Rapid and Accurate Estimation of Quantum Average Electron Densities Using Newly-Defined Atom Types

A new computational tool, the Average Electron Density Estimator (AED-Est), has been developed along with a new scheme for assigning atom type, the AAA scheme. This combination of the AED-Est and the AAA scheme is designed to rapidly estimate properties, including electron populations, volumes, and average electron density (AED) values, with high precision and an accuracy comparable to values computed at the quantum levels. AED-Est gave comparable results when using three different sets/subsets of various neutral molecules. The AED-Est reference values were obtained using 553 molecules, and then tested on a separate set of 101 molecules. The <i>R</i> <sup>2</sup> between the predicted values (obtained via the AED-Est tool) and the actual values (obtained via quantum simulations) reaches 0.99, and the RMSE values are at least 1 order of magnitude smaller than the average values. The new AAA scheme of defining atom types, which can be useful in designing new force fields, can significantly imporve the results compared to the general Amber force field, GAFF2, scheme. The AED-Est tool provided even better predictions of AED values for groups of atoms within a molecule, such as bioisosteric moieties, than for individual atoms. This has significant implications for fields such as drug discovery and the development of more effective therapeutics.

Authors

Institutions

Publication Details

Journal
ACS Omega
Published
2025-08-15
DOI
https://doi.org/10.1021/acsomega.5c03444
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Rapid and Accurate Estimation of Quantum Average Electron Densities Using Newly-Defined Atom Types

Alya A. Arabi
ACS Omega
Machine Learning in Materials Science
article

Rapid and Accurate Estimation of Quantum Average Electron Densities Using Newly-Defined Atom Types

Alya A. Arabi
article en

Abstract

A new computational tool, the Average Electron Density Estimator (AED-Est), has been developed along with a new scheme for assigning atom type, the AAA scheme. This combination of the AED-Est and the AAA scheme is designed to rapidly estimate properties, including electron populations, volumes, and average electron density (AED) values, with high precision and an accuracy comparable to values computed at the quantum levels. AED-Est gave comparable results when using three different sets/subsets of various neutral molecules. The AED-Est reference values were obtained using 553 molecules, and then tested on a separate set of 101 molecules. The <i>R</i> <sup>2</sup> between the predicted values (obtained via the AED-Est tool) and the actual values (obtained via quantum simulations) reaches 0.99, and the RMSE values are at least 1 order of magnitude smaller than the average values. The new AAA scheme of defining atom types, which can be useful in designing new force fields, can significantly imporve the results compared to the general Amber force field, GAFF2, scheme. The AED-Est tool provided even better predictions of AED values for groups of atoms within a molecule, such as bioisosteric moieties, than for individual atoms. This has significant implications for fields such as drug discovery and the development of more effective therapeutics.

ACS OmegaVol. 10(33)
United Arab Emirates University (AE)
Zayed Bin Sultan Center for Health Sciences, United Arab Emirates University
Openalex Percentile: Top 84%
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.