Repository logo
 

Linear Atomic Cluster Expansion Force Fields for Organic Molecules: Beyond RMSE.

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Kovács, Dávid Péter  ORCID logo  https://orcid.org/0000-0002-0854-2635
Oord, Cas van der 
Kucera, Jiri 
Cole, Daniel J 

Abstract

We demonstrate that fast and accurate linear force fields can be built for molecules using the atomic cluster expansion (ACE) framework. The ACE models parametrize the potential energy surface in terms of body-ordered symmetric polynomials making the functional form reminiscent of traditional molecular mechanics force fields. We show that the four- or five-body ACE force fields improve on the accuracy of the empirical force fields by up to a factor of 10, reaching the accuracy typical of recently proposed machine-learning-based approaches. We not only show state of the art accuracy and speed on the widely used MD17 and ISO17 benchmark data sets, but we also go beyond RMSE by comparing a number of ML and empirical force fields to ACE on more important tasks such as normal-mode prediction, high-temperature molecular dynamics, dihedral torsional profile prediction, and even bond breaking. We also demonstrate the smoothness, transferability, and extrapolation capabilities of ACE on a new challenging benchmark data set comprised of a potential energy surface of a flexible druglike molecule.

Description

Keywords

34 Chemical Sciences, 3406 Physical Chemistry, Bioengineering, Machine Learning and Artificial Intelligence, Networking and Information Technology R&D (NITRD), Generic health relevance, 7 Affordable and Clean Energy

Journal Title

J Chem Theory Comput

Conference Name

Journal ISSN

1549-9618
1549-9626

Volume Title

Publisher

American Chemical Society (ACS)
Sponsorship
Engineering and Physical Sciences Research Council (EP/P022596/1)
EPSRC (EP/T022159/1)
Engineering and Physical Sciences Research Council (2276922)
EPSRC iCASE studentship
Relationships
Is derived from: