Using Machine Learning Hamiltonians To Compute Molecular Motor Barrier Heights

TL;DR

This study evaluates the effectiveness of machine learning inter-atomic potentials in accurately predicting transition barrier heights in complex molecular motors, demonstrating promising results for high-throughput computational screening.

Contribution

It introduces a hybrid approach combining semi-empirical quantum methods with deep learning to efficiently estimate molecular transition states and barriers.

Findings

HIP-NN combined with PM3 produces realistic pathway guesses.

Refinement with DFT yields results matching experimental data.

Deep learning can be applied to high-precision transition path sampling.

Abstract

Machine Learning Inter-atomic Potentials (MLIPs) have become a common tool in use by computational chemists due to their combination of accuracy and speed. Yet, it is still not clear how well these tools behave at or near transitions states found in complex molecules. Here we investigate the applicability of MLIPs in evaluating the transition barrier of two, complex, molecular motor systems: a 1st generation Feringa motor and the 9c alkene 2nd generation Feringa motor. We compared paths generated with the Hierarchically Interacting Particle Neural Network (HIP-NN), the PM3 semi-empirical quantum method (SEQM), PM3 interfaced with HIP-NN (SEQM+HIP-NN), and Density Functional Theory calculations. We found that using SEQM+HIP-NN to generate cheap, realistic pathway guesses then refining the intermediates with DFT allowed us to cheaply find realistic reaction paths and energy barriers matching experiment, providing evidence that deep learning can be used for high precision computational tasks such as transition path sampling while also suggesting potential application to high throughput screening.