Institute of Computing Technology, Chinese Academy IR
| DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials | |
| Zeng, Jinzhe1,2,3,4; Zhang, Duo5,6,7; Peng, Anyang5; Zhang, Xiangyu8,9; He, Sensen10; Wang, Yan8,9; Liu, Xinzijian6; Bi, Hangrui11; Li, Yifan12; Cai, Chun5; Zhang, Chengqian7; Du, Yiming8,9; Zhu, Jia-Xin13; Mo, Pinghui14; Huang, Zhengtao15; Zeng, Qiyu16,17; Shi, Shaochen18; Qin, Xuejian19,20; Yu, Zhaoxi21; Luo, Chenxing22,23; Ding, Ye6; Liu, Yun-Pei24; Shi, Ruosong25; Wang, Zhenyu26,27; Bore, Sigbjorn Loland28,29; Chang, Junhan6,30; Deng, Zhe30; Ding, Zhaohan6; Han, Siyuan31; Jiang, Wanrun5; Ke, Guolin6; Liu, Zhaoqing30; Lu, Denghui32,33; Muraoka, Koki34; Oliaei, Hananeh35; Singh, Anurag Kumar36; Que, Haohui37; Xu, Weihong24; Xu, Zhangmancang38; Zhuang, Yong-Bin39; Dai, Jiayu16,17; Giese, Timothy J.40,41; Jia, Weile8; Xu, Ben42; York, Darrin M.40,41; Zhang, Linfeng5,6; Wang, Han43,44 | |
| 2025-05-02 | |
| 发表期刊 | JOURNAL OF CHEMICAL THEORY AND COMPUTATION
 |
| ISSN | 1549-9618 |
| 卷号 | 21期号:9页码:4375-4385 |
| 摘要 | In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks, such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of the DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multibackend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLP packages and of differentiable molecular force fields. This architecture allows seamless back-end switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. |
| DOI | 10.1021/acs.jctc.5c00340 |
| 收录类别 | SCI |
| 语种 | 英语 |
| 资助项目 | Fundation the Science and Technology Innovation Program of Hunan Province[2021RC4026] ; Research Council of Norway through the Centre of Excellence Hylleraas Centre for Quantum Molecular Sciences[262695] ; Young Researcher Talent[344993] ; EuroHPC Joint Undertaking[EHPC-REG-2023R02-088] ; Natural Science Foundation of China[92270206] ; Natural Science Foundation of China[12122103] ; National Institutes of Health[GM107485] ; National Science Foundation[2209718] ; National Key R&D Program of China[2022YFA1004300] |
| WOS研究方向 | Chemistry ; Physics |
| WOS类目 | Chemistry, Physical ; Physics, Atomic, Molecular & Chemical |
| WOS记录号 | WOS:001481066700001 |
| 出版者 | AMER CHEMICAL SOC |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://119.78.100.204/handle/2XEOYT63/40643 |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zeng, Jinzhe; Zhang, Linfeng; Wang, Han |
| 作者单位 | 1.Univ Sci & Technol China, Sch Artificial Intelligence & Data Sci, Hefei 230026, Peoples R China 2.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou 215123, Peoples R China 3.Suzhou Big Data, Suzhou 215123, Peoples R China 4.AI Res & Engn Ctr, Suzhou 215123, Peoples R China 5.AI Sci Inst, Beijing 100080, Peoples R China 6.DP Technol, Beijing 100080, Peoples R China 7.Peking Univ, Acad Adv Interdisciplinary Studies, Beijing 100871, Peoples R China 8.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100871, Peoples R China 9.Univ Chinese Acad Sci, Beijing 100871, Peoples R China 10.Baidu Inc, Beijing 100085, Peoples R China 11.Univ Toronto, Dept Comp Sci, Toronto, ON M5S 1A1, Canada 12.Princeton Univ, Dept Chem, Princeton, NJ 08540 USA 13.Xiamen Univ, Coll Chem & Chem Engn, IChEM, State Key Lab Phys Chem Solid Surfaces, Xiamen 361005, Peoples R China 14.Hunan Univ, Coll Integrated Circuits, Changsha 410082, Peoples R China 15.Wuhan Univ Technol, Sch Mat Sci & Engn, Ctr Smart Mat & Device Integrat, State Key Lab Adv Technol Mat Synth & Proc, Wuhan 430070, Peoples R China 16.Natl Univ Def Technol, Coll Sci, Changsha 410073, Peoples R China 17.Natl Univ Def Technol, Hunan Key Lab Extreme Matter & Applicat, Changsha 410073, Peoples R China 18.ByteDance Res, Beijing 100098, Peoples R China 19.Chinese Acad Sci, Ningbo Inst Mat Technol & Engn, Ningbo 315201, Peoples R China 20.Univ Chinese Acad Sci, Coll Mat Sci & Optoelect Technol, Beijing 100049, Peoples R China 21.Beijing Normal Univ, Coll Chem, Minist Educ, Key Lab Theoret & Comp Photochem, Beijing 100875, Peoples R China 22.Princeton Univ, Dept Geosci, Princeton, NJ 08544 USA 23.Columbia Univ, Dept Appl Phys & Appl Math, New York, NY 10027 USA 24.IKKEM, Lab AI Electrochem AI4EC, Xiamen 361005, Fujian, Peoples R China 25.China Acad Engn Phys, Grad Sch, Beijing 100088, Peoples R China 26.Jilin Univ, Coll Phys, Minist Educ, Key Lab Mat Simulat Methods & Software, Changchun 130012, Peoples R China 27.Jilin Univ, Int Ctr Future Sci, Changchun 130012, Peoples R China 28.Univ Oslo, Dept Chem, N-0315 Oslo, Norway 29.Univ Oslo, Hylleraas Ctr Quantum Mol Sci, N-0315 Oslo, Norway 30.Peking Univ, Coll Chem & Mol Engn, Beijing 100871, Peoples R China 31.Xiamen Univ, Coll Chem & Chem Engn, State Key Lab Phys Chem Solid Surfaces, Xiamen 361005, Peoples R China 32.Peking Univ, Dept Mech & Engn Sci, Beijing 100871, Peoples R China 33.Peking Univ, Coll Engn, HEDPS & CAPT, Beijing 100871, Peoples R China 34.Univ Tokyo, Dept Chem Syst Engn, Bunkyo Ku, Tokyo 1138656, Japan 35.Univ Illinois Urbana & Champaign, Dept Mech Sci & Engn, Urbana, IL 61801 USA 36.Indian Inst Technol Palakkad, Data Sci Dept, Palakkad 678623, Kerala, India 37.Chinese Acad Sci, Shanghai Astron Observ, Shanghai 200030, Peoples R China 38.Wuhan Univ Technol, Int Sch Mat Sci & Engn, Wuhan 430070, Peoples R China 39.Ecole Polytech Fed Lausanne, CSEA, CH-1015 Lausanne, Switzerland 40.Rutgers State Univ, Inst Quantitat Biomed, Lab Biomol Simulat Res, Piscataway, NJ 08854 USA 41.Rutgers State Univ, Dept Chem & Chem Biol, Piscataway, NJ 08854 USA 42.China Acad Engn Phys, Grad Sch, Beijing 100088, Peoples R China 43.Natl Key Lab Comp Phys, Inst Appl Phys & Comp Math, Beijing 100094, Peoples R China 44.Peking Univ, Coll Engn, HEDPS, CAPT, Beijing 100871, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zeng, Jinzhe,Zhang, Duo,Peng, Anyang,et al. DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials[J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION,2025,21(9):4375-4385. |
| APA | Zeng, Jinzhe.,Zhang, Duo.,Peng, Anyang.,Zhang, Xiangyu.,He, Sensen.,...&Wang, Han.(2025).DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials.JOURNAL OF CHEMICAL THEORY AND COMPUTATION,21(9),4375-4385. |
| MLA | Zeng, Jinzhe,et al."DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials".JOURNAL OF CHEMICAL THEORY AND COMPUTATION 21.9(2025):4375-4385. |
| 条目包含的文件 | 条目无相关文件。 | |||||
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。
修改评论