DeePMD-kit v2: A software package for deep potential models

doi:10.1063/5.0155600

	DeePMD-kit v2: A software package for deep potential models
	Zeng, Jinzhe 1,2; Zhang, Duo 3,4,5; Lu, Denghui 6; Mo, Pinghui 7; Li, Zeyu 8; Chen, Yixiao 9; Rynik, Marian 10; Huang, Li'ang 11; Li, Ziyao 4,12; Shi, Shaochen 13; Wang, Yingze 4,14; Ye, Haotian 8; Tuo, Ping 3; Yang, Jiabin 15; Ding, Ye 16,17; Li, Yifan 18; Tisi, Davide 19,20; Zeng, Qiyu 21; Bao, Han 22,23; Xia, Yu 13; Huang, Jiameng 4,24; Muraoka, Koki 25; Wang, Yibo 4; Chang, Junhan 4,14; Yuan, Fengbo 4; Bore, Sigbjorn Loland 26,27; Cai, Chun 3,4; Lin, Yinnian 28; Wang, Bo 29; Xu, Jiayan 30; Zhu, Jia-Xin 31; Luo, Chenxing 32; Zhang, Yuzhi 4; Goodall, Rhys E. A.; Liang, Wenshuo 4; Singh, Anurag Kumar 33; Yao, Sikai 4; Zhang, Jingchao 34; Wentzcovitch, Renata 32,35; Han, Jiequn 36; Liu, Jie 7; Jia, Weile 22,23; York, Darrin M.1,2; E, Weinan 3,37,38; Car, Roberto 18; Zhang, Linfeng 3,4; Wang, Han 6,39
	2023-08-07
发表期刊	JOURNAL OF CHEMICAL PHYSICS
ISSN	0021-9606
卷号	159 期号:5 页码:24
摘要	DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of DeePMD-kit offers numerous advanced features, such as DeepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, DP-range correction, DP long range, graphics processing unit support for customized operators, model compression, non-von Neumann molecular dynamics, and improved usability, including documentation, compiled binary packages, graphical user interfaces, and application programming interfaces. This article presents an overview of the current major version of the DeePMD-kit package, highlighting its features and technical details. Additionally, this article presents a comprehensive procedure for conducting molecular dynamics as a representative application, benchmarks the accuracy and efficiency of different models, and discusses ongoing developments.
DOI	10.1063/5.0155600
收录类别	SCI
语种	英语
资助项目	National Institutes of Health[GM107485] ; National Science Foundation[2138259] ; National Science Foundation[2138286] ; National Science Foundation[2138307] ; National Science Foundation[2137603] ; National Science Foundation[2138296] ; National Science Foundation[CHE190067] ; Van Dyke Award from the Department of Chemistry and Chemical Biology, Rutgers ; VEGA[APVV-19-0371] ; Slovak Research and Development Agency[2021RC4026] ; Science and Technology Innovation Program of Hunan Province[262695] ; Research Council of Norway through the Centre of Excellence Hylleraas Centre for Quantum Molecular Sciences[DE-SC0019759] ; United States Department of Energy (DOE)[2022YFA1004300] ; National Key Ramp;D Program of China[12122103] ; National Natural Science Foundation of China[CHE20002] ; State University of New Jersey ; Advanced Cyberinfrastructure Coordination Ecosystem: Services amp; Support (ACCESS) program ; Chemistry in Solution and at Interfaces (CSI) Center - United States Department of Energy ; Texas Advanced Computing Center (TACC) at the University of Texas at Austin[DE-SC0019394] ; Princeton Research Computing resources at Princeton University ; AMD Cloud Platform at AMD, Inc ; [1/0640/20]
WOS研究方向	Chemistry ; Physics
WOS类目	Chemistry, Physical ; Physics, Atomic, Molecular & Chemical
WOS记录号	WOS:001041174500011
出版者	AIP Publishing
引用统计	被引频次：107[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21344
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Han
作者单位	1.Rutgers State Univ, Inst Quantitat Biomed, Lab Biomol Simulat Res, Piscataway, NJ 08854 USA 2.Rutgers State Univ, Dept Chem & Chem Biol, Piscataway, NJ 08854 USA 3.AI Sci Inst, Beijing 100080, Peoples R China 4.DP Technol, Beijing 100080, Peoples R China 5.Peking Univ, Acad Adv Interdisciplinary Studies, Beijing 100871, Peoples R China 6.Peking Univ, Coll Engn, HEDPS, CAPT, Beijing 100871, Peoples R China 7.Hunan Univ, Coll Elect & Informat Engn, Changsha, Peoples R China 8.Peking Univ, Yuanpei Coll, Beijing 100871, Peoples R China 9.Princeton Univ, Program Appl & Computat Math, Princeton, NJ 08540 USA 10.Comenius Univ, Dept Expt Phys, Mlynska Dolina F2, Bratislava 84248, Slovakia 11.Tsinghua Univ, Inst Interdisciplinary Informat Sci, Ctr Quantum Informat, Beijing 100084, Peoples R China 12.Peking Univ, Ctr Data Sci, Beijing 100871, Peoples R China 13.ByteDance Res, Zhonghang Plaza,43, North 3rd Ring West Rd, Beijing, Peoples R China 14.Peking Univ, Coll Chem & Mol Engn, Beijing 100871, Peoples R China 15.Baidu Inc, Beijing, Peoples R China 16.Westlake Univ, Sch Life Sci, Key Lab Struct Biol Zhejiang Prov, Hangzhou, Zhejiang, Peoples R China 17.Westlake Lab Life Sci & Biomed, Westlake AI Therapeut Lab, Hangzhou, Zhejiang, Peoples R China 18.Princeton Univ, Dept Chem, Princeton, NJ 08544 USA 19.SISSA, I-34136 Trieste, Italy 20.Ecole Polytech Fed Lausanne, Inst Mat, Lab Computat Sci & Modeling, CH-1015 Lausanne, Switzerland 21.Natl Univ Def Technol, Dept Phys, Changsha 410073, Hunan, Peoples R China 22.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing, Peoples R China 23.Univ Chinese Acad Sci, Beijing, Peoples R China 24.Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China 25.Univ Tokyo, Dept Chem Syst Engn, 7-3-1 Hongo,Bunkyo Ku, Tokyo 1138656, Japan 26.Univ Oslo, Hylleraas Ctr Quantum Mol Sci, POB 1033 Blindern, N-0315 Oslo, Norway 27.Univ Oslo, Dept Chem, POB 1033 Blindern, N-0315 Oslo, Norway 28.Peking Univ, Wangxuan Inst Comp Technol, Beijing 100871, Peoples R China 29.East China Normal Univ, Shanghai Engn Res Ctr Mol Therapeut & New Drug Dev, Shanghai Key Lab ofGreen Chem & Chem Proc, Sch Chem & Mol Engn, Shanghai 200062, Peoples R China 30.Queens Univ Belfast, Sch Chem & Chem Engn, Belfast BT9 5AG, North Ireland 31.Xiamen Univ, Coll Chem & Chem Engn, State Key Lab Phys Chem Solid Surfaces, iChEM, Xiamen 361005, Peoples R China 32.Columbia Univ, Dept Appl Phys & Appl Math, New York, NY 10027 USA 33.Indian Inst Technol, Dept Data Sci, Palakkad, Kerala, India 34.NVIDIA Technol Ctr NVAITC, Santa Clara, CA 95051 USA 35.Columbia Univ, Dept Earth & Environm Sci, New York, NY 10027 USA 36.Flatiron Inst, Ctr Computat Math, New York, NY 10010 USA 37.Peking Univ, Ctr Machine Learning Res, Beijing 100871, Peoples R China 38.Peking Univ, Sch Math Sci, Beijing 100871, Peoples R China 39.Inst Appl Phys & Computat Math, Lab Computat Phys, Fenghao East Rd 2, Beijing 100094, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Jinzhe,Zhang, Duo,Lu, Denghui,et al. DeePMD-kit v2: A software package for deep potential models[J]. JOURNAL OF CHEMICAL PHYSICS,2023,159(5):24.
APA	Zeng, Jinzhe.,Zhang, Duo.,Lu, Denghui.,Mo, Pinghui.,Li, Zeyu.,...&Wang, Han.(2023).DeePMD-kit v2: A software package for deep potential models.JOURNAL OF CHEMICAL PHYSICS,159(5),24.
MLA	Zeng, Jinzhe,et al."DeePMD-kit v2: A software package for deep potential models".JOURNAL OF CHEMICAL PHYSICS 159.5(2023):24.