通过机器学习探索新型偶氮苯类光开关，其具有尽可能低的荧光激子且易于合成。

Exploring New Azobenzene Type Photoswitches by Machine Learning with Lowest Possible Fluorescence Excitons with Ease of Synthesis.

作者信息

Waheeb Azal S, Hasan Duha M, Mallah Shaimaa H, Sumrra Sajjad H, Noreen Sadaf, Elnaggar Ashraf Y, Hassan Abrar U, El Azab Islam H, Kyhoiesh Hussein A K, Mahmoud Mohamed H H

机构信息

Department of Chemistry, College of Science, AL-Muthanna, Al-Muthanna University, Samawah, Iraq.

Inorganic Chemistry Group, Scientific Research Center, Al-Ayen University, Thi-Qar, Iraq.

出版信息

J Fluoresc. 2025 May 6. doi: 10.1007/s10895-025-04336-5.

DOI:10.1007/s10895-025-04336-5

PMID:40327276

Abstract

Current investigation presents the design and analysis of 299 azobenzene photoswitches (PSs) for their lowest possible π→ π* transition energies along with their predicted emission maxima values through machine learning (ML) analysis. Their π→ π* transitions related wavelength is calculated by Erying equation to reveal its range up to 256 nm. Their Synthetic Accessibility Likelihood Index (SALI) indicates that a substantial number of them can be synthesized with ease. Among various tested ML model, eXtream Gradient Boosting (XGBoost) regression models demonstrates its high accuracy by achieving an R² value of 0.87. Their designed molecular descriptors show its Maximum Electrotopological State Index (MaxEStateIndex) to impact the model most. For its emission wavelengths, the random forest regression model yields its promising results with its R of 0.92 and a Mean Squared Error (MSE) of 0.38. Its SHAP value reveals the top contributing descriptors being Estate_VSA5, NumValenceElectrons, Estate_VSA3, Chi0n, Chi1v, PEOE_VSA9, Chi0v, and VSA_Estate2. This work not only expands the library of azobenzene PSs but also enhances their understanding of their electronic properties for their future applications in materials science.

摘要

当前的研究展示了299种偶氮苯光开关（PSs）的设计与分析，通过机器学习（ML）分析得出其尽可能低的π→π跃迁能量以及预测的发射最大值。通过艾林方程计算它们与π→π跃迁相关的波长，结果显示其范围可达256纳米。它们的合成可及性可能性指数（SALI）表明，其中相当一部分可以轻松合成。在各种测试的ML模型中，极端梯度提升（XGBoost）回归模型表现出高精度，R²值达到0.87。所设计的分子描述符显示其最大电拓扑状态指数（MaxEStateIndex）对模型影响最大。对于其发射波长，随机森林回归模型取得了不错的结果，R值为0.92，均方误差（MSE）为0.38。其SHAP值显示，贡献最大的描述符是Estate_VSA5、价电子数、Estate_VSA3、Chi0n、Chi1v、PEOE_VSA9、Chi0v和VSA_Estate2。这项工作不仅扩充了偶氮苯PSs的库，还增进了对其电子性质的理解，以便它们未来在材料科学中的应用。