Creation of Polymer Datasets with Targeted Backbones for Screening of Gas Permeability and Selectivity

A simple approach was developed to computationally construct a polymer by composing simplified molecular-input line-entry system (SMILES) strings of a polymer backbone and a molecular fragment. This method was used to create 14 polymer datasets by combining seven polymer backbones and two large molecular datasets (ZINC and QM9). Polymer backbones that were studied include four polydimethylsiloxane (PDMS) based backbones, polyethylene oxide (PEO), poly-allyl glycidyl ether, and polyphosphazene. The generated polymer datasets can be used for various cheminformatics tasks, including high-throughput screening for gas permeability and selectivity. This study used machine learning (ML) models to screen the polymers for CO2/CH4 and CO2/N2 gas separation using membranes and several polymers of interest were identified.