2019
DOI: 10.1021/acs.jmedchem.9b01129
|View full text |Cite
|
Sign up to set email alerts
|

Practical High-Quality Electrostatic Potential Surfaces for Drug Discovery Using a Graph-Convolutional Deep Neural Network

Abstract: Inspecting protein and ligand electrostatic potential (ESP) surfaces in order to optimize electrostatic complementarity is a key activity in drug design. These ESP surfaces need to reflect the true electrostatic nature of the molecules, which typically means time-consuming high-level quantum mechanics (QM) calculations are required. For interactive design much faster alternative methods are required. Here, we present a graph convolutional deep neural network (DNN) model, trained on ESP surfaces derived from hi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
76
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 100 publications
(83 citation statements)
references
References 37 publications
0
76
0
Order By: Relevance
“…The molecular electrostatic potential (MEP) of the top hit compound was also plotted over the compounds' electronic structure from the DFT calculation. The observed MEP surface around a compound by the charge distribution provides information about the reactive sites for the nucleophilic and electrophilic attack in hydrogen bonding interactions [ 29 ] and other processes requiring biological recognition [ 30 ]. The MEP for the top hit compounds shows the electrophilic region and the nucleophilic region.…”
Section: Resultsmentioning
confidence: 99%
“…The molecular electrostatic potential (MEP) of the top hit compound was also plotted over the compounds' electronic structure from the DFT calculation. The observed MEP surface around a compound by the charge distribution provides information about the reactive sites for the nucleophilic and electrophilic attack in hydrogen bonding interactions [ 29 ] and other processes requiring biological recognition [ 30 ]. The MEP for the top hit compounds shows the electrophilic region and the nucleophilic region.…”
Section: Resultsmentioning
confidence: 99%
“…Electrostatics potential plays an important role in molecular biology since it contributes to protein folding and stability, protein-protein interactions, ion binding, dimerization, protein-DNA/RNA interactions, and protein-microtubule binding (Shashikala et al, 2019). In particular, it is well-known that molecular electrostatics can be predictive of a molecule's chemical reactivity and its ability to form certain types of interactions (Rathi et al, 2020). Differences in the topology and surface electrostatic potential surrounding the cleft are thought to determine the specificity of TLPs to their target proteins and ligands (Min et al, 2004).…”
Section: Discussionmentioning
confidence: 99%
“…In contrast to atomic charges and electronegativity, which may be described as arbitrary and whose absolute values strongly depend on the context and applied method, it can be well approximated using modern quantum chemical techniques. New advances in machine learning may even establish it as a routine procedure in drug design (Rathi et al, 2020). To compare the electrostatic potential of our targets and map it to the HS and the experimental crystal structures, we computed the electron density map with the electrostatic potential using the Gaussian visualization software Gaussview 6.6.1 (Dennington et al, 2019) Schematic representation of the HOMO-LUMO gap and the orbital distribution of the HOMO and LUMO of the four compounds presented in this study as obtained at the B3LYP-D3BJ/6-311++G(d,p) level of theory.…”
Section: Figurementioning
confidence: 99%