The chemical design of polymers with target structural and/or functional properties represents a grand challenge in materials science. Although artificial intelligence and machine learning have greatly enhanced design efforts for many materials classes, applications to polymer systems remains limited, particularly those aiming to exploit property variation due to composition, sequence, or topological effects. In this talk, I will critically examin the strategies for featurization of macrmolecules, specifically polymer systems, in polymer property prediction tasks with supervised machine learning. Examples will range from assessing single-chain polymer conformation to tailoring interactions with biological compounds. These examples will highlight the need for developing new strategies that can address topological and sequence effects that can govern polymer behaviors.

Featurization in polymer property prediction: What's in a name?

ACS Fall 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.