Semi-Local Density Fingerprints for Machine Learning Molecular Properties, Intra-/Inter-molecular Interactions, and Chemical Reactions

In this work, we propose a novel machine learning (ML) feature space that is constructed using semi-local descriptors of the electron density (i.e., ρ and ▽ρ)---the quantum mechanical objects at the very heart of density functional theory (DFT). The proposed ML descriptor or "semi-local density fingerprint" (SLDF), can be quickly assembled from any input electron density, provides a compact (system-size-independent) and unique representation for each molecule, accounts for molecular symmetry by construction (and is invariant to translations and rotations), contains transferable information across wide swaths of chemical compound space, and has lead to unprecedented levels of accuracy during initial proof-of-principle tests. As a demonstration of the accuracy, reliability, and transferability that one can acheive using SLDFs, we will discuss their performance in the prediction of molecular properties, intra-/inter-molecular interactions, and chemical reactions.