The binding rate to human plasma protein for 70 diverse drugs was modeled using the descriptors calculated from the molecular structure along with a quantitative structure-activity relationship (QSAR) technique. The heuristic method (HM) and support vector machine (SVM) were utilized to construct the linear and nonlinear prediction models, leading to a good cross-validation correlation coefficient R_cv² of 0.80 and 0.82, respectively. By comparison the stability with prediction ability of the models, it was found that support vector machine was a good method for predicting the binding rate of drug to human plasma protein.

Key words: quantitative structure-activity relationship, binding rate to human plasma protein, support vector machine, heuristic method