A quantitative structure-activity relationship (QSAR) study of peptide drugs based on a new of amino acids

Abstract

The quantitative structure-activity relationship (QSAR) approach is used for finding the relationships between molecular structures and the activity of peptide drugs. In this work, the stepwise multiple regression method was employed to select the optimal subset of that have significant contributions to the drug activity of 21 oxytocin analogues, 48 bitter tasting threshold activities and 58 angiotensin-converting enzyme inhibitors. A new set of , SVWGM, was used for the prediction of the activity of the peptide drugs and then were used to build a model by the partial least squares method, The stability and generalization ability of the model was strictly analyzed by both internal and external validations, by cross-validation and external validation correlations.