Quantitative structure–activity relationship studies of a series of non-benzodiazepine structural ligands binding to benzodiazepine receptor

Heuristic method (HM) and radial basis function neural network (RBFNN) methods were proposed to generate QSAR models for a set of non-benzodiazepine ligands at the benzodiazepine receptor (BzR). Descriptors calculated from the molecular structures alone were used to represent the characteristics of the compounds. The six molecular descriptors selected by HM in CODESSA were used as inputs for RBFNN. Compared with the results of HM, more accurate prediction could be obtained from RBFNN. The correlation coefficients (R) of the nonlinear RBFNN model were 0.9113 and 0.9030 for the training and test sets, respectively. This paper proposed an effective method to design new ligands of BzR based on QSAR.

RBFNN method was proposed to generate a QSAR model for a set of non-benzodiazepines' activity at the benzodiazepine receptor (BzR), which is effective to design new ligands of BzR.Figure optionsDownload as PowerPoint slide