The analysis of volatile compounds through flavoromics and machine learning to identify the origin of traditional Chinese fermented shrimp paste from different regions

Abstract

Traditional Chinese fermented shrimp paste is a national geographical indication product with a distinctly regional flavor. The great commercial value and highly appreciated aroma urgently require establishing reliable methods to define the origin of shrimp paste and dissect the aroma essence. Therefore, in this study, flavoromics, chemometrics, and data augmented machine learning were performed to analyze shrimp paste from different regions of Bohai Bay, China. The results showed that shrimp paste contained several volatile compounds, including sulfur-containing compounds, nitrogen-containing compounds, aldehydes, and alcohols. In addition, chemometric and flavor association networks indicated that higher salt content produces some volatile compounds, such as 2-heptanone and phenylethanol. Furthermore, the prominent fruitiness and fermented aromas were associated with some key aroma substances, such as (E)-2-octenal and phenylethanol. Finally, a classification model for the origin identification of shrimp paste was developed. The results showed that seven trained machine learning models, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN), were able to accurately (100%) identify the origin of shrimp paste. In summary, this study provides a theoretical support and application basis for identifying the origin and protection of the characteristic geographical flavor of shrimp paste.