Exploring Streptococcus pneumoniae capsular typing through MALDI-TOF mass spectrometry and machine-learning algorithms in Argentina: Identifying prevalent NON PCV13 serotypes alongside PCV13 serotypes

• DOI: 10.1016/j.jmsacl.2023.11.003
• Publication Date: 2023-11-25T06:11:39Z
• Authors: Jonathan Zintgraff; Florencia Rocca; Nahuel Sánchez El...; Lucía Irazu; Maria Alicia Mosc...; Claudia Lara; Mauricio Santos
• Keywords: Pneumococcal Conjugate Vaccine

Laboratory surveillance of Streptococcus pneumoniae serotypes plays a crucial role in effectively implementing vaccines to prevent invasive pneumococcal diseases. The conventional method serotyping, known as the Quellung reaction, is both time-consuming and expensive. However, emergence MALDI-TOF MS technology has revolutionized microbiology laboratories by enabling rapid cost-effective serotyping based on protein profiles.In this study, we aimed investigate viability utilizing an adjunctive screening for capsular typing pneumoniae. Our approach involved developing classification models discern between strains originating from PCV13 (13-valent conjugate vaccine) NON isolates.Firstly, established comprehensive spectral database comprising isolates present vaccine, along with top 10 most prevalent local epidemiological data. This served foundation unsupervised spectra, which enabled us identify inherent patterns relationships within analysis dataset 215 new collected nationwide Argentina. isolates.Although our findings revealed suboptimal performance serotype classification, they provide valuable insights into potential machine learning algorithms context. sensitivity ranged 0.41 0.46, indicating their ability detect certain serotypes. observed specificity consistently remained at 0.60, suggesting moderate level accuracy identifying non-vaccine These results highlight need further refinement optimization enhance discriminative power predictive identification.By addressing limitations identified such exploring alternative feature selection techniques or optimizing algorithm parameters, can unlock full robust reliable S. work not only provides evaluation multiple but also emphasizes importance considering strengths limitations.Overall, study contributes growing body research identification purposes.