{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T22:30:38Z","timestamp":1792103438571,"version":"4.4.0"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Microorganisms"],"abstract":"<jats:p>(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.<\/jats:p>","DOI":"10.3390\/microorganisms10081658","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T22:53:30Z","timestamp":1660776810000},"page":"1658","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis"],"prefix":"10.3390","volume":"10","author":[{"given":"Flavia","family":"Dematheis","sequence":"first","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3012-2626","authenticated-orcid":false,"given":"Mathias C.","family":"Walter","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-0716","authenticated-orcid":false,"given":"Daniel","family":"Lang","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4013-8808","authenticated-orcid":false,"given":"Markus","family":"Antwerpen","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger C.","family":"Scholz","sequence":"additional","affiliation":[{"name":"Robert Koch Institut (RKI), Centre for Biological Threats and Special Pathogens, Seestr. 10, 13353 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Theres","family":"Pfalzgraf","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrico","family":"Mantel","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christin","family":"Hinz","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-7821","authenticated-orcid":false,"given":"Roman","family":"W\u00f6lfel","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8721-9248","authenticated-orcid":false,"given":"Sabine","family":"Zange","sequence":"additional","affiliation":[{"name":"Bundeswehr Institute of Microbiology, Neuherbergstrasse 11, 80937 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1111\/j.1600-065X.2010.00982.x","article-title":"An evolutionary strategy for a stealthy intracellular Brucella pathogen","volume":"240","author":"Martirosyan","year":"2011","journal-title":"Immunol. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"105","DOI":"10.20506\/rst.32.1.2193","article-title":"Pathogenesis and pathobiology of brucellosis in livestock","volume":"32","author":"Poester","year":"2013","journal-title":"Rev. Sci. Tech. OIE"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1016\/j.jfda.2019.01.001","article-title":"Current status of MALDI-TOF mass spectrometry in clinical microbiology","volume":"27","author":"Hou","year":"2019","journal-title":"J. Food Drug Anal."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ferreira, L., Casta\u00f1o, S.V., S\u00e1nchez-Juanes, F., Gonz\u00e1lez-Cabrero, S., Menegotto, F., Ordu\u00f1a-Domingo, A., Gonz\u00e1lez-Buitrago, J.M., and Mu\u00f1oz-Bellido, J.L. (2010). Identification of Brucella by MALDI-TOF Mass Spectrometry. Fast and Reliable Identification from Agar Plates and Blood Cultures. PLoS ONE, 5.","DOI":"10.1371\/journal.pone.0014235"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e01900-17","DOI":"10.1128\/JCM.01900-17","article-title":"Improved Discrimination of Bacillus anthracis from Closely Related Species in the Bacillus cereus Sensu Lato Group Based on Matrix-Assisted Laser Desorption Ionization\u2013Time of Flight Mass Spectrometry","volume":"56","author":"Pauker","year":"2018","journal-title":"J. Clin. Microbiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2469","DOI":"10.1007\/s11831-021-09660-0","article-title":"Automated Bacterial Classifications Using Machine Learning Based Computational Techniques: Architectures, Challenges and Open Research Issues","volume":"29","author":"Kotwal","year":"2022","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","article-title":"A guide to machine learning for biologists","volume":"23","author":"Greener","year":"2021","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lee, J., Shin, Y., Kim, S., Rho, K., and Park, K.H. (2017, January 23\u201325). SVM Classification Model of Similar Bacteria Species using Negative Marker: Based on Matrix-Assisted Laser Desorption\/Ionization Time-of-Flight Mass Spectrometry. Proceedings of the 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE), Washington, DC, USA.","DOI":"10.1109\/BIBE.2017.00-64"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.talanta.2003.11.034","article-title":"Forward selection radial basis function networks applied to bacterial classification based on MALDI-TOF-MS","volume":"63","author":"Zhang","year":"2004","journal-title":"Talanta"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7229","DOI":"10.1128\/AEM.00857-09","article-title":"Identification of Bacillus anthracis by Using Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry and Artificial Neural Networks","volume":"75","author":"Lasch","year":"2009","journal-title":"Appl. Environ. Microbiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1128\/JCM.02428-15","article-title":"Rapid Detection of Vancomycin-Intermediate Staphylococcus aureus by Matrix-Assisted Laser Desorption Ionization\u2013Time of Flight Mass Spectrometry","volume":"54","author":"Mather","year":"2016","journal-title":"J. Clin. Microbiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"163","DOI":"10.4265\/bio.22.163","article-title":"Rapid Discrimination between Methicillin-Sensitive and Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF Mass Spectrometry","volume":"22","author":"Sogawa","year":"2017","journal-title":"Biocontrol Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1016\/j.cmi.2020.03.014","article-title":"Machine learning for microbial identification and antimicrobial susceptibility testing on MALDI-TOF mass spectra: A systematic review","volume":"26","author":"Weis","year":"2020","journal-title":"Clin. Microbiol. Infect."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1002\/cem.1180040607","article-title":"Multivariate calibration, H.M.; Naes, T. Wiley, New York, 1989. ISBN 0 471 90979 3. Price: \u00a375.00, US$138.00. No. of pages: 504","volume":"4","year":"1990","journal-title":"J. Chemom."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1093\/bioinformatics\/bts447","article-title":"MALDIquant: A versatile R package for the analysis of mass spectrometry data","volume":"28","author":"Gibb","year":"2012","journal-title":"Bioinformatics"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Vabalas, A., Gowen, E., Poliakoff, E., and Casson, A.J. (2019). Machine learning algorithm validation with a limited sample size. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0224365"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Georgi, E., Walter, M.C., Pfalzgraf, M.-T., Northoff, B., Holdt, L.M., Scholz, H.C., Zoeller, L., Zange, S., and Antwerpen, M.H. (2017). Whole genome sequencing of Brucella melitensis isolated from 57 patients in Germany reveals high diversity in strains from Middle East. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0175425"},{"key":"ref_18","first-page":"1464","article-title":"Evaluation of genus-specific and species-specific real-time PCR assays for the identification of Brucella spp.","volume":"45","author":"Scholz","year":"2007","journal-title":"Clin. Chem. Lab. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.mimet.2009.10.015","article-title":"Advancement of a multiplex PCR for the differentiation of all currently described Brucella species","volume":"80","author":"Draeger","year":"2010","journal-title":"J. Microbiol. Methods"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2912","DOI":"10.1128\/JCM.00389-09","article-title":"Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry for Fast and Reliable Identification of Clinical Yeast Isolates","volume":"47","author":"Marklein","year":"2009","journal-title":"J. Clin. Microbiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1198\/016214502753479248","article-title":"Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data","volume":"97","author":"Dudoit","year":"2002","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1093\/bioinformatics\/btl117","article-title":"Pvclust: An R package for assessing the uncertainty in hierarchical clustering","volume":"22","author":"Suzuki","year":"2006","journal-title":"Bioinformatics"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mesureur, J., Arend, S., Celli\u00e8re, B., Courault, P., Cotte-Pattat, P.-J., Totty, H., Deol, P., Mick, V., Girard, V., and Touchberry, J. (2018). A MALDI-TOF MS database with broad genus coverage for species-level identification of Brucella. PLoS Negl. Trop. Dis., 12.","DOI":"10.1371\/journal.pntd.0006874"},{"key":"ref_24","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"CIN.S7111","DOI":"10.4137\/CIN.S7111","article-title":"A Jackknife and Voting Classifier Approach to Feature Selection and Classification","volume":"10","author":"Taylor","year":"2011","journal-title":"Cancer Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.neuroimage.2017.06.061","article-title":"Cross-validation failure: Small sample sizes lead to large error bars","volume":"180","author":"Varoquaux","year":"2018","journal-title":"NeuroImage"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.neuroimage.2016.02.079","article-title":"Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls","volume":"145","author":"Arbabshirani","year":"2017","journal-title":"NeuroImage"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","year":"2006","journal-title":"BMC Bioinform."}],"container-title":["Microorganisms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2607\/10\/8\/1658\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:11:04Z","timestamp":1760141464000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2607\/10\/8\/1658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,17]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["microorganisms10081658"],"URL":"https:\/\/doi.org\/10.3390\/microorganisms10081658","relation":{},"ISSN":["2076-2607"],"issn-type":[{"value":"2076-2607","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,17]]}}}