Search for: All records

Early virus identification is a key component of both patient treatment and epidemiological monitoring. In the case of influenza A virus infections, where the detection of subtypes associated with bird flu in humans could lead to a pandemic, rapid subtype-level identification is important. Surface-enhanced Raman spectroscopy coupled with machine learning can be used to rapidly detect and identify viruses in a label-free manner. As there is a range of available excitation wavelengths for performing Raman spectroscopy, we must choose the best one to permit discrimination between highly similar subtypes of a virus. We show that the spectra produced by influenza A subtypes H1N1 and H3N2 exhibit a higher degree of dissimilarity when using 785 nm excitation wavelength in comparison with 532 nm excitation wavelength. Furthermore, the cross-validated area under the curve (AUC) for identification was higher for the 785 nm excitation, reaching 0.95 as compared to 0.86 for 532 nm. Ultimately, this study suggests that exciting with a 785 nm wavelength is better able to differentiate two closely related influenza viruses and likely can extend to other closely related pathogens. 

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device, coupled with label-free Raman spectroscopy, holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning (ML) approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such an ML approach for analyzing Raman spectra of human and avian viruses. A convolutional neural network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A versus type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and nonenveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus [IBV]) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups—for example, amide, amino acid, and carboxylic acid—we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids, and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses.