(1) Background: MALDI-TOF mass spectrometry (MS) is the gold standard for microbial fingerprinting, however, for phylogenetically closely related species, the resolution power drops down to the genus level. In this study, we analyzed MALDI-TOF spectra from 44 strains of B. melitensis, B. suis and B. abortus to identify the optimal classification method within popular supervised and unsupervised machine learning (ML) algorithms. (2) Methods: A consensus feature selection strategy was applied to pinpoint from among the 500 MS features those that yielded the best ML model and that may play a role in species differentiation. Unsupervised k-means and hierarchical agglomerative clustering were evaluated using the silhouette coefficient, while the supervised classifiers Random Forest, Support Vector Machine, Neural Network, and Multinomial Logistic Regression were explored in a fine-tuning manner using nested k-fold cross validation (CV) with a feature reduction step between the two CV loops. (3) Results: Sixteen differentially expressed peaks were identified and used to feed ML classifiers. Unsupervised and optimized supervised models displayed excellent predictive performances with 100% accuracy. The suitability of the consensus feature selection strategy for learning system accuracy was shown. (4) Conclusion: A meaningful ML approach is here introduced, to enhance Brucella spp. classification using MALDI-TOF MS data.

Brucellosis, mainly caused by Brucella (B.) melitensis, is associated with a risk of chronification and relapses. Antimicrobial susceptibility testing (AST) standards for B. melitensis are not available, and the agent is not yet listed in the EUCAST breakpoint tables. CLSI recommendations for B. melitensis exist, but they do not fulfill the requirements of the ISO 20776 standard regarding the culture medium and the incubation conditions. Under the third EU Health Programme, laboratories specializing in the diagnostics of highly pathogenic bacteria in their respective countries formed a working group within a Joint Action aiming to develop a suitable method for the AST of B. melitensis. Under the supervision of EUCAST representatives, this working group adapted the CLSI M45 document to the ISO 20776 standard after testing and validation. These adaptations included the comparison of various culture media, culture conditions and AST methods. A Standard Operation Procedure was derived and an interlaboratory validation was performed in order to evaluate the method. The results showed pros and cons for both of the two methods but also indicate that it is not necessary to abandon Mueller–Hinton without additives for the AST of B. melitensis.