关于设计最佳计算机实验来模拟溶剂对反应动力学的影响

IF 3.2 3区 工程技术 Q2 CHEMISTRY, PHYSICAL Molecular Systems Design & Engineering Pub Date : 2024-09-06 DOI:10.1039/D4ME00074A
Lingfeng Gui, Alan Armstrong, Amparo Galindo, Fareed Bhasha Sayyed, Stanley P. Kolis and Claire S. Adjiman
{"title":"关于设计最佳计算机实验来模拟溶剂对反应动力学的影响","authors":"Lingfeng Gui, Alan Armstrong, Amparo Galindo, Fareed Bhasha Sayyed, Stanley P. Kolis and Claire S. Adjiman","doi":"10.1039/D4ME00074A","DOIUrl":null,"url":null,"abstract":"<p >Developing an accurate predictive model of solvent effects on reaction kinetics is a challenging task, yet it can play an important role in process development. While first-principles or machine learning models are often compute- or data-intensive, simple surrogate models, such as multivariate linear or quadratic regression models, are useful when computational resources and data are scarce. The judicious choice of a small set of training data, <em>i.e.</em>, a set of solvents in which quantum mechanical (QM) calculations of liquid-phase rate constants are to be performed, is critical to obtaining a reliable model. This is, however, made especially challenging by the highly irregular shape of the discrete space of possible experiments (solvent choices). In this work, we demonstrate that when choosing a set of computer experiments to generate training data, the D-optimality criterion value of the chosen set correlates well with the likelihood of achieving good model performance. With the Menshutkin reaction of pyridine and phenacyl bromide as a case study, this finding is further verified <em>via</em> the evaluation of the surrogate models regressed using D-optimal solvent sets generated from four distinct selection spaces. We also find that incorporating quadratic terms in the surrogate model and choosing the D-optimal solvent set from a selection space similar to the test set can significantly improve the accuracy of reaction rate constant predictions while using a small training dataset. Our approach holds promise for the use of statistical optimality criteria for other types of computer experiments, supporting the construction of surrogate models with reduced resource and data requirements.</p>","PeriodicalId":91,"journal":{"name":"Molecular Systems Design & Engineering","volume":" 12","pages":" 1254-1274"},"PeriodicalIF":3.2000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/me/d4me00074a?page=search","citationCount":"0","resultStr":"{\"title\":\"On the design of optimal computer experiments to model solvent effects on reaction kinetics†\",\"authors\":\"Lingfeng Gui, Alan Armstrong, Amparo Galindo, Fareed Bhasha Sayyed, Stanley P. Kolis and Claire S. Adjiman\",\"doi\":\"10.1039/D4ME00074A\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Developing an accurate predictive model of solvent effects on reaction kinetics is a challenging task, yet it can play an important role in process development. While first-principles or machine learning models are often compute- or data-intensive, simple surrogate models, such as multivariate linear or quadratic regression models, are useful when computational resources and data are scarce. The judicious choice of a small set of training data, <em>i.e.</em>, a set of solvents in which quantum mechanical (QM) calculations of liquid-phase rate constants are to be performed, is critical to obtaining a reliable model. This is, however, made especially challenging by the highly irregular shape of the discrete space of possible experiments (solvent choices). In this work, we demonstrate that when choosing a set of computer experiments to generate training data, the D-optimality criterion value of the chosen set correlates well with the likelihood of achieving good model performance. With the Menshutkin reaction of pyridine and phenacyl bromide as a case study, this finding is further verified <em>via</em> the evaluation of the surrogate models regressed using D-optimal solvent sets generated from four distinct selection spaces. We also find that incorporating quadratic terms in the surrogate model and choosing the D-optimal solvent set from a selection space similar to the test set can significantly improve the accuracy of reaction rate constant predictions while using a small training dataset. Our approach holds promise for the use of statistical optimality criteria for other types of computer experiments, supporting the construction of surrogate models with reduced resource and data requirements.</p>\",\"PeriodicalId\":91,\"journal\":{\"name\":\"Molecular Systems Design & Engineering\",\"volume\":\" 12\",\"pages\":\" 1254-1274\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://pubs.rsc.org/en/content/articlepdf/2024/me/d4me00074a?page=search\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Molecular Systems Design & Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://pubs.rsc.org/en/content/articlelanding/2024/me/d4me00074a\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Molecular Systems Design & Engineering","FirstCategoryId":"5","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/me/d4me00074a","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

就溶剂对反应动力学的影响建立精确的预测模型是一项极具挑战性的任务,但却能在工艺开发中发挥重要作用。第一原理或机器学习模型通常是计算或数据密集型的,而简单的代用模型,如多元线性或二次回归模型,在计算资源和数据稀缺的情况下非常有用。要获得可靠的模型,明智地选择一小组训练数据(即一组溶剂,在其中对液相速率常数进行量子力学(QM)计算)至关重要。然而,由于可能的实验(溶剂选择)的离散空间形状极不规则,这尤其具有挑战性。在这项工作中,我们证明了在选择一组计算机实验来生成训练数据时,所选实验组的 D-optimality 标准值与获得良好模型性能的可能性密切相关。以吡啶和苯酰溴的 Menschutkin 反应为例,通过评估使用从四个不同选择空间生成的 D-最优溶剂集回归的代用模型,进一步验证了这一发现。我们还发现,在代用模型中加入二次项,并从与测试集类似的选择空间中选择 D 最佳溶剂集,可以显著提高反应速率常数预测的准确性,同时只需使用少量的训练数据集。我们的方法有望在其他类型的计算机实验中使用统计最优性标准,支持在减少资源和数据需求的情况下构建代用模型。
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
On the design of optimal computer experiments to model solvent effects on reaction kinetics†

Developing an accurate predictive model of solvent effects on reaction kinetics is a challenging task, yet it can play an important role in process development. While first-principles or machine learning models are often compute- or data-intensive, simple surrogate models, such as multivariate linear or quadratic regression models, are useful when computational resources and data are scarce. The judicious choice of a small set of training data, i.e., a set of solvents in which quantum mechanical (QM) calculations of liquid-phase rate constants are to be performed, is critical to obtaining a reliable model. This is, however, made especially challenging by the highly irregular shape of the discrete space of possible experiments (solvent choices). In this work, we demonstrate that when choosing a set of computer experiments to generate training data, the D-optimality criterion value of the chosen set correlates well with the likelihood of achieving good model performance. With the Menshutkin reaction of pyridine and phenacyl bromide as a case study, this finding is further verified via the evaluation of the surrogate models regressed using D-optimal solvent sets generated from four distinct selection spaces. We also find that incorporating quadratic terms in the surrogate model and choosing the D-optimal solvent set from a selection space similar to the test set can significantly improve the accuracy of reaction rate constant predictions while using a small training dataset. Our approach holds promise for the use of statistical optimality criteria for other types of computer experiments, supporting the construction of surrogate models with reduced resource and data requirements.

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
Molecular Systems Design & Engineering
Molecular Systems Design & Engineering Engineering-Biomedical Engineering
CiteScore
6.40
自引率
2.80%
发文量
144
期刊介绍: Molecular Systems Design & Engineering provides a hub for cutting-edge research into how understanding of molecular properties, behaviour and interactions can be used to design and assemble better materials, systems, and processes to achieve specific functions. These may have applications of technological significance and help address global challenges.
期刊最新文献
Back cover Back cover Dual responsive fluorescence switching of organohydrogel towards base/acid† Back cover Graph-based networks for accurate prediction of ground and excited state molecular properties from minimal features†
×
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