Artificial Intelligence (AI) Smelling Machines Based on Multidimensional Chromatography: How Information Capacity and Flexibility Make Greener an Analytical Tool

Food quality has molecular foundation in the food metabolome (i.e., the complete set of primary and specialized metabolites together with volatiles generated by endogenous or exogenous phenomena –the volatilome). Modern “omics” disciplines, and their investigation approaches, have a great potential in the context of food quality objectification especially in the context of the transition toward greener concepts of analytical measurement. The concurrent quali-quantitative investigation on target and untargeted features/components offers the opportunity to exploit the full potential of each single analytical run providing answers to many different question. The contribution focuses on the objectification of industrial quality of raw hazelnuts (Corylus avellana L.), a primary ingredient for confectionery industry, where the concept of Artificial Intelligence (AI) smelling based on sensomics [1] is realized on a fully automated platform including automated headspace solid-phase microextraction (HS-SPME) followed by comprehensive two-dimensional gas chromatography (GC×GC) and parallel detection by mass spectrometry (qMS) and flame ionization detector (FID). Hazelnut volatilome encrypts information on many key-quality variables (e.g., cultivar, geographical origin, post-harvest treatments, bacteria/molds contamination, oxidative stability, and sensory perception) and by the AI smelling machine approach, it is possible to consistently monitor more than 450 untargeted and targeted features (chemical fingerprint – Figure 1A) over hundreds of samples while accurately quantifying more than 40 target analytes. Within them, key-aromas, potent odorants, and spoilage markers are included. Quantitative “AI” perceptive maps (Figure 1B), based on odor activity values (OAVs), enable consistent samples clustering based on the overall smell, while guaranteeing results transferability over time. Of particular interest is the accurate detection of spoilage odorants, which makes this technique suitable for industrial quality control purposes.