Explainable Machine Learning to Unveil Detection Mechanisms with Au Nanoisland-Based Surface-Enhanced Raman Scattering for SARS-CoV-2 Antigen Detection
Source abstract
Abstract
In this study, we introduce a simplified surface-enhanced Raman scattering (SERS) nanobiosensor for precise detection of a SARS-CoV-2 antigen, leveraging supervised machine learning approaches. The biosensor was made with Au nanoislands conjugated with a 4-aminothiophenol Raman reporter and an anti-SARS-CoV-2 antibody. Through the integration of feature selection and learning algorithms, namely, logistic regression, linear discriminant analysis, and support vector machine, we achieved high accuracies ranging from 96 to 100% in antigen detection. Furthermore, we identified the underlying detection mechanisms by employing the concept of multidimensional calibration space, which is based on decision trees and random forest algorithms. This analysis with explainable machine learning allowed us to gain insights into the reasons why our simplified nanobiosensor exhibits lower sensitivity compared with that of the previous sandwich-type immunosensors for SARS-CoV-2. The results presented here emphasize the potential of supervised machine learning in SERS biosensing, which can be applied to any type of diagnostics.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: SARS-CoV-2 detection and testing · Biosensors and Analytical Detection · SARS-CoV-2 and COVID-19 Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physics and Meteorology, School of Sciences, São Paulo State University (UNESP), Bauru 17033-360, São Paulo, Brazil
Department of Physics, Federal University of Santa Catarina, Florianópolis 88040-900, Santa Catarina, Brazil
São Carlos Institute of Physics, University of São Paulo (USP), São Carlos 13566-590, São Paulo, Brazil
Mato Grosso do Sul State University (UEMS), Dourados 79804-970, Mato Grosso do Sul, Brazil
Federal Institute of São Paulo (IFSP), Araraquara 14804-296, São Paulo, Brazil
Institute of Mathematics and Computer Sciences (ICMC), University of São Paulo (USP), São Carlos 13566-590, São Paulo, Brazil
Department of Physics, School of Sciences and Technology, São Paulo State University (UNESP), Presidente Prudente 19060-900, São Paulo, Brazil
Funding
Minist??rio da Ci??ncia, Tecnologia e Inova????o · Funda????o de Amparo ?? Pesquisa do Estado de S??o Paulo · Instituto Nacional de Eletr??nica Org??nica
References (57)
Show source-provided references
1. 10.1007/s43939-021-00012-010.1007/s43939-021-00012-0 ↗
2. Suckling, J.; Parker, J.; Dance, D.; Al, E. Mammographic Image Analysis Society (MIAS) Database v1.21, [Dataset]; Apollo-University of Cambridge Repository, 2015. https://www.repository.cam.ac.uk/handle/1810/250394.
3. 10.1016/j.apsusc.2020.14646610.1016/j.apsusc.2020.146466 ↗
4. 10.1039/D1TC02134F10.1039/D1TC02134F ↗
5. 10.1021/ac010196110.1021/ac0101961 ↗
6. 10.1016/j.bios.2020.11232610.1016/j.bios.2020.112326 ↗
7. 10.3390/bios1103006610.3390/bios11030066 ↗
8. 10.1002/jrs.626210.1002/jrs.6262 ↗
9. 10.1080/87559129.2021.193400510.1080/87559129.2021.1934005 ↗
10. 10.1021/acs.nanolett.0c0320510.1021/acs.nanolett.0c03205 ↗
11. 10.1016/j.snb.2016.09.18310.1016/j.snb.2016.09.183 ↗
12. 10.1016/j.talanta.2022.12338110.1016/j.talanta.2022.123381 ↗
13. 10.3390/bios1207046610.3390/bios12070466 ↗
14. 10.1016/j.aca.2022.34029010.1016/j.aca.2022.340290 ↗
15. 10.1016/j.bios.2015.07.05010.1016/j.bios.2015.07.050 ↗
16. 10.1016/j.bios.2005.10.02710.1016/j.bios.2005.10.027 ↗
17. 10.1016/j.aca.2022.33996010.1016/j.aca.2022.339960 ↗
18. 10.1021/nn300352b10.1021/nn300352b ↗
19. 10.1002/smll.20220454110.1002/smll.202204541 ↗
20. 10.1016/j.snb.2018.05.00110.1016/j.snb.2018.05.001 ↗
21. 10.1039/D1RA03082E10.1039/D1RA03082E ↗
22. 10.1515/ntrev-2013-000110.1515/ntrev-2013-0001 ↗
23. 10.1246/bcsj.2020035910.1246/bcsj.20200359 ↗
24. 10.1039/C5AN01240F10.1039/C5AN01240F ↗
25. 10.1021/ja405120x10.1021/ja405120x ↗
26. 10.1039/C7CC01577A10.1039/C7CC01577A ↗
27. 10.1366/00037020332255451810.1366/000370203322554518 ↗
28. 10.1002/978111995295410.1002/9781119952954 ↗
29. 10.1039/c0an00822b10.1039/c0an00822b ↗
30. 10.1016/0377-0427(87)90125-710.1016/0377-0427(87)90125-7 ↗
31. 10.1002/978047031680110.1002/9780470316801 ↗
32. 10.2307/253094610.2307/2530946 ↗
33. Tan P.-N. · 2005
34. 10.1007/978-1-4614-7138-710.1007/978-1-4614-7138-7 ↗
35. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
36. 10.1007/s11749-016-0481-710.1007/s11749-016-0481-7 ↗
37. 10.1186/1471-2105-7-9110.1186/1471-2105-7-91 ↗
38. 10.1007/978-3-319-07064-3_110.1007/978-3-319-07064-3_1 ↗
39. Kohavi, R. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In Proceedings of the 14th International Joint Conference on Artificial Intelligence; Morgan Kaufmann Publishers Inc., 1995; Vol. 2, pp 1137–1143.10.5555/1643031.1643047.10.5555/1643031.1643047 ↗
40. 10.5194/soil-5-275-201910.5194/soil-5-275-2019 ↗
41. 10.1016/j.eswa.2021.11522210.1016/j.eswa.2021.115222 ↗
42. Pedregos F. · J. Mach. Learn. Res. · 2011 · 12 · 2825
43. 10.1109/TVCG.2020.303035410.1109/TVCG.2020.3030354 ↗
44. Rai V. N. · JSM Nanotechnol Nanomed · 2016 · 4 · 1039
45. 10.1021/jp911480510.1021/jp9114805 ↗
46. 10.1117/1.359409610.1117/1.3594096 ↗
47. 10.1021/j100099a03810.1021/j100099a038 ↗
48. 10.1021/acsnano.1c0937110.1021/acsnano.1c09371 ↗
49. 10.1007/s00216-011-4853-210.1007/s00216-011-4853-2 ↗
50. 10.1021/acsami.6b1610510.1021/acsami.6b16105 ↗
51. 10.1021/acsami.9b1918010.1021/acsami.9b19180 ↗
52. 10.1039/D1QM00665G10.1039/D1QM00665G ↗
53. 10.1016/j.talanta.2022.12332710.1016/j.talanta.2022.123327 ↗
54. 10.1093/bioinformatics/btn58310.1093/bioinformatics/btn583 ↗
55. 10.1016/j.jtbi.2014.06.03710.1016/j.jtbi.2014.06.037 ↗
56. 10.1162/08997669830001719710.1162/089976698300017197 ↗
57. Domingos, P. Occam’s Two Razors: The Sharp and the Blunt. In KDD’98: Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining; AAAI Press: New York, NY, 1998; pp 37–43.