Contribution of MALDI‐TOF mass spectrometry and machine learning including deep learning techniques for the detection of virulence factors of Clostridioides difficile strains

• Published in: Microbial biotechnology Vol. 17; no. 6; pp. e14478 - n/a
• Main Authors: Godmer, Alexandre, Giai Gianetto, Quentin, Le Neindre, Killian, Latapy, Valentine, Bastide, Mathilda, Ehmig, Muriel, Lalande, Valérie, Veziris, Nicolas, Aubry, Alexandra, Barbut, Frédéric, Eckert, Catherine
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.06.2024; John Wiley and Sons Inc; Wiley
• Subjects: Acids; Algorithms; Artificial intelligence; Bacterial Proteins - genetics; Bacterial Proteins - metabolism; Bacterial Toxins - genetics; Classifiers; Cloning; Clostridioides difficile; Clostridioides difficile - chemistry; Clostridioides difficile - classification; Clostridioides difficile - genetics; Clostridioides difficile - pathogenicity; Clostridium Infections - diagnosis; Clostridium Infections - microbiology; Datasets; Deep Learning; Enterotoxins - analysis; Enterotoxins - genetics; Epidemiology; Humans; Laboratories; Learning algorithms; Machine Learning; Mass spectrometry; Mass spectroscopy; Methods; Neural networks; Optimization; Scientific imaging; Sensitivity and Specificity; Signal processing; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization - methods; Surveillance; Toxin A; Toxins; Virulence; Virulence factors; Virulence Factors - analysis; Virulence Factors - genetics; Wavelet transforms; France; Europe; Germany
• ISSN: 1751-7915; 1751-7915
• DOI: 10.1111/1751-7915.14478

Clostridioides difficile (CD) infections are defined by toxins A (TcdA) and B (TcdB) along with the binary toxin (CDT). The emergence of the ‘hypervirulent’ (Hv) strain PR 027, along with PR 176 and 181, two decades ago, reshaped CD infection epidemiology in Europe. This study assessed MALDI‐TOF mass spectrometry (MALDI‐TOF MS) combined with machine learning (ML) and Deep Learning (DL) to identify toxigenic strains (producing TcdA, TcdB with or without CDT) and Hv strains. In total, 201 CD strains were analysed, comprising 151 toxigenic (24 ToxA+B+CDT+, 22 ToxA+B+CDT+ Hv+ and 105 ToxA+B+CDT−) and 50 non‐toxigenic (ToxA−B−) strains. The DL‐based classifier exhibited a 0.95 negative predictive value for excluding ToxA−B− strains, showcasing accuracy in identifying this strain category. Sensitivity in correctly identifying ToxA+B+CDT− strains ranged from 0.68 to 0.91. Additionally, all classifiers consistently demonstrated high specificity (>0.96) in detecting ToxA+B+CDT+ strains. The classifiers' performances for Hv strain detection were linked to high specificity (≥0.96). This study highlights MALDI‐TOF MS enhanced by ML techniques as a rapid and cost‐effective tool for identifying CD strain virulence factors. Our results brought a proof‐of‐concept concerning the ability of MALDI‐TOF MS coupled with ML techniques to detect virulence factor and potentially improve the outbreak's management. This study assessed the use of MALDI‐TOF Mass Spectrometry combined with Machine Learning including Deep Learning techniques to identify toxigenic and hypervirulent strains of Clostridioides difficile. The method demonstrated high accuracy, particularly in excluding non‐toxigenic strains with a negative predictive value of 0.95 and consistently high specificity (>0.96) for detecting binary producing strains. The findings suggest that MALDI‐TOF MS enhanced by ML techniques is a rapid, cost‐effective tool for detecting virulence factors in CD strains, potentially improving outbreak management.