Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis

Abstract

(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.

MALDI-TOF as a powerful tool for identifying and differentiating closely related microorganisms: the strange case of three reference strains of Paenibacillus polymyxa

“…Although ribosomal proteins are strongly conserved in the bacterial species, they may present modest variation at the microbial strain level 28 . Several authors proposed using the MALDI-TOF MS typing method coupled with statistical tools to classify and improve the identification and differentiation of phylogenetically closely related species 27 , 29 – 31 . Indeed, adopting such an approach allows for identifying a certain number of discriminative and reproducible biomarkers with a specificity at the subspecies level 32 .…”

Enhancing predictive performance for spectroscopic studies in wildlife science through a multi-model approach: A case study for species classification of live amphibians

“…The number of individuals, spectral replicates, and total number of spectra acquired for each species are provided in S3 Document . We used a nested resampling scheme where five-fold cross-validation was conducted on both the inner and outer resampling datasets; the inner resampling is used for model calibration and parameter tuning/optimization and the outer resampling returns results on the test dataset [ 101 , 111 ]. This cross-validation procedure is expected to reduce overfitting and the overall variance yielded in the estimated performance accuracies, as the resulting output is an aggregated performance measurement that is generated by taking an average of the five training runs (as opposed to a single training run) for five iterations [ 102 ].…”

Machine learning and artificial intelligence for the diagnosis of infectious diseases in immunocompromised patients

“…With the addition of supervised and unsupervised ML algorithms, more complex samples, including those containing multiple microbes, can be accurately processed. Recently, mass fingerprints for phylogenetically related Brucella species, including B. melitensis , B. abortus , and B. suis , were distinguished using ML algorithms [27]. In this study, consensus feature selection strategy, supervised, and unsupervised ML algorithms were employed, leading to 100% accuracy in species identification.…”