The dielectric constant (DC) and glass transition temperature (Tg) properties were used to design polymers by quantitative structure-property relationship (QSPR). Using polymer data sets that included homopolymers and copolymers, property prediction models were constructed using the polymer properties and molecular descriptors calculated from monomer structures. The best combination of regression methods, types of descriptors, and preprocessing methods for constructing regression models were determined, and thus, DC and Tg prediction models with a high prediction accuracy could be constructed. Then, theoretical monomer structures, and theoretical copolymers with different combinations of monomer structures and composition ratios were generated, and the DC and Tg of the generated structures were predicted using the constructed models. Candidate structures met the desired DC and Tg values, and the proposed method could select promising monomer structures and composition ratios. Thus, monomer structures that would produce polymers with a high or low DC and high Tg were designed.
Polymer designs, especially monomer designs, can be performed with machine learning and artificial intelligence using a polymer dataset, however, it is meaningless if the designed monomer structures cannot be synthesized and the polymer compound cannot be polymerized. In this study, a retrosynthesis prediction model based on sequence-to-sequence (Seq2Seq) with attention is developed, which is originally used in language transformation, to predict reactants from monomer structures corresponding to polymers. In addition, Seq2Seq with an attention-based synthetic reaction prediction model that predicts monomer structures from reactants is also developed to propose monomer structures with free bonds for polymer design. Through case studies using an actual polymer dataset, it is confirmed that appropriate polymer designs can be achieved by using the proposed method, including the generation of valid monomer structures, the selection of the monomer structures with promising polymer properties, and the prediction of reactants for the monomer structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.