Chengbing Chen , Yutong Li , Rui Zhao , Zhoulin Liu , Zheyong Fan , Gang Tang , Zhiyong Wang
{"title":"NepTrain and NepTrainKit: Automated active learning and visualization toolkit for neuroevolution potentials","authors":"Chengbing Chen , Yutong Li , Rui Zhao , Zhoulin Liu , Zheyong Fan , Gang Tang , Zhiyong Wang","doi":"10.1016/j.cpc.2025.109859","DOIUrl":null,"url":null,"abstract":"<div><div>As a machine-learned potential, the neuroevolution potential (NEP) method features exceptional computational efficiency and has been successfully applied in materials science. Constructing high-quality training datasets is crucial for developing accurate NEP models. However, the preparation and screening of NEP training datasets remain a bottleneck for broader applications due to their time-consuming, labor-intensive, and resource-intensive nature. In this work, we have developed NepTrain and NepTrainKit, which are dedicated to initializing and managing training datasets to generate high-quality training sets while automating NEP model training. NepTrain is an open-source Python package that features a bond length filtering method to effectively identify and remove non-physical structures from molecular dynamics trajectories, thereby ensuring high-quality training datasets. NepTrainKit is a graphical user interface (GUI) software designed specifically for NEP training datasets, providing functionalities for data editing, visualization, and interactive exploration. It integrates key features such as outlier identification, farthest-point sampling, non-physical structure detection, and configuration type selection. The combination of these tools enables users to process datasets more efficiently and conveniently. Using <span><math><mi>CsPb</mi><msub><mrow><mi>I</mi></mrow><mrow><mn>3</mn></mrow></msub></math></span> as a case study, we demonstrate the complete workflow for training NEP models with NepTrain and further validate the models through materials property predictions. We believe this toolkit will greatly benefit researchers working with machine learning interatomic potentials.</div></div><div><h3>Program summary</h3><div><em>Program Title:</em> NepTrain and NepTrainKit</div><div><em>CPC Library link to program files:</em> <span><span>https://doi.org/10.17632/4s97yg7j9t.1</span><svg><path></path></svg></span></div><div><em>Developer's repository link:</em> <span><span>https://github.com/aboys-cb/NepTrain</span><svg><path></path></svg></span> and <span><span>https://github.com/aboys-cb/NepTrainKit</span><svg><path></path></svg></span></div><div><em>Licensing provisions:</em> GPLv3</div><div><em>Programming language:</em> Python</div><div><em>Nature of problem:</em> The NEP method, a novel machine learning potential model, has demonstrated broad application prospects in materials science due to its excellent computational efficiency. However, the development of accurate NEP models heavily depends on the construction of high-quality training datasets. The preparation and iterative refinement of these datasets largely rely on the researcher's expertise, which poses a significant barrier for beginners attempting to use NEP and similar machine learning potential methods.</div><div><em>Solution method:</em> NepTrain is an open-source Python package that features a bond length filtering method to effectively identify and remove non-physical structures from molecular dynamics trajectories, thereby ensuring high-quality training datasets. NepTrainKit is a graphical user interface (GUI) software designed specifically for NEP training datasets, providing functionalities for data editing, visualization, and interactive exploration. It integrates key features such as outlier identification, farthest-point sampling, non-physical structure detection, and configuration type selection.</div></div>","PeriodicalId":285,"journal":{"name":"Computer Physics Communications","volume":"317 ","pages":"Article 109859"},"PeriodicalIF":3.4000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Physics Communications","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0010465525003613","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
As a machine-learned potential, the neuroevolution potential (NEP) method features exceptional computational efficiency and has been successfully applied in materials science. Constructing high-quality training datasets is crucial for developing accurate NEP models. However, the preparation and screening of NEP training datasets remain a bottleneck for broader applications due to their time-consuming, labor-intensive, and resource-intensive nature. In this work, we have developed NepTrain and NepTrainKit, which are dedicated to initializing and managing training datasets to generate high-quality training sets while automating NEP model training. NepTrain is an open-source Python package that features a bond length filtering method to effectively identify and remove non-physical structures from molecular dynamics trajectories, thereby ensuring high-quality training datasets. NepTrainKit is a graphical user interface (GUI) software designed specifically for NEP training datasets, providing functionalities for data editing, visualization, and interactive exploration. It integrates key features such as outlier identification, farthest-point sampling, non-physical structure detection, and configuration type selection. The combination of these tools enables users to process datasets more efficiently and conveniently. Using as a case study, we demonstrate the complete workflow for training NEP models with NepTrain and further validate the models through materials property predictions. We believe this toolkit will greatly benefit researchers working with machine learning interatomic potentials.
Program summary
Program Title: NepTrain and NepTrainKit
CPC Library link to program files:https://doi.org/10.17632/4s97yg7j9t.1
Developer's repository link:https://github.com/aboys-cb/NepTrain and https://github.com/aboys-cb/NepTrainKit
Licensing provisions: GPLv3
Programming language: Python
Nature of problem: The NEP method, a novel machine learning potential model, has demonstrated broad application prospects in materials science due to its excellent computational efficiency. However, the development of accurate NEP models heavily depends on the construction of high-quality training datasets. The preparation and iterative refinement of these datasets largely rely on the researcher's expertise, which poses a significant barrier for beginners attempting to use NEP and similar machine learning potential methods.
Solution method: NepTrain is an open-source Python package that features a bond length filtering method to effectively identify and remove non-physical structures from molecular dynamics trajectories, thereby ensuring high-quality training datasets. NepTrainKit is a graphical user interface (GUI) software designed specifically for NEP training datasets, providing functionalities for data editing, visualization, and interactive exploration. It integrates key features such as outlier identification, farthest-point sampling, non-physical structure detection, and configuration type selection.
期刊介绍:
The focus of CPC is on contemporary computational methods and techniques and their implementation, the effectiveness of which will normally be evidenced by the author(s) within the context of a substantive problem in physics. Within this setting CPC publishes two types of paper.
Computer Programs in Physics (CPiP)
These papers describe significant computer programs to be archived in the CPC Program Library which is held in the Mendeley Data repository. The submitted software must be covered by an approved open source licence. Papers and associated computer programs that address a problem of contemporary interest in physics that cannot be solved by current software are particularly encouraged.
Computational Physics Papers (CP)
These are research papers in, but are not limited to, the following themes across computational physics and related disciplines.
mathematical and numerical methods and algorithms;
computational models including those associated with the design, control and analysis of experiments; and
algebraic computation.
Each will normally include software implementation and performance details. The software implementation should, ideally, be available via GitHub, Zenodo or an institutional repository.In addition, research papers on the impact of advanced computer architecture and special purpose computers on computing in the physical sciences and software topics related to, and of importance in, the physical sciences may be considered.