Enhancing Deep Learning Predictive Models with HAPPY (Hierarchically Abstracted rePeat unit of PolYmers) Representation

Abstract

Abstract We introduce HAPPY (Hierarchically Abstracted rePeat unit of PolYmers), a new string representation for polymers, designed to efficiently encapsulate essential polymer structure features for property prediction. HAPPY assigns single constituent elements for groups of sub-structures and employs grammatically complete and independent connectors between chemical linkages. Using a limited number of datasets, we trained neural networks represented by both HAPPY and conventional SMILES encoding of repeated unit structures and compared their performance in predicting five polymer properties: dielectric constant, glass transition temperature, thermal conductivity, solubility, and density. The results showed that the HAPPY-based network achieved higher prediction accuracy and two-fold faster training times. We further tested the robustness and versatility of HAPPY-based network with an augmented training dataset. Additionally, we present topo-HAPPY (Topological HAPPY), an extension that incorporates topological details of the constituent connectivity, leading to improved solubility and glass transition temperature prediction accuracy.