Machine Learning Potential-Enabled Platform for the In Silico Design of Functional Organic Molecular Crystals

The design and discovery of functional molecular materials can be greatly accelerated through in silico approaches. Machine learning (ML) models, in particular, demonstrate significant promise for the rapid analysis and manipulation (and reanalysis) of both molecular and crystal structures, essential steps to hasten materials design and discovery. A critical element of these approaches, however, is that robust ML potentials be developed that allow for accurate predictions of energies and forces acting on atoms within a given crystal. Here, we present an ML potential trained on the OCELOT Crystal Relaxation v1 data set, which is introduced in this work and consists of 15,000 molecular crystal structures and over 2.2 million crystal geometries. The ML potential can predict the energies and forces on atoms in crystal structures comprised of π-conjugated organic molecules with a mean absolute error of 0.008 eV/atom for energy and 0.034 eV/Å for forces when compared with density functional theory calculations. To enable the use of the ML potential for in silico discovery of functional molecular crystals, we develop workflows for analyzing crystal surfaces and morphologies and manipulating and relaxing crystal structures. Furthermore, we deploy these workflows on an open-access, web-based tool, OCELOT XtalTransform, that bridges the gap between sophisticated simulations and user-friendly interfaces. By offering these capabilities, OCELOT XtalTransform aims to democratize access to advanced ML potentials for functional organic molecular crystals, thereby providing new mechanisms for materials design and discovery to the broader scientific community.