Differentiation between Weissella cibaria and Weissella confusa Using Machine-Learning-Combined MALDI-TOF MS

Although Weissella cibaria and W. confusa are essential food-fermenting bacteria, they are also opportunistic pathogens. Despite these species being commercially crucial, their taxonomy is still based on inaccurate identification methods. In this study, we present a novel approach for identifying two important Weissella species, W. cibaria and W. confusa, by combining matrix-assisted laser desorption/ionization and time-of-flight mass spectrometer (MALDI-TOF MS) data using machine-learning techniques. After on- and off-plate protein extraction, we observed that the BioTyper database misidentified or could not differentiate Weissella species. Although Weissella species exhibited very similar protein profiles, these species can be differentiated on the basis of the results of a statistical analysis. To classify W. cibaria, W. confusa, and non-target Weissella species, machine learning was used for 167 spectra, which led to the listing of potential species-specific mass-to-charge (m/z) loci. Machine-learning techniques including artificial neural networks, principal component analysis combined with the K-nearest neighbor, support vector machine (SVM), and random forest were used. The model that applied the Radial Basis Function kernel algorithm in SVM achieved classification accuracy of 1.0 for training and test sets. The combination of MALDI-TOF MS and machine learning can efficiently classify closely-related species, enabling accurate microbial identification.

Automated summary

In this study, a novel approach combining mass spectrometry and machine learning techniques was used to accurately identify the important food-fermenting bacteria Weissella cibaria and W. confusa. Through protein analysis and statistical analysis, it was found that although these two bacterial species exhibited similar protein profiles, they could be differentiated and classified using machine learning methods. The combination of mass spectrometry and machine learning enables accurate microbial identification.