Machine Learning Approaches for GC–MS Data Interpretation in Flavour and Fragrance Analysis

Abstract

This review explores the integration of machine learning (ML) in the analysis of mass spectrometry data obtained by electronic impact after gas chromatography (GC–MS), with a focus on applications for the fragrance and flavour (FF) industry. It highlights recent advances in ML-driven approaches to enhance the interpretation of complex GC–MS datasets, improving efficiency in ingredient identification, classification, and quality control. Furthermore, the paper discusses various ML techniques, including supervised and unsupervised learning, and also addresses challenges such as data scarcity and intellectual property concerns.