Predicting and improving complex beer flavor through machine learning.

The perception and appreciation of food flavor depends on many interacting chemical compounds and external factors, and therefore proves challenging to understand and predict. Here, we combine extensive chemical and sensory analyses of 250 different beers to train machine learning models that allow predicting flavor and consumer appreciation. For each beer, we measure over 200 chemical properties, perform quantitative descriptive sensory analysis with a trained tasting panel and map data from over 180,000 consumer reviews to train 10 different machine learning models. The best-performing algorithm, Gradient Boosting, yields models that significantly outperform predictions based on conventional statistics and accurately predict complex food features and consumer appreciation from chemical profiles. Model dissection allows identifying specific and unexpected compounds as drivers of beer flavor and appreciation. Adding these compounds results in variants of commercial alcoholic and non-alcoholic beers with improved consumer appreciation. Together, our study reveals how big data and machine learning uncover complex links between food chemistry, flavor and consumer perception, and lays the foundation to develop novel, tailored foods with superior flavors.

Novel Saccharomyces cerevisiae variants slow down the accumulation of staling aldehydes and improve beer shelf-life.

Beer quality generally diminishes over time as staling compounds accumulate through various oxidation reactions. Here, we show that refermentation, a traditional practice where Saccharomyces cerevisiae cells are added to beer prior to bottling, diminishes the accumulation of staling aldehydes. However, commonly used beer yeasts only show a limited lifespan in beer. Using high-throughput screening and breeding, we were able to generate novel S. cerevisiae hybrids that survive for over a year in beer. Extensive chemical and sensory analyses of the two most promising hybrids showed that they slow down the accumulation of staling aldehydes, such as furfural and trans-2-nonenal and significantly increased beer flavor stability for up to 12 months. Moreover, the strains did not change the original flavor of the beer, highlighting their potential to be integrated in existing products. Together, these results demonstrate the ability to breed novel microbes that function as natural and sustainable anti-oxidative food preservatives.