In this study, in silico approaches, including multiple QSAR modeling, structural similarity\nanalysis, and molecular docking, were applied to develop QSAR classification models as a fast\nscreening tool for identifying highly-potent ABCA1 up-regulators targeting LXR�² based on a series\nof new flavonoids. Initially, four modeling approaches, including linear discriminant analysis,\nsupport vector machine, radial basis function neural network, and classification and regression\ntrees, were applied to construct different QSAR classification models. The statistics results indicated\nthat these four kinds of QSAR models were powerful tools for screening highly potent ABCA1\nup-regulators. Then, a consensus QSAR model was developed by combining the predictions from\nthese four models. To discover new ABCA1 up-regulators at maximum accuracy, the compounds in\nthe ZINC database that fulfilled the requirement of structural similarity of 0.7 compared to known\npotent ABCA1 up-regulator were subjected to the consensus QSAR model, which led to the discovery\nof 50 compounds. Finally, they were docked into the LXR�² binding site to understand their role\nin up-regulating ABCA1 expression. The excellent binding modes and docking scores of 10 hit\ncompounds suggested they were highly-potent ABCA1 up-regulators targeting LXR�². Overall, this\nstudy provided an effective strategy to discover highly potent ABCA1 up-regulators.
Loading....