Besides good bacterial identification at species level, speed and ease of taxonomic synchronization are major advantages of this computational speciesīacterial communities in the phylloplane of Prunus species. These results show that machine learning proves very useful for FAME- based bacterial species identification. Moreover, our machine learning approach also outperformed the Sherlock MIS (MIDI Inc., Newark, DE, USA). The random forests models outperform those of the other machine learning techniques. For Bacillus, Paenibacillus and Pseudomonas, random forests have resulted in sensitivity values, respectively, 0.847, 0.901 and 0.708. Notwithstanding the known limited discriminative power of FAME analysis for species identification, the computational models have resulted in good species identification results for the three genera. Nearly perfect identification has been achieved at genus level. Three techniques have been considered: artificial neural networks, random forests and support vector machines. Through the application of machine learning techniques in a supervised strategy, different computational models have been built for genus and species identification. The corresponding data set covers 74, 44 and 95 validly published bacterial species, respectively, represented by 961, 3 standard FAME profiles. Only those profiles resulting from standard growth conditions have been retained. From the database, we have selected FAME profiles of individual strains belonging to the genera Bacillus, Paenibacillus and Pseudomonas. In this study, we focus on bacterial fatty acid methyl ester (FAME) profiling as a broadly used first-line identification method.
Consequently, back-end identification libraries need to be synchronized with the List of Prokaryotic names with Standing in Nomenclature. The swift pace of bacterial species (re-)definitions has a serious impact on the accuracy and completeness of first-line identification methods. In the last decade, bacterial taxonomy witnessed a huge expansion. Slabbinck, Bram De Baets, Bernard Dawyndt, Peter De Vos, Paul
Towards large-scale FAME- based bacterial species identification using machine learning techniques.