Machine Learning of Partial Charges Derived from High-Quality Quantum-Mechanical Calculations
OPEN ACCESS
Loading...
Author / Producer
Date
2018-03-26
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Parametrization of small organic molecules for classical molecular dynamics simulations is not trivial. The vastness of the chemical space makes approaches using building blocks challenging. The most common approach is therefore an individual parametrization of each compound by deriving partial charges from semiempirical or ab initio calculations and inheriting the bonded and van der Waals (Lennard-Jones) parameters from a (bio)molecular force field. The quality of the partial charges generated in this fashion depends on the level of the quantum-chemical calculation as well as on the extraction procedure used. Here, we present a machine learning (ML) based approach for predicting partial charges extracted from density functional theory (DFT) electron densities. The training set was chosen with the goal to provide a broad coverage of the known chemical space of druglike molecules. In addition to the speed of the approach, the partial charges predicted by ML are not dependent on the three-dimensional conformation in contrast to the ones obtained by fitting to the electrostatic potential (ESP). To assess the quality and compatibility with standard force fields, we performed benchmark calculations for the free energy of hydration and liquid properties such as density and heat of vaporization.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
58 (3)
Pages / Article No.
579 - 590
Publisher
American Chemical Society
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
09458 - Riniker, Sereina Z. / Riniker, Sereina Z.
Notes
Funding
159713 - Computer simulation of small organic molecules for computer-aided drug design (SNF)
ETH-08 15-1 - A triple-resoluation QM/MM/coarse-grained model for the simulation of membrane-bound proteins (ETHZ)
ETH-08 15-1 - A triple-resoluation QM/MM/coarse-grained model for the simulation of membrane-bound proteins (ETHZ)