Multivariate statistical methods for Port Salut Argentino cheese analysis based on ripening time, storage conditions, and sampling sites

Abstract

The objective of the present work was to compare multivariate statistical methods for the classification of Port Salut Argentino cheese samples based on ripening time (1, 6, 13, 27, and 56 days), storage conditions (traditionally ripened and ripened after frozen storage) and sampling sites (internal and external zones) using the contents of caseins, peptides and amino acids measured by chromatographic analysis as well as textural and physical parameters. In particular, two linear methods, principal component analysis (PCA) and principal component similarity (PCS), and a nonlinear method, the Kohonen self-organizing artificial neural network (Kohonen ANN), were compared. The two linear methods showed the same grouping of cheese samples according to ripening time, sampling site and storage condition. These methods are closely related in their mathematical basis and the similar grouping showed by both methods can be explained by the fact that the first three principal components explained 89.3% of the data set variation. The non-linear Kohonen ANN uses a mathematical procedure completely different from PCA; however, only slight differences were observed in the grouping of cheese samples. Those differences may be related to the weight that each model gives to every variable. One interesting feature of Kohonen ANN is that weight maps (contour plots) sometimes are superior to principal component loadings (vectors) for the understanding of relationships between the groups and the original variables.