文献类型：期刊文献

英文题名：RELATION: A Deep Generative Model for Structure-Based De Novo Drug Design

作者：Wang, Mingyang[1,2];Hsieh, Chang-Yu[3];Wang, Jike[1,2];Wang, Dong[1,2];Weng, Gaoqi[1,2];Shen, Chao[1,2];Yao, Xiaojun[4];Bing, Zhitong[5];Li, Honglin[6];Cao, Dongsheng[7];Hou, Tingjun[1,2]

机构：[1]Zhejiang Univ, Innovat Inst Artificial Intelligence Med, Coll Pharmaceut Sci, Hangzhou 310058, Zhejiang, Peoples R China;[2]Zhejiang Univ, Canc Ctr, Hangzhou 310058, Zhejiang, Peoples R China;[3]Tencent, Tencent Quantum Lab, Shenzhen 518057, Guangdong, Peoples R China;[4]Macau Univ Sci & Technol, Dr Nehers Biophys Lab Innovat Drug Discovery, Macau Inst Appl Res Med & Hlth, State Key Lab Qual Res Chinese Med, Taipa 999078, Macau, Peoples R China;[5]Chinese Acad Sci, Inst Modern Phys, Lanzhou 730000, Peoples R China;[6]East China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai 200237, Peoples R China;[7]Cent South Univ, Xiangya Sch Pharmaceut Sci, Changsha 410013, Hunan, Peoples R China

年份：2022

外文期刊名：JOURNAL OF MEDICINAL CHEMISTRY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000821469900001)】；

语种：英文

摘要：Deep learning (DL)-based de novo molecular design has recently gained considerable traction. Many DL-based generative models have been successfully developed to design novel molecules, but most of them are ligandcentric and the role of the 3D geometries of target binding pockets in molecular generation has not been well-exploited. Here, we proposed a new 3D-based generative model called RELATION. In the RELATION model, the BiTL algorithm was specifically designed to extract and transfer the desired geometric features of the protein-ligand complexes to a latent space for generation. The pharmacophore conditioning and docking-based Bayesian sampling were applied to efficiently navigate the vast chemical space for the design of molecules with desired geometric properties and pharmacophore features. As a proof of concept, the RELATION model was used to design inhibitors for two targets, AKT1 and CDK2. The calculation results demonstrated that the RELATION model could efficiently generate novel molecules with favorable binding affinity and pharmacophore features.