Publications

Mass spectrometry imaging (MSI) techniques enable the generation of molecular maps from complex and heterogeneous matrices. A burger patty, whether plant-based or meat-based, represents one such complex matrix where studying the spatial distribution of components can unveil crucial features relevant to the consumer experience or production process. Furthermore, the MSI data can aid in the classification of ingredients and composition. Thin sections of different burger samples and vegetable constituents (carrot, pea, pepper, onion, and corn) were prepared for matrix-assisted laser desorption/ionization (MALDI) and desorption electrospray ionization (DESI) MSI analysis. MSI measurements were performed on all samples, and the data sets were processed to build three machine learning models aimed at detecting meat adulteration in vegetable burger samples, identifying individual ingredients within the vegetable burger matrix, and discriminating between burgers from different manufacturers. Ultimately, the successful detection of adulteration and differentiation of various burger recipes and their constituent ingredients were achieved. This study demonstrates the potential of MSI coupled with building machine learning models to enable the comprehensive characterization of burgers, addressing critical concerns for both the food industry and consumers.

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging is a potent analytical tool that provides spatially resolved chemical information on surfaces at the microscale. However, the hyperspectral nature of ToF-SIMS datasets can be challenging to analyze and interpret. Both supervised and unsupervised machine learning (ML) approaches are increasingly useful to help analyze ToF-SIMS data. Random Forest (RF) has emerged as a robust and powerful algorithm for processing mass spectrometry data. This machine learning approach offers several advantages, including accommodating nonlinear relationships, robustness to outliers in the data, managing the high-dimensional feature space, and mitigating the risk of overfitting. The application of RF to ToF-SIMS imaging facilitates the classification of complex chemical compositions and the identification of features contributing to these classifications. This tutorial aims to assist nonexperts in either machine learning or ToF-SIMS to apply Random Forest to complex ToF-SIMS datasets.