Discovery of Small-Molecule Activators for Glucose-6-Phosphate Dehydrogenase (G6PD) Using Machine Learning Approaches

Abstract

Glucose-6-Phosphate Dehydrogenase (G6PD) is a ubiquitous cytoplasmic enzyme converting glucose-6-phosphate into 6-phosphogluconate in the pentose phosphate pathway (PPP). The G6PD deficiency renders the inability to regenerate glutathione due to lack of Nicotine Adenosine Dinucleotide Phosphate (NADPH) and produces stress conditions that can cause oxidative injury to photoreceptors, retinal cells, and blood barrier function. In this study, we constructed pharmacophore-based models based on the complex of G6PD with compound AG1 (G6PD activator) followed by virtual screening. Fifty-three hit molecules were mapped with core pharmacophore features. We performed molecular descriptor calculation, clustering, and principal component analysis (PCA) to pharmacophore hit molecules and further applied statistical machine learning methods. Optimal performance of pharmacophore modeling and machine learning approaches classified the 53 hits as drug-like (18) and nondrug-like (35) compounds. The drug-like compounds further evaluated our established cheminformatics pipeline (molecular docking and in silico ADMET (absorption, distribution, metabolism, excretion and toxicity) analysis). Finally, five lead molecules with different scaffolds were selected by binding energies and in silico ADMET properties. This study proposes that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability to find potential G6PD activators used for G6PD deficiency diseases. Moreover, these compounds can be considered as safe agents for further validation studies at the cell level, animal model, and even clinic setting.

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap–Deep Learning

“…At the dataset ratio Tra/Val/Test = 2:2:1, the values of mean MCC, Acc (Test), AUC, Loss (Val), Acc (Val), F, and BAC were 0.664 ± 0.162, 0.828 ± 0.087, 0.886 ± 0.058, 0.345 ± 0.088, 84.08 ± 4.08, 0.756 ± 0.100, and 0.860 ± 0.086, respectively. Although we cannot rule out random effects, it has been shown that conformational changes of molecules, which are the position and shape of key functional groups, affect the biological activity [50,51]. Further, it was reported that the energy profile in a fragment of chemical changes periodically with torsion angles [51].…”

“…Although we cannot rule out random effects, it has been shown that conformational changes of molecules, which are the position and shape of key functional groups, affect the biological activity [50,51]. Further, it was reported that the energy profile in a fragment of chemical changes periodically with torsion angles [51]. Given these reports, the depiction angles in DeepSnap may play an important role in efficient feature extraction.…”

“…Physicochemical and chemical structural properties of small chemical compounds are pivotal data for ML approaches to assess their bioactivities. The resulting properties are applied to cluster component analysis by similar property profiles and principle component analysis (PCA) for reducing variables in the descriptors to explain most of the variables in the original data and eliminating the redundancy [51,52]. The PCA of the molecular descriptors indicated that the mean eigenvalue of principal component (PC) 1 and PC2-which are the first two PCs for explaining the total information contained in the molecular descriptors-for five of the Tra and Test datasets using the four MLs for the ≥ 30% threshold were PC1 (Tra): 35.6% ± 2.04%, PC1 (Test): 37.2% ± 1.52%, PC2 (Tra): 11.3% ± 0.96%, and PC2 (Test): 12.8% ± 0.43% (Figure 3).…”

In Silico Identification of Potential Allosteric Inhibitors of the SARS-CoV-2 Helicase

“…This suggests the standard has the lowest saturation and hence the least molecular stability. 46 In biological assays, certain compounds (PAINS: pan assay interference) yield false positive response because they have problematic structural moieties. These compounds are considered promiscuous as they are frequent hitters.…”

WITHDRAWN: Phytochemical and Molecular Dynamic Analysis of Novel Biomolecule Lancifotarene Extracted From Conocarpus Lancifolius as Cytotoxic, Antiurease and Antidiabetic Agent

“…Calculation of pharmacological pro le estimation is important for the screening of suitable drug-like compounds in the initial stage of drug discovery and development 15 .Physiochemical properties are very important to explain the drug-likeness of a selected compounds explained by Lipinski, Ghose, Veber and Egan rule16,17 . The molecular complexity of the chemical compound is measured as number of rings and aromatic rings, the fraction of carbons that were sp3 hybridized (Csp3) present in compound18 . Novel compound LFN had presented good bioavailability, acceptable lipophilicity, molar refractivity, molecular weight and the topological polar surface area.…”