Identifying the origin of a food product holds paramount importance in ensuring food safety, quality, and authenticity. Knowing where a food item comes from provides crucial information about its production methods, handling practices, and potential exposure to contaminants. Machine learning techniques play a pivotal role in this process by enabling the analysis of complex data sets to uncover patterns and associations that can reveal the geographical source of a food item. This study aims to investigate the potential use of explainable artificial intelligence for identifying the food origin. The case of study of Mozzarella di Bufala Campana PDO has been considered by examining the composition of the microbiota in each samples. Three different supervised machine learning algorithms have been compared and the best classifier model is represented by Random Forest with an Area Under the Curve (AUC) value of 0.93 and the top accuracy of 0.87. Machine learning models effectively classify origin, offering innovative ways to authenticate regional products and support local economies. Further research can explore microbiota analysis and extend applicability to diverse food products and contexts for enhanced accuracy and broader impact.

Understanding and exploiting the intrinsic mechanisms of tolerance to multiple stresses in plants is the new frontier of sustainable agriculture, since environmental challenges often occur simultaneously in agricultural systems. We recently identified three fragments, named PS1-70, PS1-120 and G, in the scaffold of prosystemin, the protein precursor of tomato systemin. These protein fragments efficiently protect tomato plants against Botrytis cinerea and Spodoptera littoralis larvae attacks by inducing defence-related genes. Since it was previously demonstrated that prosystemin protects tomato plants also against soil salinity, we analyzed the ability of PS1-70, PS1-120 and G to confer salt tolerance. As expected, the application of 150 mM NaCl induced 24% reduction of shoot fresh weight. The treatment with PS1-70 and G induced 9% and 8% increase of shoot fresh weight. In addition, under salt stress, there is a significant increase in root biomass in treated plants suggesting that the treatment mitigated salt stress. Noteworthy, fragments application improved the growth of shoots, indicating a biostimulant activity on tomato growth. These data correlated with the upregulation of key stress-related genes, (CAT2, APX2, and HSP90), associated with the activation of antioxidant and free radical scavenging reactions in stressed plant cells. Our results add novel tools to the complex problem of sustainable crop protection against different environmental stresses.

The origin of food products is an important factor to consider for consumers seeking authentic, high-quality, and safe products. Information about the origin provides valuable guidance for making informed decisions about food purchases and can help promote sustainable agricultural practices. Indeed, machine learning (ML) techniques offer a promising solution for evaluating the geographical origin of food products, including Mozzarella di Bufala Campana PDO. By analyzing various data sources, ML algorithms can discern patterns and associations that correlate with specific geographic regions. For instance, ML models can be trained on datasets containing information about the microbiota composition of Mozzarella di Bufala Campana PDO samples collected from different regions. By leveraging advanced classification or clustering algorithms, these models can learn to differentiate between microbiota profiles associated with distinct geographical origins. The proposed study aimed to implement an explainable artificial intelligence framework using microbiota data from Mozzarella PDO samples from Salerno and Caserta. Our analysis aimed to classify each sample into one of the two origin areas. We employed the XGB classifier, a machine learning algorithm, which achieved an accuracy of 0.825 ± 0.032, a F1-score of 0.849 ± 0.028 and an average AUC of 0.880 ± 0.026. The application of machine learning methods to classify the geographical origin of products, coupled with advanced techniques of chemical and biological analysis supported by artificial intelligence, promises to distinguish between authentic and adulterated products. It is important to ensure that the data used to train the models are representative and reliable. Machine learning could play a vital role in this context by enabling the analysis of vast amounts of data to identify patterns and characteristics unique to specific geographic regions.

Water Buffalo Mozzarella (BM) is a typical cheese from Southern Italy with unique flavor profile and texture. It is produced following a traditional back-slopping procedure and received the Protected Designation of Origin (PDO) label. To better understand the link between the production area, the microbiome composition and the flavor profile of the products, we performed a multiomic characterization of PDO BM collected from 57 different dairies located in the two main PDO production area, i.e. Caserta (n = 35) and Salerno (n = 22). Thus, we assessed the microbiome by high-throughput shotgun metagenomic sequencing and the Volatile Organic Compounds (VOCs) by gas chromatography/mass spectrometry (GC/MS). Streptococcus thermophilus, Lactobacillus helveticus, and Lactobacillus delbrueckii subsp. delbrueckii were identified as the core microbiome present in all samples. However, the microbiome taxonomic profiles resulted in a clustering of the samples based on their geographical origin, also showing that BM from Caserta had a greater microbial diversity. Consistently, Caserta and Salerno samples also showed different VOC profiles. These results suggest that the microbiome and its specific metabolic activity are part of the terroir that shape BM specific features, linking this traditional product with the area of production, thus opening new clues for improving traceability and fraud protection of traditional products.

Fermented foods (FFs) are part of the cultural heritage of several populations, and their production dates back 8000 years. Over the last similar to 150 years, the microbial consortia of many of the most widespread FFs have been characterised, leading in some instances to the standardisation of their production. Nevertheless, limited knowledge exists about the microbial communities of local and traditional FFs and their possible effects on human health. Recent findings suggest they might be a valuable source of novel probiotic strains, enriched in nutrients and highly sustainable for the environment. Despite the increasing number of observational studies and randomised controlled trials, it still remains unclear whether and how regular FF consumption is linked with health outcomes and enrichment of the gut microbiome in health-associated species. This review aims to sum up the knowledge about traditional FFs and their associated microbiomes, outlining the role of fermentation with respect to boosting nutritional profiles and attempting to establish a link between FF consumption and health-beneficial outcomes.