QSPR modelling for prediction of glass transition temperature of diverse polymers

• Published in: SAR and QSAR in environmental research Vol. 29; no. 12; pp. 935 - 956
• Main Authors: Khan, P.M., Roy, K.
• Format: Journal Article
• Language: English
• Published: England Taylor & Francis 02.12.2018; Taylor & Francis Ltd
• Subjects: Acrylic Resins - chemistry; Chemical synthesis; consensus modelling; Glass; Glass transition temperature; Models, Chemical; Molecular Structure; polymer; Polymers; Polymers - chemistry; Polystyrenes - chemistry; Polyvinyls - chemistry; Quantitative Structure-Activity Relationship; quantitative structure-property relationship; Regression analysis; Reproducibility of Results; Statistical analysis; Temperature; Transition Temperature; Transition temperatures; true external set; polymer; true external set; consensus modelling; quantitative structure–property relationship
• ISSN: 1062-936X; 1029-046X
• DOI: 10.1080/1062936X.2018.1536078

The glass transition temperature is a vital property of polymers with a direct impact on their stability. In the present study, we built quantitative structure-property relationship models for the prediction of the glass transition temperatures of polymers using a data set of 206 diverse polymers. Various 2D molecular descriptors were computed from the single repeating units of polymers. We derived five models from different combinations of six descriptors in each case by employing the double cross-validation technique followed by partial least squares regression. The selected models were subsequently validated by methods such as cross-validation, external validation using test set compounds, the Y-randomization (Y-scrambling) test and an applicability domain study of the developed models. All of the models have statistically significant metric values such as r 2 ranging from 0.713-0.759, Q 2 ranging from 0.662-0.724 and ranging 0.702-0.805. Finally, a comparison was made with recently published models, though the previous models were based on a much smaller data set with limited diversity. We also used a true external set to demonstrate the performance of our developed models, which may be used for the prediction and design of novel polymers prior to their synthesis.