Predicting glass transition of amorphous polymers by application of cheminformatics and molecular dynamics simulations

Predicting the glass-transition temperatures (Tg) of glass-forming polymers is critical importance as it governs thermophysical properties polymeric materials. The cheminformatics approaches based on machine learning algorithms are becoming very useful in predicting quantitative relationships between key molecular descriptors and various physical In this work, we developed a modeling framework by integrating approach coarse-grained dynamics (CG-MD) simulations to predict Tg diverse set polymers. learning-based QSPR model identified most prominent influencing hundred Informed model, CG-MD performed further delineate mechanistic interpretation systematic dependence these influential features investigating three major CG parameters, namely cohesive interaction, chain stiffness, grafting density. reveal that higher intermolecular interaction stiffness increase polymers, where their relative influences coupled with existence side chains grafted backbone. This synergistic provides valuable insights into roles paving way establishing materials-by-design for materials via engineering.