Wang, DanhuiGreenwood, PeytonKlein, Matthias S.2023-03-222023-03-222021This is a published version of an article that is available at https://doi.org/10.1002/ansa.202100052. Recommended citation: Wang, D., Greenwood, P., & Klein, M. S. (2021). Deep learning for rapid identification of microbes using metabolomics profiles. Metabolites, 11(12), 863. This item has been deposited in accordance with publisher copyright and licensing terms and with the author’s permission.https://hdl.handle.net/11274/14711https://doi.org/10.3390/metabo11120863Article originally published in Metabolites, 11(12), 863. English. Published online 2021. https://doi.org/10.3390/metabo11120863Rapid detection of viable microbes remains a challenge in fields such as microbial food safety. We here present the application of deep learning algorithms to the rapid detection of pathogenic and non-pathogenic microbes using metabolomics data. Microbes were incubated for 4 h in a protein-free defined medium, followed by 1D 1H nuclear magnetic resonance (NMR) spectroscopy measurements. NMR spectra were analyzed by spectral binning in an untargeted metabolomics approach. We trained multilayer (“deep”) artificial neural networks (ANN) on the data and used the resulting models to predict spectra of unknown microbes. ANN predicted unknown microbes in this laboratory setting with an average accuracy of 99.2% when using a simple feature selection method. We also describe learning behavior of the employed ANN and the optimization strategies that worked well with these networks for our datasets. Performance was compared to other current data analysis methods, and ANN consistently scored higher than random forest models and support vector machines, highlighting the potential of deep learning in metabolomics data analysis.en-USArtificial neural networksMachine learningFood safetyNMRPathogensArticle© 2021 by the authors.CC BY 4.0