A New Descriptor for Amino Acids and Its Applications in Peptide QSAR

To establish a new amino acid structure descriptor that can be applied in peptide quantitative structure activity relationship (QSAR) studies, a new descriptor, named SVMW, was derived by principal components analysis of the matrix of 160 MoRSE descriptors and 99 WHIM descriptors of amino acids. The scale was then applied in two panels of peptide QSAR that were molded by partial least square regression. The correlation coefficients (R-cum(2)), cross validation correlation coefficients (Q(LOO)(2)) were 0.821 and 0.783 for angiotensin-converting enzyme inhibitors (dipeptide), 0.991 and 0.969 for angiotensin-converting enzyme inhibitors (tri-peptides), 0.868 and 0.807 for bitter tasting thresholds, respectively. In addition, the estimation capability and generalization ability of the models were analyzed by external validation. The correlation coefficients of predicted values versus experimental ones of external samples (Q(ext)(2)) were 0.821, 0.774 and 0.964. Satisfactory results showed that information related to biological activity could be systemically expressed by SVWG scales, which may be a useful structural expression methodology for study on peptides QSAR.