A quantitative structure--activity relationship study on histamine receptor antagonists using the genetic algorithm--multiparameter linear regression method

A quantitative structure activity relationship (QSAR) model has been generated for predicting the antagonist potency of biphenyl derivatives as human histamine (H3) receptors. The molecular structures of the compounds were numerically represented by various kinds of molecular descriptors. The whole data set was divided into training and test sets. A genetic algorithm based multiple linear regression was used to select the most statistically effective descriptors. The final QSAR model (N = 24, R super(2) =0.916, F = 51.771, Q super(2) sub(LOO) = = 0.872, Q super(2) sub(LGO) = 0.847, Q super(2) sub(Boot) = 0.857) was fully validated employing the leave-one-out (LOO) cross-validation approach, Fischer statistics (F), the Y-randomization test, and predictions based on the test data set. The test set presented an external prediction power of R super(2) sub(test) = 0.855. In conclusion, the generated QSAR model could be used as a valuable tool for designing similar groups of new antagonists of histamine (H3) receptors.