QSAR modeling using the Gaussian process applied for a series of flavonoids as potential antioxidants

Flavonoids have been the subject of several studies for many years, particularly due to their high antioxidant activity. However, understanding the structure-activity relationships (SAR) of flavonoids is crucial for optimizing their properties and designing new derivatives with enhanced activities. In this study, we employed Quantitative Structure-Activity Relationship (QSAR) methods to analyze a group of 31 flavonoids with known biological activity. The Gaussian program was used to calculate the molecular descriptors. Using statistical modeling techniques, such as multiple linear regression, we developed QSAR models to correlate the molecular descriptors with the activity values. The models were rigorously validated using appropriate procedures to ensure their reliability and predictive power with a correlation coefficient R2pred = 0.86, and an absolute average relative error (AARE pred) of 0.06 for the test set.(c) 2023 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).