Scholarlink

Background <p>Rapid serotype identification of circulating <i>Streptococcus pneumoniae</i> is essential for both effective epidemiological surveillance and clinical management. The gold standard serotyping method (Quellung reaction) is time-consuming, labor-intensive and expensive. Fourier transform infrared (FT-IR) spectroscopy using the IR-Biotyper<sup>®</sup> (Bruker Daltonics GmbH, Bremen, Germany) system has recently been proposed as a rapid and low-cost technique for serotype identification, based on spectral analysis of capsular polysaccharide components. The integration of machine learning algorithms within the IR-Biotyper<sup>®</sup> enables automated analysis and classification of FT-IR spectra, allowing rapid prediction of pneumococcal serotypes. The present study evaluated the application of machine learning algorithms for serotype identification in clinical <i>S. pneumoniae</i> isolates using the IR-Biotyper<sup>®</sup> system.</p> Results <p>A database with 128 isolates, representing 30 different serotypes, was used to develop four classifiers. A global classifier was designed to predict twelve serotypes (3, 4, 6A/6C, 7C/7F, 12F, 15A/15B/15C, 19A/19F, 22F, 23A/23B/23F, 24B/24F, 35B and 38) achieving 99% accuracy. Additionally, three sequential sub-classifiers were developed to differentiate; 6A from 6C, 15A from 15B and 15C, and 23A from 23B and 23F, with validation dataset accuracies of 100%, 89% and 100% respectively. The evaluation of unknown serotypes showed 92% accuracy.</p> Conclusions <p>FT-IR spectroscopy showed high concordance with Quellung reaction, supporting its use as a rapid and cost-effective method for serotype identification of <i>S. pneumoniae</i>. Sequential sub-classification represents a practical strategy that could be used to classify additional serotypes of epidemiological relevance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FT-IR–based strategy for Streptococcus pneumoniae serotyping using machine-learning classifiers

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Javiera Jiménez-Rodríguez,
  • Patricia García,
  • Marcela Potin,
  • Tamara González-Villarroel,
  • María Cecilia Zumarán,
  • Lorena Porte,
  • Carmen Varela-Alvarado,
  • Aniela Wozniak

摘要

Background

Rapid serotype identification of circulating Streptococcus pneumoniae is essential for both effective epidemiological surveillance and clinical management. The gold standard serotyping method (Quellung reaction) is time-consuming, labor-intensive and expensive. Fourier transform infrared (FT-IR) spectroscopy using the IR-Biotyper® (Bruker Daltonics GmbH, Bremen, Germany) system has recently been proposed as a rapid and low-cost technique for serotype identification, based on spectral analysis of capsular polysaccharide components. The integration of machine learning algorithms within the IR-Biotyper® enables automated analysis and classification of FT-IR spectra, allowing rapid prediction of pneumococcal serotypes. The present study evaluated the application of machine learning algorithms for serotype identification in clinical S. pneumoniae isolates using the IR-Biotyper® system.

Results

A database with 128 isolates, representing 30 different serotypes, was used to develop four classifiers. A global classifier was designed to predict twelve serotypes (3, 4, 6A/6C, 7C/7F, 12F, 15A/15B/15C, 19A/19F, 22F, 23A/23B/23F, 24B/24F, 35B and 38) achieving 99% accuracy. Additionally, three sequential sub-classifiers were developed to differentiate; 6A from 6C, 15A from 15B and 15C, and 23A from 23B and 23F, with validation dataset accuracies of 100%, 89% and 100% respectively. The evaluation of unknown serotypes showed 92% accuracy.

Conclusions

FT-IR spectroscopy showed high concordance with Quellung reaction, supporting its use as a rapid and cost-effective method for serotype identification of S. pneumoniae. Sequential sub-classification represents a practical strategy that could be used to classify additional serotypes of epidemiological relevance.