Authentication of Douro DO monovarietal red wines based on anthocyanin profile: Comparison of partial least squares ? discriminant analysis, decision trees and artificial neural networks

In this study, the feasibility of discriminating monovarietal red wines from Touriga Nacional (TN), Touriga Franca (TF), and Tinta Roriz (TR) from Douro Demarcated Region (DDR) using the anthocyanin profile was investigated in combination with partial least squares ? discrimination analysis (PLS-DA), classification and regression trees (CART) and artificial neural networks (ANN). CART and ANN were more accurate in the classification of monovarietal wines according to their origin with a 100% classification rate in the test set. PLS-DA presented an accuracy of 91.4%. The variables most important for monovarietal wines authentication were petunidin-3-glucoside, malvidin-3-acetylglucoside, and cyanidin-3-glucoside for the PLS-DA, petunidin-3glucoside, peonidin-3-acetylglucoside, and malvidin-3-acetylglucoside for CART analysis, and malvidin-3acetylglucoside, petunidin-3-glucoside, malvidin-3-glucoside, peonidin-3-coumaroylglucoside and delphinidin3-glucoside for ANN. The results demonstrate that the anthocyanin profile of Touriga Nacional, Touriga Franca, and Tinta Roriz Douro Denomination of Origin monovarietal red wines combined with multivariate analysis is an effective tool for verifying their authenticity.