The understanding of the metabolic behaviour of complex systems such as eukaryotic cells needs the development of new approaches that are able to deal with the complexity due to a large number of interactions within the system. In this paper, we applied an approach based on the combined use of in vivo NMR experiments and mathematical modelling in order to analyze the metabolic response to ethanol stress in a wild-strain of Saccharomyces cerevisiae. Considering the cellular metabolic processes resulting from activation, inhibition, and feed-back activities, we developed a model able to describe the modulation of the whole system induced by an external stress due to increasing concentrations of exogenous ethanol. This approach was able to interpret the experimental results in terms of metabolic response to exogenous ethanol in the yeast. The robustness and flexibility of the model enables it to work correctly at different initial exogenous ethanol concentrations.