COVID-19 salivary Raman fingerprint: innovative approach for the detection of current and past SARS-CoV-2 infections

C Carlomagno,M Bedoni,S Monteleone,A Lax,E Messina,J Navarro,A Caronni,F Marenco,D Bertazioli,A Gualerzi,P I Banfi,C Arienti,S Picciolini,L Bianchi

doi:10.1038/s41598-021-84565-3

C Carlomagno, M Bedoni + Show 12 more

Open Access

https://doi.org/10.1038/s41598-021-84565-3

Copy DOI

Abstract

The pandemic of COVID-19 is continuously spreading, becoming a worldwide emergency. Early and fast identification of subjects with a current or past infection must be achieved to slow down the epidemiological widening. Here we report a Raman-based approach for the analysis of saliva, able to significantly discriminate the signal of patients with a current infection by COVID-19 from healthy subjects and/or subjects with a past infection. Our results demonstrated the differences in saliva biochemical composition of the three experimental groups, with modifications grouped in specific attributable spectral regions. The Raman-based classification model was able to discriminate the signal collected from COVID-19 patients with accuracy, precision, sensitivity and specificity of more than 95%. In order to translate this discrimination from the signal-level to the patient-level, we developed a Deep Learning model obtaining accuracy in the range 89–92%. These findings have implications for the creation of a potential Raman-based diagnostic tool, using saliva as minimal invasive and highly informative biofluid, demonstrating the efficacy of the classification model.

Highlights

The pandemic of COVID-19 is continuously spreading, becoming a worldwide emergency
The presented spectra are mainly dominated by the peaks attributed to C–N stretching and C H3 rocking in protein backbone (897 and 1155 cm−1) and by the signal at 1453 cm−1 assigned to the C–H stretching of glycoproteins, mostly generated from mucines 26,27
The correlations with the data extracted from the Raman database through Multivariate Analysis (MVA) are of crucial importance for two reasons: the first one is an indication of the reliability of the proposed methodology, which explains the intrinsic relationship between the Raman analysis and the complex biochemical composition of saliva under pathological conditions

Summary

Introduction

The pandemic of COVID-19 is continuously spreading, becoming a worldwide emergency. Early and fast identification of subjects with a current or past infection must be achieved to slow down the epidemiological widening. In order to translate this discrimination from the signal-level to the patient-level, we developed a Deep Learning model obtaining accuracy in the range 89–92% These findings have implications for the creation of a potential Raman-based diagnostic tool, using saliva as minimal invasive and highly informative biofluid, demonstrating the efficacy of the classification model. The immunological method circumvents the extraction of virus nucleic acid and shortens the detection time; it is not applicable for the early diagnosis of COVID19 due to the low antibody concentration at the beginning In this framework, vibrational spectroscopies like Raman spectroscopy (RS) are promising alternatives in molecular diagnostics. Our data provide evidence that the saliva of patients with current infection by SARS-CoV-2 presents a biochemical signature that allows their fast detection and discrimination from people with a past SARS-CoV-2 infection and from healthy subjects, with accuracy, precision, specificity and sensitivity of more than 90%. The correlation with the extracted data confirmed the reliability of the method, demonstrating statistical correlation with the clinical scales used for the COVID-19 severity classification and with the time between the first positive SARS-CoV-2 test and the last negative

Methods

Results

Conclusion