Machine learning-driven SERS fingerprinting of disintegrated viral components for rapid detection of SARS-CoV-2 in environmental dust

Abstract

Surveillance of airborne viruses in crowded indoor spaces is crucial for managing outbreaks, as highlighted by the SARS-CoV-2 pandemic. However, the rapid and on-site detection of fast-mutating viruses, such as SARS-CoV-2, in complex environmental backgrounds remains challenging. Our study introduces a machine learning (ML)-driven surface-enhanced Raman spectroscopy (SERS) approach for detecting viruses within environmental dust matrices. By decomposing intact virions into individual structural components via a Raman-background-free lysis protocol and concentrating them into nanogap SERS hotspots, we significantly enhance the SERS signal intensity and fingerprint information density from viral structural components. Utilizing Principal Component Analysis (PCA), we establish a robust connection between the SERS data of these structural components and their biological sequences, laying a solid foundation for virus detection through SERS. Furthermore, we demonstrate reliable quantitative detection of SARS-CoV-2 using identified SARS-CoV-2 peaks at concentrations down to 102 pfu/ml through Gaussian Process Regression (GPR) and a digital SERS methodology. Finally, applying a Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA) algorithm, we identify SARS-CoV-2, influenza A virus, and Zika virus within an environmental dust background with over 86% accuracy. Therefore, our ML-driven SERS approach holds promise for rapid environmental virus monitoring to manage future outbreaks.