Scholarlink

<p>In this study, an approach to design new fluorescent organic polymers based on benzodithiophene (BDT) chromophores are presented by utilizing machine learning (ML) techniques. For this, the BDT chromophores, from the literature, along with their corresponding λ<sub>e</sub>. by using Rapid Discovery Kit (RDKit), their molecular descriptors are designed to employ ML models for predicting their λ<sub>max</sub> and λ<sub>e</sub> properties. Among the evaluated models, Linear Regression, Random Forest and Decision Tree models demonstrate the best performance, achieving R² values between 0.96 and 0.98. Their analysis of SHapley Additive exPlanations (SHAP) values reveals that the Labute Accessible Surface Area (ASA) and the number of Rotatable Bonds can be the most influential features to impact their performance. Leveraging these insights, their 5,000 new polymers are designed with their predicted λ<sub>e</sub> extending up to 987&#xa0;nm. Their highest Synthetic Accessibility Likelihood Index (SALI) scores for the top 1,000 polymers reaches up to 3.21 to indicate their accessibility for synthesis. This work not only advances the understanding of BDT -based materials but can also provide a framework for designing of new fluorescent polymers.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Curating Benzothiophene Experimental Absorption and Emission Spectra to Design Fluorescent Organic Polymer Chemical Space: A Machine Learning Quest

  • 期刊论文

  • 发表日期：

    2025年2月10日

查看全文
  • Shaimaa H. Mallah,
  • Azal S. Waheeb,
  • Abrar U. Hassan,
  • Masar A. Awad,
  • Ayad R. Jalfan,
  • Ashraf Y. Elnaggar,
  • Islam H. El Azab,
  • Mohamed H. H. Mahmoud

摘要

In this study, an approach to design new fluorescent organic polymers based on benzodithiophene (BDT) chromophores are presented by utilizing machine learning (ML) techniques. For this, the BDT chromophores, from the literature, along with their corresponding λe. by using Rapid Discovery Kit (RDKit), their molecular descriptors are designed to employ ML models for predicting their λmax and λe properties. Among the evaluated models, Linear Regression, Random Forest and Decision Tree models demonstrate the best performance, achieving R² values between 0.96 and 0.98. Their analysis of SHapley Additive exPlanations (SHAP) values reveals that the Labute Accessible Surface Area (ASA) and the number of Rotatable Bonds can be the most influential features to impact their performance. Leveraging these insights, their 5,000 new polymers are designed with their predicted λe extending up to 987 nm. Their highest Synthetic Accessibility Likelihood Index (SALI) scores for the top 1,000 polymers reaches up to 3.21 to indicate their accessibility for synthesis. This work not only advances the understanding of BDT -based materials but can also provide a framework for designing of new fluorescent polymers.