DeePMD-kit v2: A software package for deep potential models-Reference-Cited by-同舟云学术

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

Published:2023-08-01 Issue:5 Volume:159 Page:
ISSN:0021-9606
Container-title:The Journal of Chemical Physics
language:en
Short-container-title:

Author:

Zeng Jinzhe¹^ORCID,Zhang Duo²³⁴^ORCID,Lu Denghui⁵^ORCID,Mo Pinghui⁶^ORCID,Li Zeyu⁷^ORCID,Chen Yixiao⁸^ORCID,Rynik Marián⁹^ORCID,Huang Li’ang¹⁰^ORCID,Li Ziyao¹³^ORCID,Shi Shaochen¹¹^ORCID,Wang Yingze¹³,Ye Haotian⁷^ORCID,Tuo Ping²^ORCID,Yang Jiabin¹²,Ding Ye¹^ORCID,Li Yifan¹³^ORCID,Tisi Davide¹^ORCID,Zeng Qiyu¹⁴^ORCID,Bao Han²^ORCID,Xia Yu¹¹^ORCID,Huang Jiameng²³^ORCID,Muraoka Koki¹⁵^ORCID,Wang Yibo³^ORCID,Chang Junhan¹³^ORCID,Yuan Fengbo³^ORCID,Bore Sigbjørn Løland¹⁶^ORCID,Cai Chun²³^ORCID,Lin Yinnian¹⁷^ORCID,Wang Bo¹⁸^ORCID,Xu Jiayan¹⁹^ORCID,Zhu Jia-Xin²⁰^ORCID,Luo Chenxing²¹^ORCID,Zhang Yuzhi³^ORCID,Goodall Rhys E. A.²²^ORCID,Liang Wenshuo³^ORCID,Singh Anurag Kumar²³^ORCID,Yao Sikai³^ORCID,Zhang Jingchao²⁴^ORCID,Wentzcovitch Renata³^ORCID,Han Jiequn²⁵^ORCID,Liu Jie⁶^ORCID,Jia Weile²^ORCID,York Darrin M.¹^ORCID,E Weinan²³^ORCID,Car Roberto¹³^ORCID,Zhang Linfeng²³^ORCID,Wang Han³⁵^ORCID

Affiliation:

1. Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University 1 , Piscataway, New Jersey 08854, USA

2. AI for Science Institute 2 , Beijing 100080, People’s Republic of China

3. DP Technology 3 , Beijing 100080, People’s Republic of China

4. Academy for Advanced Interdisciplinary Studies, Peking University 4 , Beijing 100871, People’s Republic of China

5. HEDPS, CAPT, College of Engineering, Peking University 5 , Beijing 100871, People’s Republic of China

6. College of Electrical and Information Engineering, Hunan University 6 , Changsha, People’s Republic of China

7. Yuanpei College, Peking University 7 , Beijing 100871, People’s Republic of China

8. Program in Applied and Computational Mathematics, Princeton University 8 , Princeton, New Jersey 08540, USA

9. Department of Experimental Physics, Comenius University 9 , Mlynská Dolina F2, 842 48 Bratislava, Slovakia

10. Center for Quantum Information, Institute for Interdisciplinary Information Sciences, Tsinghua University 10 , Beijing 100084, People’s Republic of China

11. ByteDance Research, Zhonghang Plaza 12 , No. 43, North 3rd Ring West Road, Haidian District, Beijing, People’s Republic of China

12. Baidu, Inc. 14 , Beijing, People’s Republic of China

13. Department of Chemistry, Princeton University 17 , Princeton, New Jersey 08544, USA

14. Department of Physics, National University of Defense Technology 20 , Changsha, Hunan 410073, People’s Republic of China

15. Department of Chemical System Engineering, The University of Tokyo 24 , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

16. Hylleraas Centre for Quantum Molecular Sciences and Department of Chemistry, University of Oslo 25 , P.O. Box 1033 Blindern, 0315 Oslo, Norway

17. Wangxuan Institute of Computer Technology, Peking University 26 , Beijing 100871, People’s Republic of China

18. Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Key Laboratory of Green Chemistry and Chemical Process, School of Chemistry and Molecular Engineering, East China Normal University 27 , Shanghai 200062, People’s Republic of China

19. School of Chemistry and Chemical Engineering, Queen’s University Belfast 28 , Belfast BT9 5AG, United Kingdom

20. State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University 29 , Xiamen 361005, People’s Republic of China

21. Department of Applied Physics and Applied Mathematics, Columbia University 30 , New York, New York 10027, USA

22. Independent Researcher 31 , London, United Kingdom

23. Department of Data Science, Indian Institute of Technology 32 , Palakkad, Kerala, India

24. NVIDIA AI Technology Center (NVAITC) 33 , Santa Clara, California 95051, USA

25. Center for Computational Mathematics, Flatiron Institute 35 , New York, New York 10010, USA

Abstract

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.

Funder

National Institutes of Health

National Science Foundation

U.S. Department of Energy

Slovak Research and Development Agency

Slovak Science Grant Agency

Hunan Provincial Science and Technology Department

Research Council of Norway

National Key Research and Development Program of China

National Natural Science Foundation of China

Publisher

AIP Publishing