Tao Lei, Chen Guang, Li Ying
Department of Mechanical Engineering, University of Connecticut, Storrs, CT 06269, USA.
Polymer Program, Institute of Materials Science, University of Connecticut, Storrs, CT 06269, USA.
Patterns (N Y). 2021 Mar 26;2(4):100225. doi: 10.1016/j.patter.2021.100225. eCollection 2021 Apr 9.
To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimental values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates with > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers.
为了构建一个机器学习（ML）模型来建立聚合物结构与玻璃化转变温度之间的相关性，我们从最大的聚合物数据库PoLyInfo中收集了近13000种不同的真实均聚物。我们使用这些聚合物化学结构的摩根指纹表示法，用6923个实验值训练深度神经网络（DNN）模型。有趣的是，与分子动力学模拟和实验结果相比，训练后的DNN模型能够合理地预测具有不同分子结构的聚合物的未知值。凭借经过验证的可转移性和泛化能力，该ML模型被用于对近100万种假设聚合物进行高通量筛选。我们识别出65000多种玻璃化转变温度大于200°C的有前景的候选物，这是现有已知高温聚合物（PoLyInfo中约2000种）的30倍。发现如此大量有前景的候选物将对高温聚合物的开发和设计具有重大意义。
