR3 orthosteric inhibitors to CDC42 allosteric inhibitors, GCK and GPRC5A allosteric activators. The directly generated binding modes of these compounds are close to predictions through molecular docking and further validated via the X-ray co-crystal structure. All these results highlight ED2Mol's potential as a useful tool in drug design with enhanced effectiveness, physical reliability and practical applicability.
WOS关键词PROTEIN ; GLUCOKINASE ; IDENTIFICATION ; INHIBITION ; DISCOVERY ; SETS
资助项目National Key RD program of China (2023YFF1205103 to J.Z.), the National Natural Science Foundation of China (81925034, 82441035, 22237005 to J.Z. and 824B2105 to M.L.), Innovative research team of high-level local universities in Shanghai (SHSMU-ZDCX20212[2023YFF1205103] ; National Key R&D Program of China[81925034] ; National Key R&D Program of China[82441035] ; National Key R&D Program of China[22237005] ; National Key R&D Program of China[824B2105] ; National Natural Science Foundation of China[SHSMU-ZDCX20212700] ; National Natural Science Foundation of China[SN-ZJU-SIAS-007] ; Innovative Research Team of High-Level Local Universities in Shanghai[2022BEG01002] ; Key Research and Development Program of Ningxia Hui Autonomous Region[2024CXTD013] ; Ningxia Peptide and Small Molecule Innovative Drug Research Science and Technology Innovation Team[XJKF240322] ; Ningxia Peptide and Small Molecule Innovative Drug Research Science and Technology Innovation Team[LG8888] ; Ningxia Peptide and Small Molecule Innovative Drug Research Science and Technology Innovation Team[ZIRC2020-06] ; Open Competition Mechanism to Select the Best Candidates for Key Research Projects of Ningxia Medical University[24KCPYZD001] ; Shanghai Jiao Tong University School of Medicine PhD Cultivation Fund for Science and Innovation
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001554761500003
出版者NATURE PORTFOLIO
源URL[http://119.78.100.183/handle/2S10ELR8/321333]  
专题国家级研究中心_原创新药研究全国重点实验室
通讯作者Zhang, Jian
作者单位1.Chinese Acad Sci, State Key Lab Drug Res, Shanghai Inst Mat Med, Shanghai, Peoples R China
2.Shanghai Jiao Tong Univ, Ruijin Hosp, Natl Res Ctr Translat Med Shanghai, State Key Lab Med Genom,Sch Med, Shanghai, Peoples R China
3.Shanghai Jiao Tong Univ, Inst Med Artificial Intelligence, Dept Pharmaceut & Artificial Intelligence Sci, Sch Med, Shanghai, Peoples R China
4.Ningxia Med Univ, Coll Pharm, Yinchuan, Peoples R China
5.Nutshell BioTech Co Ltd, Shanghai, Peoples R China
6.Blueray Biopharm Co Ltd, Shanghai, Peoples R China
7.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Li, Mingyu,Song, Kun,He, Jixiao,et al. Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol[J]. NATURE MACHINE INTELLIGENCE,2025,7(8):19.
APA Li, Mingyu.,Song, Kun.,He, Jixiao.,Zhao, Mingzhu.,You, Gengshu.,...&Zhang, Jian.(2025).Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol.NATURE MACHINE INTELLIGENCE,7(8),19.
MLA Li, Mingyu,et al."Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol".NATURE MACHINE INTELLIGENCE 7.8(2025):19.

入库方式： OAI收割

来源：上海药物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。