{"title":"Using Graph Neural Networks to Predict Positions of the Absorption Maxima of a Number of Dyes","authors":"M. M. Lukanov, A. A. Ksenofontov","doi":"10.1134/S003602442470287X","DOIUrl":null,"url":null,"abstract":"<p>Results are presented from developing a model for accurately predicting the wavelength of the absorption maximum of boron(III) dipyrromethenates (BODIPYs). The model is based on a graph neural network (GNN) and includes data for >2500 dyes of various natures. Statistical parameters of the model (MAE and <i>R</i><sup>2</sup>) are 4 nm and 0.99 for the training set and 13.5 nm and 0.87 for the testing set. The developed model is available to the public in the GitHub repository (https://github.com/lukanov-9b/Abs_model.git).</p>","PeriodicalId":767,"journal":{"name":"Russian Journal of Physical Chemistry A","volume":"98 14","pages":"3342 - 3346"},"PeriodicalIF":0.7000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Russian Journal of Physical Chemistry A","FirstCategoryId":"92","ListUrlMain":"https://link.springer.com/article/10.1134/S003602442470287X","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Results are presented from developing a model for accurately predicting the wavelength of the absorption maximum of boron(III) dipyrromethenates (BODIPYs). The model is based on a graph neural network (GNN) and includes data for >2500 dyes of various natures. Statistical parameters of the model (MAE and R2) are 4 nm and 0.99 for the training set and 13.5 nm and 0.87 for the testing set. The developed model is available to the public in the GitHub repository (https://github.com/lukanov-9b/Abs_model.git).
期刊介绍：
Russian Journal of Physical Chemistry A. Focus on Chemistry (Zhurnal Fizicheskoi Khimii), founded in 1930, offers a comprehensive review of theoretical and experimental research from the Russian Academy of Sciences, leading research and academic centers from Russia and from all over the world.
Articles are devoted to chemical thermodynamics and thermochemistry, biophysical chemistry, photochemistry and magnetochemistry, materials structure, quantum chemistry, physical chemistry of nanomaterials and solutions, surface phenomena and adsorption, and methods and techniques of physicochemical studies.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
