Mass spectrometry and machine learning for the accurate diagnosis of benzylpenicillin and multidrug resistance of Staphylococcus aureus in bovine mastitis

Abstract

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, naïve Bayes, MLP neural network and QDA had Cohen’s kappa values over 85.00%. For the benzylpenicillin phenotyping analysis, RBF SVM, MLP neural network, naïve 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.

PredictingPseudomonas aeruginosadrug resistance using artificial intelligence and clinical MALDI-TOF mass spectra

“…Next, we introduced a novel, yet simple method called dynamic binning to extract features from the preprocessed spectra. Dynamic binning addresses the shortcomings of two commonly used feature engineering methods for MALDI-TOF MS data: peak detection (i.e., using intensity peaks as features) [13, 15, 18], and fixed-length binning (i.e., using bins of pre-specified size as features) [14, 17]. The former approach requires additional analysis steps for peak alignment and potentially overlooks regions without peaks, while the latter approach often generates a large feature set that greatly outnumbers sample size, thereby increasing the chances of over-fitting.…”

Current molecular approach for diagnosis of MRSA: a meta-narrative review

“…A recent study by Tang and colleagues ( 41 ) reported that MALDI-TOF MS on intact bacteria combined with a refined analysis framework allows accurate classification of methicillin-sensitive Staphylococcus aureus (MSSA) and MRSA. Esener and colleagues showed that MALDI-TOF has a sensitivity of 99.93% ± 0.25%, specificity of 95.04% ± 3.83%, and accuracy = 97.54% ± 1.91% ( 42 ). MALDI-TOF is low in cost, and analysis can be conducted within a short time, allowing rapid microbial resistance to be detected.…”

Precision Medicine Approaches with Metabolomics and Artificial Intelligence

“…SVM achieved 91.66% accuracy in identifying two groups of samples based on seven features, and the authors proposed biomarkers that play a role in pathogenesis, such as the metabolism of nicotinamide and glutathione as well as tryptophan and sphingolipids. In another recent study, SVM was used to classify benzylpenicillin and multidrug resistance in Staphylococcus aureus [ 54 ]. The authors performed matrix-assisted laser desorption/ionization–time of flight mass spectrometry to identify signature profiles of antibiotic resistance in S. aureus isolates.…”