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

• Published in: International journal of molecular sciences Vol. 21; no. 4; p. 1523
• Main Authors: Saddala, Madhu Sudhana, Lennikov, Anton, Huang, Hu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 23.02.2020; MDPI
• Subjects: Adenosine; admet; Amino acids; Animal models; Animals; Binding sites; Catalytic Domain; Clustering; Crystal structure; Dehydrogenases; Diabetes; Diabetic retinopathy; docking; Drug Discovery - methods; Drug Evaluation, Preclinical; Enzymes; g6pd; Glucose; Glucose 6 phosphate dehydrogenase; Glucosephosphate dehydrogenase; Glucosephosphate Dehydrogenase - chemistry; Glucosephosphate Dehydrogenase - drug effects; Glucosephosphate Dehydrogenase - genetics; Glucosephosphate Dehydrogenase - metabolism; Glucosephosphate Dehydrogenase Deficiency - drug therapy; Glutathione - metabolism; Humans; Informatics; Learning algorithms; Ligands; Machine Learning; Molecular docking; Molecular Docking Simulation; Molecular weight; NADP; NADP - chemistry; NADP - metabolism; Nicotine; Organic chemistry; Oxidation-Reduction; Oxidative Stress; Pentose; Pentose Phosphate Pathway; Pharmacology; pharmacophore modeling; Photoreceptors; Principal components analysis; Protein Interaction Domains and Motifs; Proteins; Retina; Retinal cells; Statistical methods; Toxicity; X-Ray Diffraction; pharmacophore modeling; docking; G6PD; machine learning; ADMET
• ISSN: 1422-0067; 1661-6596; 1422-0067
• DOI: 10.3390/ijms21041523

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 ADMET (absorption, distribution, metabolism, excretion and toxicity) analysis). Finally, five lead molecules with different scaffolds were selected by binding energies and 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.