
Fast pathogen identification using single-cell matrix-assisted laser desorption/ionization-aerosol time-of-flight mass spectrometry data and deep learning methods
- Author
- Christina Papagiannopoulou (UGent) , René Parchen, Peter Rubbens and Willem Waegeman (UGent)
- Organization
- Abstract
- In diagnostics of infectious diseases, matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry (MALDI-TOF MS) can be applied for the identification of pathogenic microorganisms. However, to achieve a trustworthy identification from MALDI-TOF MS data, a significant amount of biomass should be considered. The bacterial load that potentially occurs in a sample is therefore routinely amplified by culturing, which is a time-consuming procedure. In this paper, we show that culturing can be avoided by conducting MALDI-TOF MS on individual bacterial cells. This results in a more rapid identification of species with an acceptable accuracy. We propose a deep learning architecture to analyze the data and compare its performance with traditional supervised machine learning algorithms. We illustrate our workflow on a large data set that contains bacterial species related to urinary tract infections. Overall we obtain accuracies up to 85% in discriminating five different species.
- Keywords
- Analytical Chemistry, DESORPTION IONIZATION-TIME, URINARY-TRACT-INFECTIONS, BACTERIA, CLASSIFICATION, DIAGNOSIS, MS
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.39 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8665242
- MLA
- Papagiannopoulou, Christina, et al. “Fast Pathogen Identification Using Single-Cell Matrix-Assisted Laser Desorption/Ionization-Aerosol Time-of-Flight Mass Spectrometry Data and Deep Learning Methods.” ANALYTICAL CHEMISTRY, vol. 92, no. 11, 2020, pp. 7523–31, doi:10.1021/acs.analchem.9b05806.
- APA
- Papagiannopoulou, C., Parchen, R., Rubbens, P., & Waegeman, W. (2020). Fast pathogen identification using single-cell matrix-assisted laser desorption/ionization-aerosol time-of-flight mass spectrometry data and deep learning methods. ANALYTICAL CHEMISTRY, 92(11), 7523–7531. https://doi.org/10.1021/acs.analchem.9b05806
- Chicago author-date
- Papagiannopoulou, Christina, René Parchen, Peter Rubbens, and Willem Waegeman. 2020. “Fast Pathogen Identification Using Single-Cell Matrix-Assisted Laser Desorption/Ionization-Aerosol Time-of-Flight Mass Spectrometry Data and Deep Learning Methods.” ANALYTICAL CHEMISTRY 92 (11): 7523–31. https://doi.org/10.1021/acs.analchem.9b05806.
- Chicago author-date (all authors)
- Papagiannopoulou, Christina, René Parchen, Peter Rubbens, and Willem Waegeman. 2020. “Fast Pathogen Identification Using Single-Cell Matrix-Assisted Laser Desorption/Ionization-Aerosol Time-of-Flight Mass Spectrometry Data and Deep Learning Methods.” ANALYTICAL CHEMISTRY 92 (11): 7523–7531. doi:10.1021/acs.analchem.9b05806.
- Vancouver
- 1.Papagiannopoulou C, Parchen R, Rubbens P, Waegeman W. Fast pathogen identification using single-cell matrix-assisted laser desorption/ionization-aerosol time-of-flight mass spectrometry data and deep learning methods. ANALYTICAL CHEMISTRY. 2020;92(11):7523–31.
- IEEE
- [1]C. Papagiannopoulou, R. Parchen, P. Rubbens, and W. Waegeman, “Fast pathogen identification using single-cell matrix-assisted laser desorption/ionization-aerosol time-of-flight mass spectrometry data and deep learning methods,” ANALYTICAL CHEMISTRY, vol. 92, no. 11, pp. 7523–7531, 2020.
@article{8665242, abstract = {{In diagnostics of infectious diseases, matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry (MALDI-TOF MS) can be applied for the identification of pathogenic microorganisms. However, to achieve a trustworthy identification from MALDI-TOF MS data, a significant amount of biomass should be considered. The bacterial load that potentially occurs in a sample is therefore routinely amplified by culturing, which is a time-consuming procedure. In this paper, we show that culturing can be avoided by conducting MALDI-TOF MS on individual bacterial cells. This results in a more rapid identification of species with an acceptable accuracy. We propose a deep learning architecture to analyze the data and compare its performance with traditional supervised machine learning algorithms. We illustrate our workflow on a large data set that contains bacterial species related to urinary tract infections. Overall we obtain accuracies up to 85% in discriminating five different species.}}, author = {{Papagiannopoulou, Christina and Parchen, René and Rubbens, Peter and Waegeman, Willem}}, issn = {{0003-2700}}, journal = {{ANALYTICAL CHEMISTRY}}, keywords = {{Analytical Chemistry,DESORPTION IONIZATION-TIME,URINARY-TRACT-INFECTIONS,BACTERIA,CLASSIFICATION,DIAGNOSIS,MS}}, language = {{eng}}, number = {{11}}, pages = {{7523--7531}}, title = {{Fast pathogen identification using single-cell matrix-assisted laser desorption/ionization-aerosol time-of-flight mass spectrometry data and deep learning methods}}, url = {{http://doi.org/10.1021/acs.analchem.9b05806}}, volume = {{92}}, year = {{2020}}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: