查看文章

A recent discovery of aromatase crystal structure triggered the efforts to design novel aromatase inhibitors for breast cancer therapy. While correlating docking scores with inhibitory potencies of known ligands, feeble robustness of scoring functions toward prediction was observed. This prompted us to develop new prediction models using stepwise regression analysis based on consensus of different docking and their scoring methods (gold, LigandFit, and glide). Quantitative structure–activity relationships were developed between the aromatase inhibitory activity (pIC₅₀) of flavonoid derivatives (n = 39) and docking scores and docking descriptors. QSAR models have been validated internally [using leave‐one‐out cross‐validated )] and externally to ensure the predictive capacity of the models. Model 2 [M2] developed using consensus of docking scores of scoring functions viz. ASP, potential of mean force and …