BODIPYs 的 B NMR 化学位移的准确预测机器学习。

Accurate prediction of B NMR chemical shift of BODIPYs machine learning.

机构信息

G.A. Krestov Institute of Solution Chemistry of the Russian Academy of Sciences, Akademicheskaya Street, 153045 Ivanovo, Russia.

Ivanovo State University of Chemistry and Technology, 7, Sheremetevskiy Avenue, Ivanovo 153000, Russia.

出版信息

Phys Chem Chem Phys. 2023 Mar 29;25(13):9472-9481. doi: 10.1039/d3cp00253e.

DOI:10.1039/d3cp00253e

PMID:36935644

Abstract

In this article, we present the results of developing a model based on an RFR machine learning method using the ISIDA fragment descriptors for predicting the B NMR chemical shift of BODIPYs. The model is freely available at https://ochem.eu/article/146458. The model demonstrates the high quality of predicting the B NMR chemical shift (RMSE, 5CV (FINALE training set) = 0.40 ppm, RMSE (TEST set) = 0.14 ppm). In addition, we compared the "cost" and the user-friendliness for calculations using the quantum-chemical model with the DFT/GIAO approach. The B NMR chemical shift prediction accuracy (RMSE) of the model considered is more than three times higher and tremendously faster than the DFT/GIAO calculations. As a result, we provide a convenient tool and database that we collected for all researchers, that allows them to predict the B NMR chemical shift of boron-containing dyes. We believe that the new model will make it easier for researchers to correctly interpret the B NMR chemical shifts experimentally determined and to select more optimal conditions to perform an NMR experiment.

摘要

在本文中，我们展示了基于 RFR 机器学习方法使用 ISIDA 片段描述符开发模型的结果，用于预测 BODIPYs 的 B NMR 化学位移。该模型可在 https://ochem.eu/article/146458 上免费获取。该模型证明了预测 B NMR 化学位移的高质量（RMSE，5CV（FINALE 训练集）= 0.40 ppm，RMSE（测试集）= 0.14 ppm）。此外，我们比较了使用量子化学模型与 DFT/GIAO 方法计算的“成本”和用户友好性。所考虑的模型的 B NMR 化学位移预测精度（RMSE）比 DFT/GIAO 计算高三倍以上，并且速度快得多。因此，我们为所有研究人员提供了一个方便的工具和数据库，使他们能够预测含硼染料的 B NMR 化学位移。我们相信，新模型将使研究人员更容易正确解释实验确定的 B NMR 化学位移，并选择更优化的条件来进行 NMR 实验。