CopDDB: a descriptor database for copolymers and its application to the machine learning

Polymer informatics, which involves the application of data-driven science to polymers, has attracted considerable interest. However, developing adequate descriptors for polymers, particularly copolymers, to facilitate machine learning models with limited datasets remains a challenge. To address this issue, we computed sets of parameters, including reaction energies and activation barriers of elementary reactions in the early stage of radical polymerization, for 2500 radical-monomer pairs derived from 50 commercially available monomers, and constructed an open database named “Copolymer Descriptor Database (CopDDB).” Furthermore, we built machine learning models using our descriptors as explanatory variables and physical properties such as the reactivity ratio, monomer conversion, monomer composition ratio, and molecular weight as objective variables. These models achieved high predictive accuracies, demonstrating the potential of our descriptors to advance the field of polymer informatics.