Yeonjoon Kim , Jaeyoung Cho , Hojin Jung , Lydia E. Meyer , Gina M. Fioroni , Christopher D. Stubbs , Keunhong Jeong , Robert L. McCormick , Peter C. St. John , Seonah Kim
{"title":"利用可解释图注意网络预测汽化特性,设计绿色化学品","authors":"Yeonjoon Kim , Jaeyoung Cho , Hojin Jung , Lydia E. Meyer , Gina M. Fioroni , Christopher D. Stubbs , Keunhong Jeong , Robert L. McCormick , Peter C. St. John , Seonah Kim","doi":"10.1039/d4gc01994f","DOIUrl":null,"url":null,"abstract":"<div><div>Computational predictions of vaporization properties aid the <em>de novo</em> design of green chemicals, including clean alternative fuels, working fluids for efficient thermal energy recovery, and polymers that are easily degradable and recyclable. Here, we developed chemically explainable graph attention networks to predict five physical properties pertinent to performance in utilizing renewable energy: heat of vaporization (HoV), critical temperature, flash point, boiling point, and liquid heat capacity. The predictive model for HoV was trained using ∼150 000 data points, considering their uncertainties and temperature dependence. Next, this model was expanded to the other properties through transfer learning to overcome the limitations due to fewer data points (700–7500). The chemical interpretability of the model was then investigated, demonstrating that the model explains molecular structural effects on vaporization properties. Finally, the developed predictive models were applied to design chemicals that have desirable properties as efficient and green working fluids, fuels, and polymers, enabling fast and accurate screening before experiments.</div></div>","PeriodicalId":9,"journal":{"name":"ACS Catalysis ","volume":null,"pages":null},"PeriodicalIF":11.3000,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/gc/d4gc01994f?page=search","citationCount":"0","resultStr":"{\"title\":\"Designing green chemicals by predicting vaporization properties using explainable graph attention networks†\",\"authors\":\"Yeonjoon Kim , Jaeyoung Cho , Hojin Jung , Lydia E. Meyer , Gina M. Fioroni , Christopher D. Stubbs , Keunhong Jeong , Robert L. McCormick , Peter C. St. John , Seonah Kim\",\"doi\":\"10.1039/d4gc01994f\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Computational predictions of vaporization properties aid the <em>de novo</em> design of green chemicals, including clean alternative fuels, working fluids for efficient thermal energy recovery, and polymers that are easily degradable and recyclable. Here, we developed chemically explainable graph attention networks to predict five physical properties pertinent to performance in utilizing renewable energy: heat of vaporization (HoV), critical temperature, flash point, boiling point, and liquid heat capacity. The predictive model for HoV was trained using ∼150 000 data points, considering their uncertainties and temperature dependence. Next, this model was expanded to the other properties through transfer learning to overcome the limitations due to fewer data points (700–7500). The chemical interpretability of the model was then investigated, demonstrating that the model explains molecular structural effects on vaporization properties. Finally, the developed predictive models were applied to design chemicals that have desirable properties as efficient and green working fluids, fuels, and polymers, enabling fast and accurate screening before experiments.</div></div>\",\"PeriodicalId\":9,\"journal\":{\"name\":\"ACS Catalysis \",\"volume\":null,\"pages\":null},\"PeriodicalIF\":11.3000,\"publicationDate\":\"2024-09-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://pubs.rsc.org/en/content/articlepdf/2024/gc/d4gc01994f?page=search\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Catalysis \",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://www.sciencedirect.com/org/science/article/pii/S1463926224007787\",\"RegionNum\":1,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Catalysis ","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/org/science/article/pii/S1463926224007787","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
Designing green chemicals by predicting vaporization properties using explainable graph attention networks†
Computational predictions of vaporization properties aid the de novo design of green chemicals, including clean alternative fuels, working fluids for efficient thermal energy recovery, and polymers that are easily degradable and recyclable. Here, we developed chemically explainable graph attention networks to predict five physical properties pertinent to performance in utilizing renewable energy: heat of vaporization (HoV), critical temperature, flash point, boiling point, and liquid heat capacity. The predictive model for HoV was trained using ∼150 000 data points, considering their uncertainties and temperature dependence. Next, this model was expanded to the other properties through transfer learning to overcome the limitations due to fewer data points (700–7500). The chemical interpretability of the model was then investigated, demonstrating that the model explains molecular structural effects on vaporization properties. Finally, the developed predictive models were applied to design chemicals that have desirable properties as efficient and green working fluids, fuels, and polymers, enabling fast and accurate screening before experiments.
期刊介绍:
ACS Catalysis is an esteemed journal that publishes original research in the fields of heterogeneous catalysis, molecular catalysis, and biocatalysis. It offers broad coverage across diverse areas such as life sciences, organometallics and synthesis, photochemistry and electrochemistry, drug discovery and synthesis, materials science, environmental protection, polymer discovery and synthesis, and energy and fuels.
The scope of the journal is to showcase innovative work in various aspects of catalysis. This includes new reactions and novel synthetic approaches utilizing known catalysts, the discovery or modification of new catalysts, elucidation of catalytic mechanisms through cutting-edge investigations, practical enhancements of existing processes, as well as conceptual advances in the field. Contributions to ACS Catalysis can encompass both experimental and theoretical research focused on catalytic molecules, macromolecules, and materials that exhibit catalytic turnover.