Interpretable machine learning integrated with TD-DFT descriptors and SHAP analysis for predicting the maximum absorption wavelength of azo dyes

结合TD-DFT描述符和SHAP分析的可解释机器学习方法用于预测偶氮染料的最大吸收波长

阅读:1

Abstract

The maximum absorption wavelength (λ (max)) represents a key property determining the application performance of azo dyes, and accurate prediction of λ (max) is of paramount importance for accelerating the rational design of novel dye molecules. Existing prediction models exhibit significant limitations in terms of prediction accuracy and chemical interpretability. In this work, we propose an innovative prediction framework for λ (max) of azo dyes by integrating Gaussian Process Regression (GPR) with key molecular descriptors derived from time-dependent density functional theory (TD-DFT) calculations. Results indicate that the coefficient of determination (R (2)) for leave-one-out cross-validation (LOOCV) was 0.83, and that for the independent test set was 0.74. According to SHAP analysis, the S(0) → S(1) transition energy exhibits a negative correlation with λ (max) (maximum absorption wavelength), while the concurrent elevation of HOMO and LUMO energies induces a red-shift in λ (max). Notably, the number of sulfur atoms in the R substituent shows a positive correlation with λ (max). Furthermore, a high-throughput screening strategy was employed to identify 21 azo molecules with relatively large λ (max) values from 14 376 virtual samples. The predicted λ (max) of these identified molecules is expected to undergo a red-shift relative to the baseline maximum λ (max) of 650 nm in the original dataset. This study presents a straightforward approach for the discovery of azo dyes with extended λ (max), providing a practical reference for the targeted design of such functional materials.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。