Prediction of binding affinities to beta1 isoform of human thyroid hormone receptor by genetic algorithm and projection pursuit regression.

Quantitative structure-activity relationship (QSAR) has been applied to a set of thyroid hormone receptor beta(1) (TRbeta(1)) antagonists, which are of special interest because of their potential role in safe therapies for nonthyroid disorders while avoiding the cardiac side effects. Using the calculated structural descriptors by CODESSA program, principal component analysis (PCA) was performed on the whole compounds to assist the separation of the data into the training set and the test set in QSAR analysis. Six molecular descriptors selected by genetic algorithm (GA) were used as inputs for a projection pursuit regression (PPR) study to develop a more accurate QSAR model. The PPR model performs well both in the fitting and prediction capacity. For the test set, it gave a predictive correlation coefficient (R) of 0.9450, root mean square error (RMSE) of 0.4498, and absolute average relative deviation (AARD) of 4.19%, respectively, confirming the ability of PPR for the prediction of the binding affinities of compounds to beta(1) isoform of human thyroid hormone receptor (TRbeta(1)).