We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics.
We use our approach to predict the thermal half-lives of 19, 000 azobenzene derivatives.
Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.
Macromolecules are large, complex molecules composed of covalently bonded monomer units, existing in different stereochemical configurations and topologies.
2 code implementations • 13 Jan 2021 • Tian Xie, Arthur France-Lanord, Yanming Wang, Jeffrey Lopez, Michael Austin Stolberg, Megan Hill, Graham Michael Leverick, Rafael Gomez-Bombarelli, Jeremiah A. Johnson, Yang Shao-Horn, Jeffrey C. Grossman
Polymer electrolytes are promising candidates for the next generation lithium-ion battery technology.
Here we investigate how the 3D information of multiple conformers, traditionally known as 4D information in the cheminformatics community, can improve molecular property prediction in deep learning models.
The potential of mean force is expressed as two jointly-trained neural network interatomic potentials that learn the coupled short-range and the many-body long range molecular interactions.
Computational Physics Materials Science
The Geometric Ensemble Of Molecules (GEOM) dataset contains conformers for 133, 000 species from QM9, and 317, 000 species with experimental data related to biophysics, physiology, and physical chemistry.
Predicting and directing polymorphic transformations is a critical challenge in zeolite synthesis.
Graph Similarity Materials Science