Machine Learning of Analytical Electron Density in Large Molecules Through Message-Passing

Machine learning milestones in computational chemistry are overshadowed by their unaccountability and the overwhelming zoo of tools for each specific task. A promising path to tackle these problems is using machine learning to reproduce physical magnitudes as a basis to derive many other properties. By using a model of the electron density consisting of an analytical expansion on a linear set of isotropic and anisotropic functions, we implemented in this work a message-passing neural network able to reproduce electron density in molecules with just a 2.5% absolute error in complex cases. We also adapted our methodology to describe electron density in large biomolecules (proteins) and to obtain atomic charges, interaction energies, and DFT energies. We show that electron density learning is a new promising avenue with a variety of forthcoming applications.

Automated summary

The study demonstrates the successful application of machine learning to reproduce electron density in molecules with a low absolute error rate. The methodology was also adapted to describe electron density in large biomolecules and obtain atomic charges, interaction energies, and DFT energies. This research highlights electron density learning as a promising avenue with numerous potential applications.