SVEEVA descriptor application to peptide QSAR

Abstract

A new descriptor, SVEEVA (principal component scores vector of electronic eigenvalue descriptors), was derived from principal component analysis (PCA) of a matrix of 220 electronic eigenvalue descriptors of coded amino acids. SVEEVA scales were then applied in three panels of peptide quantitative structure-activity relationship (QSAR) that were modeled by partial least squares regression (PLS). The obtained models with the correlation coefficient ($R{{\rm cum}}{2} $), cross-validation correlation coefficient ($Q{{\rm LOO}}{2} $) were 0.894 and 0.839 for 58 angiotensin-converting enzyme inhibitors, 0.995 and 0.949 for 12 antimicrobial polypeptides, and 0.995 and 0.976 for 20 thromboplastin inhibitors. Satisfactory results showed that information related to biological activity can be systemically expressed by SVEEVA scales, which may be a useful structural expression methodology for study on peptide QSAR. A new descriptor of coded amino acids, SVEEVA, was applied in quantitative structure activity relationship of angiotensin-converting enzyme inhibitors, antimicrobial polypeptides and thromboplastin inhibitors. The results showed that SVEEVA could better characterize structural features of peptides and provide more sound statistical models. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.