Diabetes mellitus is a serious health disease that affects people all over the world. The number of persons identified with diabetes mellitus rises each year. α -Glucosidase is a digestive enzyme used to control diabetes mellitus. The searching for new potent α-glucosidase inhibitors capable of delaying carbohydrate digestion in the human body is an important strategy towards control of diabetes mellitus. In this work, a series of quinoline-based Schiff base derivatives already identified as α-glucosidase inhibitory activity was studied by using 2D/3D-QSAR approach. The best HQSAR/A-B-C-H-Ch-DA and CoMSIA/SEDA models were constructed using thirteen molecules in the training set, resulting in favorable values of Q2 (0.834 and 0.607), and high values of R2 (0.985 and 0.912), respectively. The generated HQSAR/A-B-C-H-Ch-DA and CoMSIA/SEDA contour plots were precious for designing and enhancing the α-glucosidase inhibitory activity of quinoline-based Schiff base molecules. Considering these results, two novel α-glucosidase compounds were designed to possess significant activity. The newly suggested molecules showed good outcomes in the preliminary in silico ADME/Tox evaluations. Molecular docking results revealed that the new designed inhibitors have a good stability in the active pocket of the studied receptor compared to voglibose, clinically used as an α-glucosidase inhibitor. MD simulation and MM-GBSA results confirmed the molecular docking outcomes. Finally, DFT analysis was useful in determining the most electrophilic and nucleophilic centers of the two designed α-glucosidase inhibitors.

While the number of AIDS-related deaths continues to rise, efforts have been made to transform the disease into a manageable chronic condition. HIV protease inhibitors have become central to combination therapy. As a result, these inhibitors have become a major focus of anti-HIV drug development. This research takes a data-driven approach to drug development through the use of quantitative structure-activity relationship (QSAR) analysis. A dataset of 450 anti-HIV drugs was used to construct and validate models. Using extensive validation methods and various machine learning algorithms, the results clearly showed that the "ET" regression outperformed the other models (“XGB”, “LGBM”, “DT”, “RF”, “GB”, “Bag”, and “HGB”) in terms of goodness of fit, predictivity, generalizability, and model robustness. Promising compounds were subjected to molecular docking and molecular dynamics simulation, resulting in drugs with favourable pharmacokinetic and pharmacodynamic properties that consistently interact with the therapeutic target.