Next Article in Journal
Investigation of the Dynamism of Nanosized SOA Particle Formation in Indoor Air by a Scanning Mobility Particle Sizer and Proton-Transfer-Reaction Mass Spectrometry
Next Article in Special Issue
A Deep-Learning Approach toward Rational Molecular Docking Protocol Selection
Previous Article in Journal
Parameterization of Boronates Using VFFDT and Paramfit for Molecular Dynamics Simulation
Previous Article in Special Issue
Discovery of Novel Imidazopyridine GSK-3β Inhibitors Supported by Computational Approaches
Article

Combined Machine Learning and Molecular Modelling Workflow for the Recognition of Potentially Novel Fungicides

Ruđer Bošković Institute, Bijenička cesta 54, 10 000 Zagreb, Croatia
*
Author to whom correspondence should be addressed.
Academic Editor: Maria Cristina De Rosa
Molecules 2020, 25(9), 2198; https://doi.org/10.3390/molecules25092198
Received: 20 March 2020 / Revised: 2 May 2020 / Accepted: 6 May 2020 / Published: 8 May 2020
(This article belongs to the Special Issue Drug Discovery and Molecular Docking)
Novel machine learning and molecular modelling filtering procedures for drug repurposing have been carried out for the recognition of the novel fungicide targets of Cyp51 and Erg2. Classification and regression approaches on molecular descriptors have been performed using stepwise multilinear regression (FS-MLR), uninformative-variable elimination partial-least square regression, and a non-linear method called Forward Stepwise Limited Correlation Random Forest (FS-LM-RF). Altogether, 112 prediction models from two different approaches have been built for the descriptor recognition of fungicide hit compounds. Aiming at the fungal targets of sterol biosynthesis in membranes, antifungal hit compounds have been selected for docking experiments from the Drugbank database using the Autodock4 molecular docking program. The results were verified by Gold Protein-Ligand Docking Software. The best-docked conformation, for each high-scored ligand considered, was submitted to quantum mechanics/molecular mechanics (QM/MM) gradient optimization with final single point calculations taking into account both the basis set superposition error and thermal corrections (with frequency calculations). Finally, seven Drugbank lead compounds were selected based on their high QM/MM scores for the Cyp51 target, and three were selected for the Erg2 target. These lead compounds could be recommended for further in vitro studies. View Full-Text
Keywords: classification; regression; docking; drug repurposing; QM/MM; Fe-N(R)C angle classification; regression; docking; drug repurposing; QM/MM; Fe-N(R)C angle
Show Figures

Figure 1

MDPI and ACS Style

Jović, O.; Šmuc, T. Combined Machine Learning and Molecular Modelling Workflow for the Recognition of Potentially Novel Fungicides. Molecules 2020, 25, 2198. https://doi.org/10.3390/molecules25092198

AMA Style

Jović O, Šmuc T. Combined Machine Learning and Molecular Modelling Workflow for the Recognition of Potentially Novel Fungicides. Molecules. 2020; 25(9):2198. https://doi.org/10.3390/molecules25092198

Chicago/Turabian Style

Jović, Ozren, and Tomislav Šmuc. 2020. "Combined Machine Learning and Molecular Modelling Workflow for the Recognition of Potentially Novel Fungicides" Molecules 25, no. 9: 2198. https://doi.org/10.3390/molecules25092198

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop