We developed a machine learning model based on a Euclidean neural network framework to study large biological macromolecules such as DNA. The machine learning model bypasses computationally demanding quantum simulations to predict electron densities of up to 99% accuracy. We show that the machine learning model extrapolates to larger system sizes with negligible loss of accuracy by comparing model predictions to quantum calculations for DNA structures of increasing chain length. We apply the model to produce electron densities for various experimental DNA crystal structures typically considered to be too large for conventional calculations. We suggest the machine-learned electron densities can be used to calculate non-spherical atomic form factors to construct a more accurate atomic model for X-ray crystal structure refinement.

Machine learning to predict quantum accurate electron densities for DNA: Applications for X-ray crystal structure refinement

ACS Spring 2022

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