Casanola-Martin Gerardo M, Karuth Anas, Pham-The Hai, González-Díaz Humbert, Webster Dean C, Rasulev Bakhtiyor
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND, USA.
University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, Hanoi, Vietnam.
Commun Chem. 2024 Oct 2;7(1):226. doi: 10.1038/s42004-024-01305-0.
Glass transition temperature of polymers, Tg, is an important thermophysical property, which sometimes can be difficult to measure experimentally. In this regard, data-driven machine learning approaches are important alternatives to assess Tg values, in a high-throughput way. In this study, a large dataset of more than 900 polymers with reported glass transition temperature (T) was assembled from various public sources in order to develop a predictive model depicting the structure-property relationships. The collected dataset was curated, explored via cluster analysis, and then split into training and test sets for validation purposes and then polymer structures characterized by molecular descriptors. To find the models, several machine learning techniques, including multiple linear regression (MLR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), gaussian processes for regression (GPR), and multi-layer perceptron (MLP) were explored. As result, a model with the subset of 15 descriptors accurately predicting the glass transition temperatures was developed. The electronic effect indices were determined to be important properties that positively contribute to the T values. The SVM-based model showed the best performance with determination coefficients (R) of 0.813 and 0.770, for training and test sets, respectively. Also, the SVM model showed the lowest estimation error, RMSE = 0.062. In addition, the developed structure-property model was implemented as a web app to be used as an online computational tool to design and evaluate new homopolymers with desired glass transition profiles.
聚合物的玻璃化转变温度Tg是一项重要的热物理性质，有时通过实验测定会存在困难。在这方面，数据驱动的机器学习方法是以高通量方式评估Tg值的重要替代方法。在本研究中，从各种公开来源收集了一个包含900多种已报道玻璃化转变温度（T）的聚合物的大型数据集，以建立一个描述结构-性质关系的预测模型。对收集到的数据集进行整理，通过聚类分析进行探索，然后为验证目的将其分为训练集和测试集，接着用分子描述符对聚合物结构进行表征。为了找到模型，探索了多种机器学习技术，包括多元线性回归（MLR）、k近邻（k-NN）、支持向量机（SVM）、随机森林（RF）、高斯过程回归（GPR）和多层感知器（MLP）。结果，开发了一个使用15个描述符子集能准确预测玻璃化转变温度的模型。确定电子效应指数是对T值有正向贡献的重要性质。基于SVM的模型表现最佳，训练集和测试集的决定系数（R）分别为0.813和0.770。此外，SVM模型的估计误差最低，RMSE = 0.062。此外，所开发的结构-性质模型被实现为一个网络应用程序，用作在线计算工具来设计和评估具有所需玻璃化转变曲线的新型均聚物。
