MYCOLab Ai Logo - gold and army green

Integrating Machine Learning and Molecular Methods for Trichophyton indotineae Identification and Resistance Profiling Using MALDI-TOF Spectra

Summary

A new type of fungus called Trichophyton indotineae is causing stubborn skin infections that don’t respond well to standard antifungal treatments. Researchers used advanced laboratory techniques combined with computer analysis to better identify this fungus from MALDI-TOF spectra, which is a quick fingerprinting method for microorganisms. The study showed that machine learning could accurately distinguish this problematic fungus from similar species and found specific markers that could help clinics detect it faster, potentially improving patient treatment outcomes.

Background

Trichophyton indotineae is an emerging dermatophyte species causing recalcitrant and terbinafine-resistant dermatophytosis with significant diagnostic and treatment challenges. Conventional MALDI-TOF mass spectrometry has shown limited reliability in distinguishing T. indotineae from closely related species within the T. mentagrophytes complex. The global dissemination of this pathogen, first identified in South Asia, raises urgent concerns for improved diagnostic accuracy and therapeutic strategies.

Objective

This study aimed to improve identification and resistance profiling of T. indotineae by integrating molecular methods with machine learning-assisted analysis of MALDI-TOF mass spectra. The research evaluated whether multivariate analysis and supervised machine learning algorithms could enhance diagnostic resolution compared to conventional MALDI-TOF identification.

Results

Terbinafine resistance was detected in 23 isolates, correlating with ERG1 mutations including F397L, L393S, F415C, and A448T. While conventional MALDI-TOF failed to reliably distinguish species, PLS-DA and SVM achieved 100% balanced accuracy in species classification. Biomarker analysis identified discriminatory spectral peaks at 3417.29 m/z and 3423.53 m/z for T. mentagrophytes and T. indotineae, respectively.

Conclusion

Combining MALDI-TOF MS with multivariate analysis and machine learning significantly improves diagnostic resolution for T. indotineae identification. This integrated approach offers a practical, cost-effective alternative to sequencing in resource-limited settings and could enhance routine detection of terbinafine-resistant T. indotineae for more targeted antifungal therapy.
  • Published in:Pathogens,
  • Study Type:Clinical Research Study,
  • Source: 10.3390/pathogens14100986 / 41156597
Scroll to Top