Mass Spectrometry And Machine Learning For The Accurate Diagnosis Of Benzylpenicillin And Multidrug Resistance Of Staphylococcus Aureus In Bovine Mastitis

Staphylococcus aureus is a serious human and animal pathogen threat exhibiting extraordinary capacity for acquiring new antibiotic resistance traits in the pathogen population worldwide. The development of fast, affordable and effective diagnostic solutions capable of discriminating between antibiotic-resistant and susceptible S. aureus strains would be of huge benefit for effective disease detection and treatment. Here we develop a diagnostics solution that uses Matrix-Assisted Laser Desorption/Ionisation-Time of Flight Mass Spectrometry (MALDI-TOF) and machine learning, to identify signature profiles of antibiotic resistance to either multidrug or benzylpenicillin in S. aureus isolates. Using ten different supervised learning techniques, we have analysed a set of 82 S. aureus isolates collected from 67 cows diagnosed with bovine mastitis across 24 farms. For the multidrug phenotyping analysis, LDA, linear SVM, RBF SVM, logistic regression, naive Bayes, MLP neural network and QDA had Cohen's kappa values over 85.00%. For the benzylpenicillin phenotyping analysis, RBF SVM, MLP neural network, naive Bayes, logistic regression, linear SVM, QDA, LDA, and random forests had Cohen's kappa values over 85.00%. For the benzylpenicillin the diagnostic systems achieved up to (mean result standard deviation over 30 runs on the test set): accuracy = 97.54% +/- 1.91%, sensitivity = 99.93% +/- 0.25%, specificity = 95.04% +/- 3.83%, and Cohen's kappa = 95.04% +/- 3.83%. Moreover, the diagnostic platform complemented by a protein-protein network and 3D structural protein information framework allowed the identification of five molecular determinants underlying the susceptible and resistant profiles. Four proteins were able to classify multidrug-resistant and susceptible strains with 96.81% +/- 0.43% accuracy. Five proteins, including the previous four, were able to classify benzylpenicillin resistant and susceptible strains with 97.54% +/- 1.91% accuracy. Our approach may open up new avenues for the development of a fast, affordable and effective day-to-day diagnostic solution, which would offer new opportunities for targeting resistant bacteria.Author summary Antibiotic resistance is one of the biggest threats to human and animal health. The incessant emergence of new multidrug-resistant bacteria needs to be counterbalanced by the implementation of effective diagnostics solutions to detect resistance and support treatment selection. The objective of this study is the development of effective diagnostic solutions to identify resistance to benzylpenicillin and other drugs in S. aureus strains infecting dairy cattle. S. aureus is one of the most common pathogens of clinical mastitis in the dairy industry, affecting productivity, profitability, animal health and welfare, and has an extraordinary capacity for acquiring new antibiotic resistance traits. Our diagnostic solution combines machine learning and mass spectrometry. The application to a test set of 82 S. aureus isolates collected from 67 cows diagnosed with bovine mastitis across 24 farms discriminated between multidrug-resistant and susceptible strains with (mean result +/- standard deviation over 30 runs on the test set) 96.81% +/- 0.43% accuracy, and between benzylpenicillin-resistant and susceptible strains with 97.54% +/- 1.91% accuracy. Through a dedicated bioinformatics pipeline developed on the results of machine learning, we were able to obtain new insights into the molecular determinants and mechanism underlying the antibiotic resistance phenotypes. We believe that our approach may open up new avenues for the development of a fast, affordable and effective diagnostic solution which would offer new opportunities for targeting resistant bacteria and support with timely, accurate and targeted treatment selection.