Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes
Introduction: Laboratory surveillance of Streptococcus pneumoniae serotypes plays a crucial role in effectively implementing vaccines to prevent invasive pneumococcal diseases. The conventional method of serotyping, known as the Quellung reaction, is both time-consuming and expensive. However, the e...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-11-01
|
Series: | Journal of Mass Spectrometry and Advances in the Clinical Lab |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2667145X23000366 |
_version_ | 1797394781195730944 |
---|---|
author | Jonathan Zintgraff Florencia Rocca Nahuel Sánchez Eluchans Lucía Irazu Maria Alicia Moscoloni Claudia Lara Mauricio Santos |
author_facet | Jonathan Zintgraff Florencia Rocca Nahuel Sánchez Eluchans Lucía Irazu Maria Alicia Moscoloni Claudia Lara Mauricio Santos |
author_sort | Jonathan Zintgraff |
collection | DOAJ |
description | Introduction: Laboratory surveillance of Streptococcus pneumoniae serotypes plays a crucial role in effectively implementing vaccines to prevent invasive pneumococcal diseases. The conventional method of serotyping, known as the Quellung reaction, is both time-consuming and expensive. However, the emergence of MALDI-TOF MS technology has revolutionized microbiology laboratories by enabling rapid and cost-effective serotyping based on protein profiles. Objectives: In this study, we aimed to investigate the viability of utilizing MALDI-TOF MS technology as an adjunctive and screening method for capsular typing of Streptococcus pneumoniae. Our approach involved developing classification models based on MALDI-TOF MS to discern between Streptococcus pneumoniae strains originating from PCV13 (13-valent pneumococcal conjugate vaccine) and NON PCV13 isolates. Methods: Firstly, we established a comprehensive spectral database comprising isolates of serotypes present in the PCV13 vaccine, along with the top 10 most prevalent NON PCV13 serotypes based on local epidemiological data. This database served as a foundation for developing unsupervised models utilizing MALDI-TOF MS spectra, which enabled us to identify inherent patterns and relationships within the data. Our analysis involved a dataset comprising 215 new isolates collected from nationwide surveillance in Argentina. Our approach involved developing classification models based on MALDI-TOF MS to discern between Streptococcus pneumoniae strains originating from PCV13 (13-valent pneumococcal conjugate vaccine) and NON PCV13 isolates. Results: Although our findings revealed suboptimal performance in serotype classification, they provide valuable insights into the potential of machine learning algorithms in this context. The sensitivity of the models ranged from 0.41 to 0.46, indicating their ability to detect certain serotypes. The observed specificity consistently remained at 0.60, suggesting a moderate level of accuracy in identifying non-vaccine serotypes. These results highlight the need for further refinement and optimization of the algorithms to enhance their discriminative power and predictive accuracy in serotype identification.By addressing the limitations identified in this study, such as exploring alternative feature selection techniques or optimizing algorithm parameters, we can unlock the full potential of machine learning in robust and reliable serotype classification of S. pneumoniae. Our work not only provides a comprehensive evaluation of multiple machine learning models but also emphasizes the importance of considering their strengths and limitations. Conclusion: Overall, our study contributes to the growing body of research on utilizing MALDI-TOF MS and machine learning algorithms for serotype identification purposes. |
first_indexed | 2024-03-09T00:24:40Z |
format | Article |
id | doaj.art-d2f4cab665864b82af85d0708f94a41e |
institution | Directory Open Access Journal |
issn | 2667-145X |
language | English |
last_indexed | 2024-03-09T00:24:40Z |
publishDate | 2023-11-01 |
publisher | Elsevier |
record_format | Article |
series | Journal of Mass Spectrometry and Advances in the Clinical Lab |
spelling | doaj.art-d2f4cab665864b82af85d0708f94a41e2023-12-12T04:36:50ZengElsevierJournal of Mass Spectrometry and Advances in the Clinical Lab2667-145X2023-11-01306173Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypesJonathan Zintgraff0Florencia Rocca1Nahuel Sánchez Eluchans2Lucía Irazu3Maria Alicia Moscoloni4Claudia Lara5Mauricio Santos6Servicio Bacteriología Clínica, Instituto Nacional de Enfermedades Infecciosas (INEI)- Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, Argentina; Red Nacional de Espectrometría de Masas aplicada a la Microbiología Clínica (ReNaEM Argentina), Argentina; Corresponding author.Instituto Nacional de Enfermedades Infecciosas (INEI) – Administración Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, Argentina; Red Nacional de Espectrometría de Masas aplicada a la Microbiología Clínica (ReNaEM Argentina), ArgentinaServicio Bacteriología Clínica, Instituto Nacional de Enfermedades Infecciosas (INEI)- Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, ArgentinaInstituto Nacional de Enfermedades Infecciosas (INEI) – Administración Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, ArgentinaServicio Bacteriología Clínica, Instituto Nacional de Enfermedades Infecciosas (INEI)- Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, ArgentinaServicio Bacteriología Clínica, Instituto Nacional de Enfermedades Infecciosas (INEI)- Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, ArgentinaServicio Bacteriología Clínica, Instituto Nacional de Enfermedades Infecciosas (INEI)- Nacional de Laboratorios e Institutos de Salud (ANLIS) “Dr. Carlos G. Malbrán”, Buenos Aires, ArgentinaIntroduction: Laboratory surveillance of Streptococcus pneumoniae serotypes plays a crucial role in effectively implementing vaccines to prevent invasive pneumococcal diseases. The conventional method of serotyping, known as the Quellung reaction, is both time-consuming and expensive. However, the emergence of MALDI-TOF MS technology has revolutionized microbiology laboratories by enabling rapid and cost-effective serotyping based on protein profiles. Objectives: In this study, we aimed to investigate the viability of utilizing MALDI-TOF MS technology as an adjunctive and screening method for capsular typing of Streptococcus pneumoniae. Our approach involved developing classification models based on MALDI-TOF MS to discern between Streptococcus pneumoniae strains originating from PCV13 (13-valent pneumococcal conjugate vaccine) and NON PCV13 isolates. Methods: Firstly, we established a comprehensive spectral database comprising isolates of serotypes present in the PCV13 vaccine, along with the top 10 most prevalent NON PCV13 serotypes based on local epidemiological data. This database served as a foundation for developing unsupervised models utilizing MALDI-TOF MS spectra, which enabled us to identify inherent patterns and relationships within the data. Our analysis involved a dataset comprising 215 new isolates collected from nationwide surveillance in Argentina. Our approach involved developing classification models based on MALDI-TOF MS to discern between Streptococcus pneumoniae strains originating from PCV13 (13-valent pneumococcal conjugate vaccine) and NON PCV13 isolates. Results: Although our findings revealed suboptimal performance in serotype classification, they provide valuable insights into the potential of machine learning algorithms in this context. The sensitivity of the models ranged from 0.41 to 0.46, indicating their ability to detect certain serotypes. The observed specificity consistently remained at 0.60, suggesting a moderate level of accuracy in identifying non-vaccine serotypes. These results highlight the need for further refinement and optimization of the algorithms to enhance their discriminative power and predictive accuracy in serotype identification.By addressing the limitations identified in this study, such as exploring alternative feature selection techniques or optimizing algorithm parameters, we can unlock the full potential of machine learning in robust and reliable serotype classification of S. pneumoniae. Our work not only provides a comprehensive evaluation of multiple machine learning models but also emphasizes the importance of considering their strengths and limitations. Conclusion: Overall, our study contributes to the growing body of research on utilizing MALDI-TOF MS and machine learning algorithms for serotype identification purposes.http://www.sciencedirect.com/science/article/pii/S2667145X23000366Streptococcus pneumoniaMALDI TOFMass spectrometryConjugates vaccinesCapsular typingMachine learning |
spellingShingle | Jonathan Zintgraff Florencia Rocca Nahuel Sánchez Eluchans Lucía Irazu Maria Alicia Moscoloni Claudia Lara Mauricio Santos Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes Journal of Mass Spectrometry and Advances in the Clinical Lab Streptococcus pneumonia MALDI TOF Mass spectrometry Conjugates vaccines Capsular typing Machine learning |
title | Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes |
title_full | Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes |
title_fullStr | Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes |
title_full_unstemmed | Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes |
title_short | Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes |
title_sort | exploring streptococcus pneumoniae capsular typing through maldi tof mass spectrometry and machine learning algorithms in argentina identifying prevalent non pcv13 serotypes alongside pcv13 serotypes |
topic | Streptococcus pneumonia MALDI TOF Mass spectrometry Conjugates vaccines Capsular typing Machine learning |
url | http://www.sciencedirect.com/science/article/pii/S2667145X23000366 |
work_keys_str_mv | AT jonathanzintgraff exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT florenciarocca exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT nahuelsanchezeluchans exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT luciairazu exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT mariaaliciamoscoloni exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT claudialara exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes AT mauriciosantos exploringstreptococcuspneumoniaecapsulartypingthroughmalditofmassspectrometryandmachinelearningalgorithmsinargentinaidentifyingprevalentnonpcv13serotypesalongsidepcv13serotypes |