Detection of SARS-CoV-2 in patient specimens by surface enhanced Raman spectroscopy and deep learning

Diagnosis of SARS-CoV-2 infection allows for disease intervention, control, and management for COVID-19. The real-time reverse transcriptase-polymerase chain reaction (RT-PCR) is considered the gold standard used to detect the virus. Due to the high testing volumes, the process has a long turnaround time, i.e., 2-3 days. It also requires expensive equipment and involves highly trained staff. Other fast diagnostic methods, such as lateral flow assay based on antibody detection, have limitations such as lower specificity and sensitivity. Thus, there is a critical need for a rapid and low-cost point-of-care (POC) diagnostic method to accurately diagnose SARS-CoV-2 infections in patients. In this study, three rapid, portable, and cost-effective methods to detect SARS-CoV-2 in human nasopharyngeal swab specimens are developed using surface enhanced Raman spectroscopy (SERS) and deep learning: RNA hybridization, ACE-2 capture, and direct detection. Combining the SERS spectra with a deep learning algorithm, all methods can achieve > 99% accuracy to classify the positive and negative specimens and the test-to-answer time is within 30 min. The RNA hybridization method can achieve a limit of detection of 1000 copies/ml, and the ACE-2 method is capable of differentiating between different variants of SARS-CoV-2 viruses. The direct detection method can additionally quantitatively predict the cycle threshold (Ct) value of RT-PCR tests for positive specimens, demonstrating a diagnostic accuracy of 99.04% in blind tests of 104 specimens. These results indicate that SERS combined with deep learning could be a potential rapid POC COVID-19 diagnostic platform.