Abstract
We propose a chemical language processing model to predict polymers’ glass transition temperature () through a polymer language (SMILES, Simplified Molecular Input Line Entry System) embedding and recurrent neural network. This model only receives the SMILES strings of a polymer’s repeat units as inputs and considers the SMILES strings as sequential data at the character level. Using this method, there is no need to calculate any additional molecular descriptors or fingerprints of polymers, and thereby, being very computationally efficient. More importantly, it avoids the difficulties to generate molecular descriptors for repeat units containing polymerization point ‘*’. Results show that the trained model demonstrates reasonable prediction performance on unseen polymer’s . Besides, this model is further applied for high-throughput screening on an unlabeled polymer database to identify high-temperature polymers that are desired for applications in extreme environments. Our work demonstrates that the SMILES strings of polymer repeat units can be used as an effective feature representation to develop a chemical language processing model for predictions of polymer . The framework of this model is general and can be used to construct structure–property relationships for other polymer properties.
Highlights
Glass transition temperature (Tg) of polymers is an important physical property, which has been studied extensively in polymer science and engineering [1,2,3,4,5,6]
It is observed that the deep learning (DL) model is relatively stable under different hyperparameters, with the mean absolute error (MAE) metric on the test dataset being in the range of 30∼34 ◦C
Since feature representation is of great importance for machine learning (ML) models [30], alternative forms of polymer lexicon can be developed to build superior chemical language processing models
Summary
Glass transition temperature (Tg) of polymers is an important physical property, which has been studied extensively in polymer science and engineering [1,2,3,4,5,6]. It is well known that Tg value is dependent on the chain mobility or free volume of a polymer [9]. Though theoretical studies have offered critical understandings of polymer’s glass transition, it is still deficient for accurate predictions of Tg of general polymers and not effective for inverse polymer design. Prediction of polymer properties using infinite chain descriptors (ICD) and machine learning: Toward optimized dielectric polymeric materials. Extensions of recurrent neural network language model. The message passing neural networks for chemical property prediction on SMILES. Joint Language and Translation Modeling with Recurrent Neural Networks. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing; Association for Computational Linguistics, Seattle, WA, USA, 18–21 October 2013; pp. An objective-reinforced generative adversarial network for inverse-design chemistry (ORGANIC).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
