P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching
文献类型：期刊论文
| 作者 | Jin, Yaowei3; Huang, Qi1; Song, Ziyang6; Zheng, Mingyue2,4,5 ; Teng, Dan4; Shi, Qian3
|
| 刊名 | JOURNAL OF CHEMICAL THEORY AND COMPUTATION
 |
| 出版日期 | 2025-03-10 |
| 卷号 | 21期号:6页码:3288-3296 |
| ISSN号 | 1549-9618 |
| DOI | 10.1021/acs.jctc.4c01620 |
| 英文摘要 | Biological processes, functions, and properties are intricately linked to the ensemble of protein conformations rather than being solely determined by a single stable conformation. In this study, we developed P2DFlow, a generative model based on SE(3) flow matching, to predict the structural ensembles of proteins. We specifically designed a valuable prior for the flow process and enhanced the model's ability to distinguish each intermediate state by incorporating an additional dimension to describe the ensemble data, which can reflect the physical laws governing the distribution of ensembles so that the prior knowledge can effectively guide the generation process. When trained and evaluated on the MD data sets of ATLAS, P2DFlow outperforms other baseline models on extensive experiments, successfully capturing the observable dynamic fluctuations as evidenced in crystal structure and MD simulations. As a potential proxy agent for protein molecular simulation, the high-quality ensembles generated by P2DFlow could significantly aid in understanding protein functions across various scenarios. Code is available at https://github.com/BLEACH366/P2DFlow. |
| 资助项目 | National Natural Science Foundation of China[2022YFC3400504] ; National Key Research and Development Program of China[23QD1400600] ; National Key Research and Development Program of China[23YF1449200] ; Shanghai Rising-Star Program[GZC20232846] ; Shanghai Rising-Star Program[2022M712402] ; Postdoctoral Fellowship Program of CPSF[22309134] ; National Natural Science Foundation of China |
| WOS研究方向 | Chemistry ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001443893200001 |
| 出版者 | AMER CHEMICAL SOC |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/316545]  |
| 专题 | 新药研究国家重点实验室 |
| 通讯作者 | Teng, Dan; Shi, Qian |
| 作者单位 | 1.Fudan Univ, Inst Elect Light Sources, Sch Informat Sci & Technol, Shanghai 200438, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Lingang Lab, Shanghai 200031, Peoples R China 4.Chinese Acad Sci, Shanghai Inst Mat Med, Drug Discovery & Design Ctr, State Key Lab Drug Res, Shanghai 201203, Peoples R China 5.Nanjing Univ Chinese Med, Sch Chinese Mat Med, Nanjing 210023, Peoples R China 6.Tongji Univ, Sch Chem Sci & Engn, Shanghai Key Lab Chem Assessment & Sustainabil, Shanghai 200092, Peoples R China |
| 推荐引用方式 GB/T 7714 | Jin, Yaowei,Huang, Qi,Song, Ziyang,et al. P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching[J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION,2025,21(6):3288-3296. |
| APA | Jin, Yaowei,Huang, Qi,Song, Ziyang,Zheng, Mingyue,Teng, Dan,&Shi, Qian.(2025).P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching.JOURNAL OF CHEMICAL THEORY AND COMPUTATION,21(6),3288-3296. |
| MLA | Jin, Yaowei,et al."P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching".JOURNAL OF CHEMICAL THEORY AND COMPUTATION 21.6(2025):3288-3296. |
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。