Abstract
In this work, a descriptor, SVRG (principal component scores vector of radial distribution function descriptors and geometrical descriptors), was derived from principal component analysis (PCA) of a matrix of two structural variables of coded amino acids, including radial distribution function index (RDF) and geometrical index. SVRG scales were then applied in three panels of peptide quantitative structure–activity relationships (QSARs) which were modelled by partial least squares regression (PLS). The obtained models with the correlation coefficient (), cross-validation correlation coefficient () were 0.910 and 0.863 for 48 bitter-tasting dipeptides; 0.968 and 0.931 for 21 oxytocin analogues; and 0.992 and 0.954 for 20 thromboplastin inhibitors. Satisfactory results showed that SVRG contained much chemical information relating to bioactivities. The approach may be a useful structural expression methodology for studies on peptide QSAR.
Acknowledgements
The authors appreciate the financial support from the Scientific Research Planning Program of the Education Department of Shaanxi Province (11JK0602), the Scientific Research Planning Program of Shaanxi Province of China (2009JQ2005), the Scientific Research Planning Program of Yulin City and the Graduate Innovation Fund of Shaanxi University of Science and Technology.