Creating Gaussian Process Regression Models for Molecular Simulations Using Adaptive Sampling

24 June 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


FFLUX is a new force field that combines the accuracy of quantum mechanics with the speed of force
fields, without any link to the architecture of classical force fields. This force field is atom‐focused and
adopts the parameter‐free topological atom from Quantum Chemical Topology (QCT). FFLUX uses
Gaussian Process Regression (GPR) (aka kriging) models to make predicƟons of atomic properties, which
in this work are atomic energies according to QCT’s InteracƟng Quantum Atom (IQA) approach. Here
we report the adaptive sampling technique Maximum Expected Prediction Error (MEPE) to create data‐
compact, efficient and accurate kriging models (sub kJ mol‐1 for water, ammonia, methane and
methanol, and sub kcal mol‐1 for N‐methylacetamide (NMA)). The models cope with large molecular
distortions and are ready for use in molecular simulation. A brand new press‐one‐buƩon Python
pipeline, called ICHOR, carries out the training.


Quantum Chemical Topology (QCT)
Kriging model

Supplementary materials

AdaptiveSampling SI submit


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.