Related Experiment Video
Updated: Jun 6, 2025
07:08
A Rapid, Multiplex Dual Reporter IgG and IgM SARS-CoV-2 Neutralization Assay for a Multiplexed Bead-Based Flow Analysis System
Published on: April 6, 2021
4.9K
Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2
Thais de Andrade Silva1, Gabriel Fernandes Souza Dos Santos1, Adilson Ribeiro Prado2
1Morphology Department, Federal University of Espirito Santo, Av Marechal Campos, 1468, Vitória 29040-090, ES, Brazil.
Biosensors
|November 26, 2024
Summary
This study presents a novel method for detecting SARS-CoV-2 antibodies using Surface-Enhanced Raman Spectroscopy (SERS) and machine learning. The combined approach achieved high accuracy in identifying the virus, offering a promising diagnostic tool.
Area of Science:
- Biomedical Engineering
- Analytical Chemistry
- Computational Biology
Background:
- Accurate and rapid detection of SARS-CoV-2 antibodies is crucial for disease management and vaccine efficacy assessment.
- Existing diagnostic methods may have limitations in terms of speed, cost, or sensitivity.
- Development of novel biosensing platforms integrated with advanced data analysis is needed.
Purpose of the Study:
- To develop and validate an efficient method for detecting SARS-CoV-2 antibodies in human blood samples.
- To explore the utility of Surface-Enhanced Raman Spectroscopy (SERS) coupled with machine learning for antibody detection.
- To compare the performance of various machine learning algorithms for classifying SARS-CoV-2 positive and negative samples.
Main Methods:
- Utilized gold nanoparticles conjugated with SARS-CoV-2 spike protein for antibody capture.
- Collected Raman spectra from 594 human blood serum samples.
- Employed machine learning algorithms (kNN, SVM, DTs, LR, LightGBM) implemented in Python with the Scikit-Learn library.
- Applied Uniform Manifold Approximation and Projection (UMAP) for feature extraction from Raman spectra.
Main Results:
- The k-Nearest Neighbors (kNN) model demonstrated high performance with a sensitivity of 0.943, specificity of 0.9275, and accuracy of 0.9377.
- Machine learning analysis effectively differentiated Raman spectra between SARS-CoV-2 positive and negative samples.
- The study successfully extracted distinguishing characteristics from Raman spectra using UMAP.
Conclusions:
- The integration of SERS with machine learning provides an efficient and accurate diagnostic approach for SARS-CoV-2 antibodies.
- The kNN model showed superior performance among the evaluated algorithms for this specific application.
- This study offers valuable insights into the advantages and limitations of different machine learning models for biosensing data analysis, guiding future research.
