Detection of A and B Influenza Viruses by Surface-Enhanced Raman Scattering Spectroscopy and Machine Learning.

Area of Science:

• Biophysics
• Spectroscopy
• Computational Biology

Background:

• Influenza viruses A and B pose significant public health challenges.
• Accurate and rapid detection methods are crucial for effective diagnosis and treatment.
• Current detection methods may lack specificity or require complex procedures.

Purpose of the Study:

• To explore the feasibility of using surface-enhanced Raman spectroscopy (SERS) combined with machine learning for influenza virus detection.
• To differentiate between influenza A and B virus types using SERS.
• To determine the sensitivity and accuracy of the proposed method.

Main Methods:

• Utilized surface-enhanced Raman spectroscopy (SERS) to obtain spectral data from influenza viruses.
• Applied machine learning algorithms, specifically the support vector machine (SVM) method, for data analysis and classification.
• Evaluated the performance of the SERS-machine learning approach at various virus concentrations.

Main Results:

• SERS spectra alone did not provide distinct peaks for direct influenza virus classification.
• The support vector machine method successfully differentiated influenza A and B viruses with 93% accuracy at a concentration of 200 μg/mL.
• The minimum detectable virus concentration was approximately 0.05 μg/mL of protein, with an 84% detection accuracy.

Conclusions:

• The integration of SERS and machine learning offers a promising approach for sensitive and specific influenza virus detection.
• This method enables the differentiation of influenza A and B subtypes, which is critical for epidemiological surveillance and clinical management.
• Further research may optimize this technique for point-of-care diagnostics.