Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials

Abstract It has proved challenging to represent the behavior of polymeric macromolecules as machine learning features for biomaterial interaction prediction. There are several approaches this representation, yet no consensus a universal representational framework, in part due sensitivity biomacromolecular interactions polymer properties. To help navigate process feature engineering, we provide an overview popular classes data representations while discussing their merits and limitations. Generally, increasing accessibility engineering knowledge will contribute goal accelerating clinical translation from biomaterials discovery.