Electrostatic Embedding of Machine Learning Potentials

06 September 2022, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

This work presents a variant of an electrostatic embedding scheme that allows the embedding of arbitrary machine learned potentials trained on molecular systems in vacuo. The scheme is based on physically motivated models of electronic density and polarizability, resulting in a generic model without relying on an exhaustive training set. The scheme only requires in vacuo single point QM calculations to provide training densities and molecular dipolar polarizabilities. As an example, the scheme is applied to create an embedding model for the QM7 dataset using Gaussian Process Regression with only 445 reference atomic environments. The model was tested on SARS-CoV-2 protease complex with PF-00835231, resulting in predicted embedding energy RMSE of 2 kcal/mol, compared to explicit DFT/MM calculations.

Keywords

machine learning potential
QM/MM
electrostatic embedding
polarizability

Supplementary materials

Title
Description
Actions
Title
Supporting Information
Description
Sections: S1 Molecules excluded from the dataset S2 Selection of reference atomic environments S3 Modified sparse GPR S4 Molecular dipolar polarizability from Thole model S5 Results with MBIS volumes S6 Calculation of electrostatic potential S7 χ from MBIS partitioning S8 Absolute embedding energy prediction errors S9 Learning workflow S10 Prediction workflow
Actions

Supplementary weblinks

Comments

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.