Aromatic donor-acceptor columnar liquid crystals (DACLC) are materials that self-assemble from the 1:1 molar mixture of the complementary electron-rich “donor” and electron-poor “acceptor” molecules. In general, these component molecules have two or more “side chains” that affect the properties of bulk DACLC they make up, including phase transition temperature, phase stability, and charge mobility. However, understanding, and predicting, how varying the identity of the component side chains will affect the bulk DACLC properties remains an important and difficult challenge for these materials and for organic materials in general. Herein we report an initial application of machine learning programs for predicting the phase transition temperature of DACLCs from their component structures. We explore several machine learning models based on the available training set of reported DACLC materials. The potential of these models to reasonably predict phase transition temperatures will be discussed.

Uncovering the relationships between small-molecule structure to bulk properties in donor-acceptor columnar liquid crystals

ACS Spring Meeting 2021

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