Computational Modeling of Aldose Reductase Inhibitory Activity of Flavonoids Derivatives for Diabetic Complications Treatment

Background: Diabetes mellitus is a chronic metabolic disease that constitutes a risk factor for patients infected by COVID-19. Aldose reductase (ALR2) is an enzyme that catalyzes the formation of sorbitol in the metabolism of glucose via polyols in diabetic patients and leads to a group of diabetic complications: cataracts, retinopathies, neuropathies, and nephropathies. Introduction: Inhibitors of this enzyme are therapeutic targets for the prophylaxis and treatment of these conditions. The aim of this work was to identify flavonoids isolated from medicinal plants, fruits, and vegetables as potential inhibitors of ALR2. Methods: In this study, using the MATLAB numerical computation system and the molecular descriptors implemented in the DRAGON software, a regression tree was developed, with an R-2 of 0.953 and adequate parameters for its fit. Results: The model was validated to take into account internal and external validation procedures. Besides, the applicability domain was determined to guarantee the reliability of the predictions. Due to its good predictive power (R-ext(2) = 0.949), the model was used to predict the inhibition of ALR2 by flavonoids reported in dietary sources. The most promising flavonoids are Myricetin and Tricin (pIC(50) predicted = 7.296), which are within the application domain and meet drug-like properties for oral administration. Conclusion: Finally, we can conclude that the proposed tools are useful for the rapid and economical identification of flavonoid-based potential drug candidates against ALR2 in diabetic complications.