Universal neural network potentials as descriptors: towards scalable chemical property prediction using quantum and classical computers

IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Digital discovery Pub Date : 2024-07-16 DOI:10.1039/D4DD00098F
Tomoya Shiota, Kenji Ishihara and Wataru Mizukami
{"title":"Universal neural network potentials as descriptors: towards scalable chemical property prediction using quantum and classical computers","authors":"Tomoya Shiota, Kenji Ishihara and Wataru Mizukami","doi":"10.1039/D4DD00098F","DOIUrl":null,"url":null,"abstract":"<p >Accurate prediction of diverse chemical properties is crucial for advancing molecular design and materials discovery. Here we present a versatile approach that uses the intermediate information of a universal neural network potential as a general-purpose descriptor for chemical property prediction. Our method is based on the insight that by training a sophisticated neural network architecture for universal force fields, it learns transferable representations of atomic environments. We show that transfer learning with graph neural network potentials such as M3GNet and MACE achieves accuracy comparable to state-of-the-art methods for predicting the NMR chemical shifts by using quantum machine learning as well as a standard classical regression model, despite the compactness of its descriptors. In particular, the MACE descriptor demonstrates the highest accuracy to date on the <small><sup>13</sup></small>C NMR chemical shift benchmarks for drug molecules. This work provides an efficient way to accurately predict properties, potentially accelerating the discovery of new molecules and materials.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 9","pages":" 1714-1728"},"PeriodicalIF":6.2000,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00098f?page=search","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital discovery","FirstCategoryId":"1085","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00098f","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate prediction of diverse chemical properties is crucial for advancing molecular design and materials discovery. Here we present a versatile approach that uses the intermediate information of a universal neural network potential as a general-purpose descriptor for chemical property prediction. Our method is based on the insight that by training a sophisticated neural network architecture for universal force fields, it learns transferable representations of atomic environments. We show that transfer learning with graph neural network potentials such as M3GNet and MACE achieves accuracy comparable to state-of-the-art methods for predicting the NMR chemical shifts by using quantum machine learning as well as a standard classical regression model, despite the compactness of its descriptors. In particular, the MACE descriptor demonstrates the highest accuracy to date on the 13C NMR chemical shift benchmarks for drug molecules. This work provides an efficient way to accurately predict properties, potentially accelerating the discovery of new molecules and materials.

Abstract Image

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
作为描述符的通用神经网络势:利用量子和经典计算机实现可扩展的化学性质预测
准确预测各种化学特性对于推进分子设计和材料发现至关重要。在这里,我们提出了一种多功能方法,利用通用神经网络势的中间信息作为化学性质预测的通用描述符。我们的方法基于这样一种见解,即通过训练通用力场的复杂神经网络架构,它可以学习原子环境的可迁移表征。我们的研究表明,利用 M3GNet 和 MACE 等图神经网络潜能进行迁移学习,尽管其描述符非常紧凑,但在预测核磁共振化学位移方面,其准确性可与使用量子机器学习和标准经典回归模型的最先进方法相媲美。特别是,MACE 描述子在药物分子的 ${^{13}}$C NMR 化学位移基准上显示了迄今为止最高的准确度。这项工作提供了一种准确预测性质的有效方法,有可能加速新分子和新材料的发现。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
2.80
自引率
0.00%
发文量
0
期刊最新文献
Back cover ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials. Sorting polyolefins with near-infrared spectroscopy: identification of optimal data analysis pipelines and machine learning classifiers†‡ High accuracy uncertainty-aware interatomic force modeling with equivariant Bayesian neural networks† Correction: A smile is all you need: predicting limiting activity coefficients from SMILES with natural language processing
×
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