Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG

This work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated with spike protein were used in human blood samples to identify anti-SARS-CoV-2 antibodies. The compreh...

Full description

Saved in:
Bibliographic Details
Main Authors: Thais de Andrade Silva, Gabriel Fernandes Souza dos Santos, Adilson Ribeiro Prado, Daniel Cruz Cavalieri, Arnaldo Gomes Leal Junior, Flávio Garcia Pereira, Camilo A. R. Díaz, Marco Cesar Cunegundes Guimarães, Servio Túlio Alves Cassini, Jairo Pinto de Oliveira
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Biosensors
Subjects:
Online Access:https://www.mdpi.com/2079-6374/14/11/523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154117197594624
author Thais de Andrade Silva
Gabriel Fernandes Souza dos Santos
Adilson Ribeiro Prado
Daniel Cruz Cavalieri
Arnaldo Gomes Leal Junior
Flávio Garcia Pereira
Camilo A. R. Díaz
Marco Cesar Cunegundes Guimarães
Servio Túlio Alves Cassini
Jairo Pinto de Oliveira
author_facet Thais de Andrade Silva
Gabriel Fernandes Souza dos Santos
Adilson Ribeiro Prado
Daniel Cruz Cavalieri
Arnaldo Gomes Leal Junior
Flávio Garcia Pereira
Camilo A. R. Díaz
Marco Cesar Cunegundes Guimarães
Servio Túlio Alves Cassini
Jairo Pinto de Oliveira
author_sort Thais de Andrade Silva
collection DOAJ
description This work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated with spike protein were used in human blood samples to identify anti-SARS-CoV-2 antibodies. The comprehensive database utilized Raman spectra from all 594 blood serum samples. Machine learning investigations were carried out using the Scikit-Learn library and were implemented in Python, and the characteristics of Raman spectra of positive and negative SARS-CoV-2 samples were extracted using the Uniform Manifold Approximation and Projection (UMAP) technique. The machine learning models used were k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Decision Trees (DTs), logistic regression (LR), and Light Gradient Boosting Machine (LightGBM). The kNN model led to a sensitivity of 0.943, specificity of 0.9275, and accuracy of 0.9377. This study showed that combining Raman spectroscopy and a machine algorithm can be an effective diagnostic method. Furthermore, we highlighted the advantages and disadvantages of each algorithm, providing valuable information for future research.
format Article
id doaj-art-ab805b3e37714db09e30c413f6130c67
institution Kabale University
issn 2079-6374
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Biosensors
spelling doaj-art-ab805b3e37714db09e30c413f6130c672024-11-26T17:54:32ZengMDPI AGBiosensors2079-63742024-10-01141152310.3390/bios14110523Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgGThais de Andrade Silva0Gabriel Fernandes Souza dos Santos1Adilson Ribeiro Prado2Daniel Cruz Cavalieri3Arnaldo Gomes Leal Junior4Flávio Garcia Pereira5Camilo A. R. Díaz6Marco Cesar Cunegundes Guimarães7Servio Túlio Alves Cassini8Jairo Pinto de Oliveira9Morphology Department, Federal University of Espirito Santo, Av Marechal Campos, 1468, Vitória 29040-090, ES, BrazilMorphology Department, Federal University of Espirito Santo, Av Marechal Campos, 1468, Vitória 29040-090, ES, BrazilFederal Institute of Espírito Santo, Campus Serra, Serra 29173-087, ES, BrazilFederal Institute of Espírito Santo, Campus Serra, Serra 29173-087, ES, BrazilTelecommunications Laboratory, Electrical Engineering Department, Federal University of Espírito Santo (UFES), Av Fernando Ferrari 514, Vitória 29075-910, ES, BrazilFederal Institute of Espírito Santo, Campus Serra, Serra 29173-087, ES, BrazilTelecommunications Laboratory, Electrical Engineering Department, Federal University of Espírito Santo (UFES), Av Fernando Ferrari 514, Vitória 29075-910, ES, BrazilMorphology Department, Federal University of Espirito Santo, Av Marechal Campos, 1468, Vitória 29040-090, ES, BrazilCenter of Research, Innovation and Development of Espirito Santo, Ladeira Eliezer Batista, Cariacica 29140-130, ES, BrazilMorphology Department, Federal University of Espirito Santo, Av Marechal Campos, 1468, Vitória 29040-090, ES, BrazilThis work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated with spike protein were used in human blood samples to identify anti-SARS-CoV-2 antibodies. The comprehensive database utilized Raman spectra from all 594 blood serum samples. Machine learning investigations were carried out using the Scikit-Learn library and were implemented in Python, and the characteristics of Raman spectra of positive and negative SARS-CoV-2 samples were extracted using the Uniform Manifold Approximation and Projection (UMAP) technique. The machine learning models used were k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Decision Trees (DTs), logistic regression (LR), and Light Gradient Boosting Machine (LightGBM). The kNN model led to a sensitivity of 0.943, specificity of 0.9275, and accuracy of 0.9377. This study showed that combining Raman spectroscopy and a machine algorithm can be an effective diagnostic method. Furthermore, we highlighted the advantages and disadvantages of each algorithm, providing valuable information for future research.https://www.mdpi.com/2079-6374/14/11/523gold nanoparticlesmultivariate analysisSERSmachine learning
spellingShingle Thais de Andrade Silva
Gabriel Fernandes Souza dos Santos
Adilson Ribeiro Prado
Daniel Cruz Cavalieri
Arnaldo Gomes Leal Junior
Flávio Garcia Pereira
Camilo A. R. Díaz
Marco Cesar Cunegundes Guimarães
Servio Túlio Alves Cassini
Jairo Pinto de Oliveira
Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
Biosensors
gold nanoparticles
multivariate analysis
SERS
machine learning
title Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
title_full Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
title_fullStr Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
title_full_unstemmed Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
title_short Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG
title_sort surface enhanced raman scattering combined with machine learning for rapid and sensitive detection of anti sars cov 2 igg
topic gold nanoparticles
multivariate analysis
SERS
machine learning
url https://www.mdpi.com/2079-6374/14/11/523
work_keys_str_mv AT thaisdeandradesilva surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT gabrielfernandessouzadossantos surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT adilsonribeiroprado surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT danielcruzcavalieri surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT arnaldogomeslealjunior surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT flaviogarciapereira surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT camiloardiaz surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT marcocesarcunegundesguimaraes surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT serviotulioalvescassini surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg
AT jairopintodeoliveira surfaceenhancedramanscatteringcombinedwithmachinelearningforrapidandsensitivedetectionofantisarscov2igg