Integrating Coarse-Grained Modeling, Machine Learning, and Optimization for Biopolymer Design

The chemical design of polymers with target structural and/or functional properties represents a grand challenge in materials science. While data-driven design approaches are promising, success with polymers has been limited, largely due to limitations in data availability. In this talk, I will discuss a promising workflow that combines coarse-grained modeling, machine learning, and model optimization to achieve the targeted sequence design of biopolymers. This workflow will be explained for the test case of controlling polymer folding/size based on polymer sequence/chemistry, and early results towards enzyme encapsulation will be presented. Important facets of machine learning for polymer applications, such as featurization strategies and data requirements will also be discussed.