A Two QSAR Way for Antidiabetic Agents Targeting Using α-Amylase and α-Glucosidase Inhibitors: Model Parameters Settings in Artificial Intelligence Techniques

Background: This work showed the use of 0-2D Dragon molecular descriptors in the prediction of α-amylase and α-glucosidase inhibitory activity. Methods: Several artificial intelligence techniques are used for obtaining quantitative structure-activity relationship (QSAR) models to discriminate active (inhibitor) compounds from inactive (non-inhibitor) ones. The machine learning methodologies such as support vector machine, artificial neural network, and k-nearest neighbor (k-NN) were employed. The k-NN technique had the best classification performances for both targets with values above 90% for the training and prediction sets, correspondingly. Results and Conclusion: These results provided a double target modeling approach for increasing the estimation of antidiabetic chemicals identification aimed by double-way workflow in virtual screenings pipelines.