Creating Gaussian process regression models for molecular simulations using adaptive sampling

doi:10.1063/5.0017887

Creating Gaussian process regression models for molecular simulations using adaptive sampling

2020-08-04

34

PRE

AI

M

Matthew J. Burn

P

Paul L. A. Popelier *

DOI：10.1063/5.0017887

Original

Original request for help

Save

Abstract

En 中文

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 (also known as kriging) models to make predictions of atomic properties, which in this work are atomic energies according to QCT's interacting quantum atom approach. Here, we report the adaptive sampling technique maximum expected prediction error 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). The models cope with large molecular distortions and are ready for use in molecular simulation. A brand new press-one-button Python pipeline, called ICHOR, carries out the training.

Keywords:

INTERACTING QUANTUM ATOMS

POTENTIAL-ENERGY SURFACES

FORCE-FIELDS

DYNAMICS

PREDICTION

GRADIENT

PEPTIDE

WATER

PSEUDOPOTENTIALS

ELECTROSTATICS

Creating Gaussian process regression models for molecular simulations using adaptive sampling

Abstract

AI Summary

Journal

Organization