Zur Kurzanzeige

2022-08-17Zeitschriftenartikel
Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis
dc.contributor.authorDematheis, Flavia
dc.contributor.authorWalter, Mathias C.
dc.contributor.authorLang, Daniel
dc.contributor.authorAntwerpen, Markus
dc.contributor.authorScholz, Holger C.
dc.contributor.authorPfalzgraf, Marie-Theres
dc.contributor.authorMantel, Enrico
dc.contributor.authorHinz, Christin
dc.contributor.authorWölfel, Roman
dc.contributor.authorZange, Sabine
dc.date.accessioned2024-09-19T10:07:47Z
dc.date.available2024-09-19T10:07:47Z
dc.date.issued2022-08-17none
dc.identifier.other10.3390/microorganisms10081658
dc.identifier.urihttp://edoc.rki.de/176904/12228
dc.description.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.eng
dc.language.isoengnone
dc.publisherRobert Koch-Institut
dc.rights(CC BY 3.0 DE) Namensnennung 3.0 Deutschlandger
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/de/
dc.subjectMALDI-TOF MSeng
dc.subjectbrucella melitensiseng
dc.subjectb. suiseng
dc.subjectb. arbortuseng
dc.subjectmachine learningeng
dc.subjectnested k-fold cross validationeng
dc.subjectfeature selectioneng
dc.subjectReng
dc.subject.ddc610 Medizin und Gesundheitnone
dc.titleMachine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suisnone
dc.typearticle
dc.identifier.urnurn:nbn:de:0257-176904/12228-0
dc.type.versionpublishedVersionnone
local.edoc.container-titleMicroorganismsnone
local.edoc.container-issn2076-2607none
local.edoc.pages14none
local.edoc.type-nameZeitschriftenartikel
local.edoc.container-typeperiodical
local.edoc.container-type-nameZeitschrift
local.edoc.container-urlhttps://www.mdpi.com/journal/microorganismsnone
local.edoc.container-publisher-nameMDPInone
local.edoc.container-volume10none
local.edoc.container-issue8none
local.edoc.container-reportyear2022none
dc.description.versionPeer Reviewednone

Zur Kurzanzeige