Related Experiment Video
Updated: Jul 2, 2026
08:13
A Filter-based Surface Enhanced Raman Spectroscopic Assay for Rapid Detection of Chemical Contaminants
Published on: February 19, 2016
9.3K
Identification of Fusarium sambucinum species complex by surface-enhanced Raman spectroscopy and XGBoost algorithm
Elem T S Caramês1, Venancio F de Moraes-Neto2, Bruno G Bertozzi2
1Department of Microbiology, Institute of Biomedical Sciences, University of São Paulo, 05508-900 São Paulo, Brazil.
Food Chemistry
|March 21, 2025
Summary
Surface-enhanced Raman spectroscopy (SERS) coupled with XGBoost machine learning accurately identifies Fusarium fungi species. This rapid method offers a promising alternative to traditional, time-consuming fungal identification techniques.
Area of Science:
- Mycology
- Spectroscopy
- Biotechnology
Background:
- Accurate identification of Fusarium fungi is vital due to their impact on food safety and potential toxicity.
- Conventional fungal identification methods are often slow and require significant resources.
- Developing rapid and reliable diagnostic tools for fungal pathogens is a key research area.
Purpose of the Study:
- To evaluate the efficacy of surface-enhanced Raman spectroscopy (SERS) for identifying species within the Fusarium sambucinum complex.
- To develop and validate a machine learning model for classifying fungal species based on SERS data.
- To explore the chemical basis for SERS-based fungal discrimination.
Main Methods:
- Acquisition of SERS spectra from 60 Fusarium fungal samples isolated from barley.
- Utilization of gold nanoparticles for enhanced Raman signal detection.
- Application of the eXtreme Gradient Boosting (XGBoost) algorithm for spectral data classification.
Main Results:
- The SERS-XGBoost method achieved perfect classification performance: 100% precision, recall, accuracy, and F1-score.
- Key spectral features linked to fungal chemical composition (chitin, metabolites, proteins) were identified.
- The model demonstrated robust discrimination among the four Fusarium species studied.
Conclusions:
- SERS combined with XGBoost provides a highly accurate and rapid method for Fusarium species identification.
- This approach offers a significant advancement over traditional, labor-intensive fungal identification techniques.
- The SERS-XGBoost methodology shows potential for broad application in microbial identification and diagnostics.
