摘要：Streptococcus uberis is one of the most common pathogens of clinical mastitis in the dairy industry. Knowledge of pathogen transmission route is essential for the selection of the most suitable intervention. Here we show that spectral profiles acquired from clinical isolates using matrix-assisted laser desorption ionization/time of flight (MALDI-TOF) can be used to implement diagnostic classifiers based on machine learning for the successful discrimination of environmental and contagious S. uberis strains. Classifiers dedicated to individual farms achieved up to 97.81% accuracy at cross-validation when using a genetic algorithm, with Cohen's kappa coefficient of 0.94. This indicates the potential of the proposed methodology to successfully support screening at the herd level. A global classifier developed on merged data from 19 farms achieved 95.88% accuracy at cross-validation (kappa 0.93) and 70.67% accuracy at external validation (kappa 0.34), using data from another 10 farms left as holdout. This indicates that more work is needed to develop a screening solution successful at the population level. Significant MALDI-TOF spectral peaks were extracted from the trained classifiers. The peaks were found to correspond to bacteriocin and ribosomal proteins, suggesting that immunity, growth and competition over nutrients may be correlated to the different transmission routes.
