Rapid classification of SARS-CoV-2 variant strains using machine learning-based label-free SERS strategy

Jingwang Qin; Xiangdong Tian; Siying Liu; Zhengxia Yang; Dawei Shi; Sihong Xu; Yun Zhang

doi:10.1016/j.talanta.2023.125080

Rapid classification of SARS-CoV-2 variant strains using machine learning-based label-free SERS strategy

Talanta. 2024 Jan 15:267:125080. doi: 10.1016/j.talanta.2023.125080. Epub 2023 Aug 17.

Authors

Jingwang Qin¹, Xiangdong Tian¹, Siying Liu², Zhengxia Yang², Dawei Shi³, Sihong Xu⁴, Yun Zhang⁵

Affiliations

¹ State Key Laboratory of Structural Chemistry, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou, Fujian, 350002, PR China; Department of Translational Medicine, Xiamen Institute of Rare Earth Materials, Haixi Institute, Chinese Academy of Sciences, Xiamen, 361021, PR China.
² State Key Laboratory of Structural Chemistry, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou, Fujian, 350002, PR China; Department of Translational Medicine, Xiamen Institute of Rare Earth Materials, Haixi Institute, Chinese Academy of Sciences, Xiamen, 361021, PR China; University of the Chinese Academy of Sciences, Beijing, 100049, China.
³ National Institutes for Food and Drug Control, Beijing, 100050, China. Electronic address: shidw@nifdc.org.cn.
⁴ National Institutes for Food and Drug Control, Beijing, 100050, China. Electronic address: xushong@nifdc.org.cn.
⁵ State Key Laboratory of Structural Chemistry, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou, Fujian, 350002, PR China; Department of Translational Medicine, Xiamen Institute of Rare Earth Materials, Haixi Institute, Chinese Academy of Sciences, Xiamen, 361021, PR China; University of the Chinese Academy of Sciences, Beijing, 100049, China. Electronic address: zhangy@fjirsm.ac.cn.

PMID: 37678002
DOI: 10.1016/j.talanta.2023.125080

Abstract

The spread of COVID-19 over the past three years is largely due to the continuous mutation of the virus, which has significantly impeded global efforts to prevent and control this epidemic. Specifically, mutations in the amino acid sequence of the surface spike (S) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have directly impacted its biological functions, leading to enhanced transmission and triggering an immune escape effect. Therefore, prompt identification of these mutations is crucial for formulating targeted treatment plans and implementing precise prevention and control measures. In this study, the label-free surface-enhanced Raman scattering (SERS) technology combined with machine learning (ML) algorithms provide a potential solution for accurate identification of SARS-CoV-2 variants. We establish a SERS spectral database of SARS-CoV-2 variants and demonstrate that a diagnostic classifier using a logistic regression (LR) algorithm can provide accurate results within 10 min. Our classifier achieves 100% accuracy for Beta (B.1.351/501Y.V2), Delta (B.1.617), Wuhan (COVID-19) and Omicron (BA.1) variants. In addition, our method achieves 100% accuracy in blind tests of positive and negative human nasal swabs based on the LR model. This method enables detection and classification of variants in complex biological samples. Therefore, ML-based SERS technology is expected to accurately discriminate various SARS-CoV-2 variants and may be used for rapid diagnosis and therapeutic decision-making.

Keywords: Machine learning algorithm; SARS-CoV-2 variants; Statistical analysis; Surface-enhanced raman spectroscopy.

MeSH terms

Algorithms
COVID-19* / diagnosis
Humans
Machine Learning
SARS-CoV-2* / genetics

Supplementary concepts

SARS-CoV-2 variants