Design, Assessment, and Application of Machine Learning Potential Energy Surfaces

TL;DR

This paper reviews the development and application of Machine Learning-based Potential Energy Surfaces, highlighting practical methodologies and demonstrating their use in biomolecular systems like peptides and DNA base pairs.

Contribution

It provides a comprehensive overview of ML-PES construction, assessment, and application, with practical guidelines and case studies in biomolecular chemistry.

Findings

ML-PES enable accurate simulations of complex biomolecular systems.

The paper demonstrates ML-PES effectiveness in modeling peptide dynamics and proton transfer.

Practical recommendations improve ML-PES reliability and usability.

Abstract

Potential Energy Surfaces (PESs) are an indispensable tool to investigate, characterise and understand chemical and biological systems in the gas and condensed phases. Advances in Machine Learning (ML) methodologies have led to the development of Machine Learned Potential Energy Surfaces (ML-PES) which are now widely used to simulate such systems. The present work provides an overview of concepts, methodologies and recommendations for constructing and using ML-PESs. The choice of topics is focused on practical and recurrent issues to conceive and use such model. Application of the principles discussed are illustrated through two different systems of biomolecular importance: the non-reactive dynamics of the Alanine-Lysine-Alanine tripeptide in gas and solution phases, and double proton transfer reactions in DNA base pairs.