利用基于生成变压器架构的神经网络精确计算原子间作用力

IF 8.3 2区 材料科学 Q1 MATERIALS SCIENCE, MULTIDISCIPLINARY ACS Applied Materials & Interfaces Pub Date : 2024-10-23 DOI:10.1021/acs.jctc.4c0120510.1021/acs.jctc.4c01205
Juntao Lai, Bowen Kan, Yangjun Wu, Qiang Fu*, Honghui Shang*, Zhenyu Li and Jinlong Yang*, 
{"title":"利用基于生成变压器架构的神经网络精确计算原子间作用力","authors":"Juntao Lai,&nbsp;Bowen Kan,&nbsp;Yangjun Wu,&nbsp;Qiang Fu*,&nbsp;Honghui Shang*,&nbsp;Zhenyu Li and Jinlong Yang*,&nbsp;","doi":"10.1021/acs.jctc.4c0120510.1021/acs.jctc.4c01205","DOIUrl":null,"url":null,"abstract":"<p >Using neural networks to express electronic wave functions represents a new paradigm for solving the Schrödinger equation in quantum chemistry. For practical quantum chemistry simulations, one needs to know not only energies of molecules, but also accurate forces acting on constituent atoms. In this work, we achieve the accurate calculation of interatomic forces on QiankunNet, a platform that combines transformer-based deep neural networks with efficient batched autoregressive sampling. Our approach permits the application of the Hellmann–Feynman theorem to force calculations without introducing corrective Pulay terms. The results show that the calculated interatomic forces are in close agreement with those derived from the full configuration interaction method, irrespective of whether the system is a simple molecule or a strongly correlated electron system like a linear hydrogen chain. Furthermore, the calculated interatomic forces are employed for atomic relaxation in the torsional rotation process of ethylene, and the energy barrier obtained from the scanned potential energy surface is in excellent agreement with the experiment. Our work contributes to the application of artificial intelligence to broader quantum chemistry simulations, such as modeling challenging chemical transformations where electron correlations are difficult to describe.</p>","PeriodicalId":5,"journal":{"name":"ACS Applied Materials & Interfaces","volume":null,"pages":null},"PeriodicalIF":8.3000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Accurate Calculation of Interatomic Forces with Neural Networks Based on a Generative Transformer Architecture\",\"authors\":\"Juntao Lai,&nbsp;Bowen Kan,&nbsp;Yangjun Wu,&nbsp;Qiang Fu*,&nbsp;Honghui Shang*,&nbsp;Zhenyu Li and Jinlong Yang*,&nbsp;\",\"doi\":\"10.1021/acs.jctc.4c0120510.1021/acs.jctc.4c01205\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Using neural networks to express electronic wave functions represents a new paradigm for solving the Schrödinger equation in quantum chemistry. For practical quantum chemistry simulations, one needs to know not only energies of molecules, but also accurate forces acting on constituent atoms. In this work, we achieve the accurate calculation of interatomic forces on QiankunNet, a platform that combines transformer-based deep neural networks with efficient batched autoregressive sampling. Our approach permits the application of the Hellmann–Feynman theorem to force calculations without introducing corrective Pulay terms. The results show that the calculated interatomic forces are in close agreement with those derived from the full configuration interaction method, irrespective of whether the system is a simple molecule or a strongly correlated electron system like a linear hydrogen chain. Furthermore, the calculated interatomic forces are employed for atomic relaxation in the torsional rotation process of ethylene, and the energy barrier obtained from the scanned potential energy surface is in excellent agreement with the experiment. Our work contributes to the application of artificial intelligence to broader quantum chemistry simulations, such as modeling challenging chemical transformations where electron correlations are difficult to describe.</p>\",\"PeriodicalId\":5,\"journal\":{\"name\":\"ACS Applied Materials & Interfaces\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.3000,\"publicationDate\":\"2024-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Applied Materials & Interfaces\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://pubs.acs.org/doi/10.1021/acs.jctc.4c01205\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Materials & Interfaces","FirstCategoryId":"92","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acs.jctc.4c01205","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

使用神经网络来表达电子波函数是解决量子化学中薛定谔方程的一种新模式。在实际的量子化学模拟中,人们不仅需要知道分子的能量,还需要知道作用在组成原子上的精确力。在这项工作中,我们在乾坤网上实现了原子间作用力的精确计算。乾坤网是一个将基于变压器的深度神经网络与高效的批次自回归采样相结合的平台。我们的方法允许将赫尔曼-费曼定理应用于力计算,而无需引入校正普雷项。结果表明,无论系统是简单的分子还是线性氢链等强相关电子系统,计算出的原子间作用力都与全构型相互作用方法得出的原子间作用力非常接近。此外,在乙烯的扭转旋转过程中,利用计算出的原子间力进行原子弛豫,从扫描势能面得到的能量势垒与实验结果非常吻合。我们的工作有助于将人工智能应用于更广泛的量子化学模拟,例如模拟电子关联难以描述的高难度化学转化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Accurate Calculation of Interatomic Forces with Neural Networks Based on a Generative Transformer Architecture

Using neural networks to express electronic wave functions represents a new paradigm for solving the Schrödinger equation in quantum chemistry. For practical quantum chemistry simulations, one needs to know not only energies of molecules, but also accurate forces acting on constituent atoms. In this work, we achieve the accurate calculation of interatomic forces on QiankunNet, a platform that combines transformer-based deep neural networks with efficient batched autoregressive sampling. Our approach permits the application of the Hellmann–Feynman theorem to force calculations without introducing corrective Pulay terms. The results show that the calculated interatomic forces are in close agreement with those derived from the full configuration interaction method, irrespective of whether the system is a simple molecule or a strongly correlated electron system like a linear hydrogen chain. Furthermore, the calculated interatomic forces are employed for atomic relaxation in the torsional rotation process of ethylene, and the energy barrier obtained from the scanned potential energy surface is in excellent agreement with the experiment. Our work contributes to the application of artificial intelligence to broader quantum chemistry simulations, such as modeling challenging chemical transformations where electron correlations are difficult to describe.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
ACS Applied Materials & Interfaces
ACS Applied Materials & Interfaces 工程技术-材料科学:综合
CiteScore
16.00
自引率
6.30%
发文量
4978
审稿时长
1.8 months
期刊介绍: ACS Applied Materials & Interfaces is a leading interdisciplinary journal that brings together chemists, engineers, physicists, and biologists to explore the development and utilization of newly-discovered materials and interfacial processes for specific applications. Our journal has experienced remarkable growth since its establishment in 2009, both in terms of the number of articles published and the impact of the research showcased. We are proud to foster a truly global community, with the majority of published articles originating from outside the United States, reflecting the rapid growth of applied research worldwide.
期刊最新文献
Decreased levels of phosphorylated synuclein in plasma are correlated with poststroke cognitive impairment. Small molecule inhibitor DDQ-treated hippocampal neuronal cells show improved neurite outgrowth and synaptic branching. Polyethylene glycol fusion repair of severed sciatic nerves accelerates recovery of nociceptive sensory perceptions in male and female rats of different strains. Reduced mesencephalic astrocyte-derived neurotrophic factor expression by mutant androgen receptor contributes to neurodegeneration in a model of spinal and bulbar muscular atrophy pathology. Enhanced autophagic clearance of amyloid-β via histone deacetylase 6-mediated V-ATPase assembly and lysosomal acidification protects against Alzheimer's disease in vitro and in vivo.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1