1H-NMR Metabolomics as a Tool for Winemaking Monitoring

Abstract

The chemical composition of wine is known to be influenced by multiple factors including some viticulture practices and winemaking processes. ¹H-NMR metabolomics has been successfully applied to the study of wine authenticity. In the present study, ¹H-NMR metabolomics in combination with multivariate analysis was applied to investigate the effects of grape maturity and enzyme and fining treatments on Cabernet Sauvignon wines. A total of forty wine metabolites were quantified. Three different stages of maturity were studied (under-maturity, maturity and over-maturity). Enzyme treatments were carried out using two pectolytic enzymes (E1 and E2). Finally, two proteinaceous fining treatments were compared (vegetable protein, fining F1; pea protein and PVPP, fining F2). The results show a clear difference between the three stages of maturity, with an impact on different classes of metabolites including amino acids, organic acids, sugars, phenolic compounds, alcohols and esters. A clear separation between enzymes E1 and E2 was observed. Both fining agents had a significant effect on metabolite concentrations. The results demonstrate that ¹H-NMR metabolomics provides a fast and robust approach to study the effect of winemaking processes on wine metabolites. These results support the interest to pursue the development of ¹H-NMR metabolomics to investigate the effects of winemaking on wine quality.

Keywords: 1H-NMR; metabolomics; wine; winemaking.

Figure 1

Typical ¹H-NMR spectrum of wine after water and ethanol suppression (NOESYGPPS1D sequence). Identified constituents are listed in Table 1 (compounds in green are quantified on the ZGPR sequence).

Figure 2

Multivariate analysis of ¹H-NMR spectra of wine samples from grapes harvested at three different stages of maturity (M1: under-maturity; M2: maturity; M3: over-maturity): (a) PCA score plot; (b) OPLS-DA score plot; (c) OPLS-DA score showing separation of M1 and M2 samples; (d) loadings from OPLS-DA between M1 and M2 samples; (e) OPLS-DA score showing separation of M2 and M3 samples; (f) loadings from OPLS-DA between M2 and M3 samples (t[1] and to[1]: first predictive and orthogonal components; t[2]: second predictive component; pq[1] and poso[1]: predictive and orthogonal component loadings).

Figure 3

Multivariate analysis of ¹H-NMR spectra of wine samples treated by different enzymes (E0: untreated; E1: enzyme 1; E2: enzyme 2): (a) OPLS-DA score plot; (b) loading plot; (c) boxplots of 11 most discriminant wine constituents (t[1] and t[2]: first and second predictive components; pq[1] and pq[2]: first and second predictive component loadings). The significance in the difference was calculated by ANOVA followed by Tukey’s multiple comparison test (indicated as * p < 0.05, ** p < 0.01, *** p < 0.001).

Figure 4

Multivariate analysis of ¹H-NMR spectra of wine samples treated by different finings (F0: untreated; F1: fining 1; F2: fining 2): (a) OPLS-DA score plot; (b) loading plot; (c) boxplots of 6 most discriminant wine constituents (t[1] and t[2]: first and second predictive components; pq[1] and pq[2]: first and second predictive component loadings). The significance in the difference was calculated by ANOVA followed by Tukey’s multiple comparison test (indicated as * p < 0.05, ** p < 0.01, *** p < 0.001).