DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins

To classify raw SERS Raman spectra from biological materials, we propose DeepRaman, a new architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation approach. Unlike standard machine learning approaches such as PCA, LDA, SVM, RF, GBM etc, DeepRaman fu...

Full description

Saved in:
Bibliographic Details
Main Author: Samir Brahim, Belhaouari (author)
Other Authors: Talbi, Abdelhamid (author), Elgamal, Mahmoud (author), Elmagarmid, Khadija Ahmed (author), Ghannoum, Shaimaa (author), Yang, Yanjun (author), Zhao, Yiping (author), Zughaier, Susu M. (author), Bensmail, Halima (author)
Format: article
Published: 2025
Subjects:
Online Access:http://dx.doi.org/10.1016/j.heliyon.2025.e42550
https://www.sciencedirect.com/science/article/pii/S2405844025009302
http://hdl.handle.net/10576/64058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1857415086613725184
author Samir Brahim, Belhaouari
author2 Talbi, Abdelhamid
Elgamal, Mahmoud
Elmagarmid, Khadija Ahmed
Ghannoum, Shaimaa
Yang, Yanjun
Zhao, Yiping
Zughaier, Susu M.
Bensmail, Halima
author2_role author
author
author
author
author
author
author
author
author_facet Samir Brahim, Belhaouari
Talbi, Abdelhamid
Elgamal, Mahmoud
Elmagarmid, Khadija Ahmed
Ghannoum, Shaimaa
Yang, Yanjun
Zhao, Yiping
Zughaier, Susu M.
Bensmail, Halima
author_role author
dc.creator.none.fl_str_mv Samir Brahim, Belhaouari
Talbi, Abdelhamid
Elgamal, Mahmoud
Elmagarmid, Khadija Ahmed
Ghannoum, Shaimaa
Yang, Yanjun
Zhao, Yiping
Zughaier, Susu M.
Bensmail, Halima
dc.date.none.fl_str_mv 2025-04-08T06:59:49Z
2025-02-28
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://dx.doi.org/10.1016/j.heliyon.2025.e42550
24058440
https://www.sciencedirect.com/science/article/pii/S2405844025009302
http://hdl.handle.net/10576/64058
4
11
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Elsevier
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Raman spectroscopy
CNN
Fourier transform
Progressive fourier transform
Scalogram
SVM
k-NN
ImageNet
Dense CNN
dc.title.none.fl_str_mv DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
dc.type.none.fl_str_mv Article
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description To classify raw SERS Raman spectra from biological materials, we propose DeepRaman, a new architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation approach. Unlike standard machine learning approaches such as PCA, LDA, SVM, RF, GBM etc, DeepRaman functions independently, requiring no human interaction, and can be used to much smaller datasets than traditional CNNs. Performance of DeepRaman on 14 endotoxins bacteria and on a public data achieved an extraordinary accuracy of 99 percent. This provides exact endotoxin classification and has tremendous potential for accelerated medical diagnostics and treatment decision-making in cases of pathogenic infections. BackgroundBacterial endotoxin, a lipopolysaccharide exuded by bacteria during their growth and infection process, serves as a valuable biomarker for bacterial identification. It is a vital component of the outer membrane layer in Gram-negative bacteria. By employing silver nanorod-based array substrates, surface-enhanced Raman scattering (SERS) spectra were obtained for two separate datasets: Eleven endotoxins produced by bacteria, each having an 8.75 pg average detection quantity per measurement, and three controls chitin, lipoteichoic acid (LTA), bacterial peptidoglycan (PGN), because their structures differ greatly from those of LPS. ObjectiveThis study utilized various classical machine learning techniques, such as support vector machines, k-nearest neighbors, and random forests, in conjunction with a modified deep learning approach called DeepRaman. These algorithms were employed to distinguish and categorize bacterial endotoxins, following appropriate spectral pre-processing, which involved novel filtering techniques and advanced feature extraction methods. ResultMost traditional machine learning algorithms achieved distinction accuracies of over 99 percent, whereas DeepRaman demonstrated an exceptional accuracy of 100 percent. This method offers precise endotoxin classification and holds significant potential for expedited medical diagnoses and therapeutic decision-making in cases of pathogenic infections. ConclusionWe present the effectiveness of DeepRaman, an innovative architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation method, in classifying raw SERS Raman spectral data from biological specimens with unparalleled accuracy relative to conventional machine learning algorithms. Notably, this Convolutional Neural Network (CNN) operates autonomously, requiring no human intervention, and can be applied with substantially smaller datasets than traditional CNNs. Furthermore, it exhibits remarkable proficiency in managing challenging baseline scenarios that often lead to failures in other techniques, thereby promoting the broader clinical adoption of Raman spectroscopy.
eu_rights_str_mv openAccess
format article
id qu_e3de9b66b161d00921f68fe76f1554e4
identifier_str_mv 24058440
4
11
language_invalid_str_mv en
network_acronym_str qu
network_name_str Qatar University repository
oai_identifier_str oai:qspace.qu.edu.qa:10576/64058
publishDate 2025
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
spelling DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxinsSamir Brahim, BelhaouariTalbi, AbdelhamidElgamal, MahmoudElmagarmid, Khadija AhmedGhannoum, ShaimaaYang, YanjunZhao, YipingZughaier, Susu M.Bensmail, HalimaRaman spectroscopyCNNFourier transformProgressive fourier transformScalogramSVMk-NNImageNetDense CNNTo classify raw SERS Raman spectra from biological materials, we propose DeepRaman, a new architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation approach. Unlike standard machine learning approaches such as PCA, LDA, SVM, RF, GBM etc, DeepRaman functions independently, requiring no human interaction, and can be used to much smaller datasets than traditional CNNs. Performance of DeepRaman on 14 endotoxins bacteria and on a public data achieved an extraordinary accuracy of 99 percent. This provides exact endotoxin classification and has tremendous potential for accelerated medical diagnostics and treatment decision-making in cases of pathogenic infections. BackgroundBacterial endotoxin, a lipopolysaccharide exuded by bacteria during their growth and infection process, serves as a valuable biomarker for bacterial identification. It is a vital component of the outer membrane layer in Gram-negative bacteria. By employing silver nanorod-based array substrates, surface-enhanced Raman scattering (SERS) spectra were obtained for two separate datasets: Eleven endotoxins produced by bacteria, each having an 8.75 pg average detection quantity per measurement, and three controls chitin, lipoteichoic acid (LTA), bacterial peptidoglycan (PGN), because their structures differ greatly from those of LPS. ObjectiveThis study utilized various classical machine learning techniques, such as support vector machines, k-nearest neighbors, and random forests, in conjunction with a modified deep learning approach called DeepRaman. These algorithms were employed to distinguish and categorize bacterial endotoxins, following appropriate spectral pre-processing, which involved novel filtering techniques and advanced feature extraction methods. ResultMost traditional machine learning algorithms achieved distinction accuracies of over 99 percent, whereas DeepRaman demonstrated an exceptional accuracy of 100 percent. This method offers precise endotoxin classification and holds significant potential for expedited medical diagnoses and therapeutic decision-making in cases of pathogenic infections. ConclusionWe present the effectiveness of DeepRaman, an innovative architecture inspired by the Progressive Fourier Transform and integrated with the scalogram transformation method, in classifying raw SERS Raman spectral data from biological specimens with unparalleled accuracy relative to conventional machine learning algorithms. Notably, this Convolutional Neural Network (CNN) operates autonomously, requiring no human intervention, and can be applied with substantially smaller datasets than traditional CNNs. Furthermore, it exhibits remarkable proficiency in managing challenging baseline scenarios that often lead to failures in other techniques, thereby promoting the broader clinical adoption of Raman spectroscopy.This research was funded by the Qatar National Research Fund (QNRF now QRDI) under Grant NPRP12S-0224-190144. Computational resources were provided by the Qatar Research Computing Institute (QCRI).Elsevier2025-04-08T06:59:49Z2025-02-28Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1016/j.heliyon.2025.e4255024058440https://www.sciencedirect.com/science/article/pii/S2405844025009302http://hdl.handle.net/10576/64058411enhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:qspace.qu.edu.qa:10576/640582025-04-08T19:06:14Z
spellingShingle DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
Samir Brahim, Belhaouari
Raman spectroscopy
CNN
Fourier transform
Progressive fourier transform
Scalogram
SVM
k-NN
ImageNet
Dense CNN
status_str publishedVersion
title DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
title_full DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
title_fullStr DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
title_full_unstemmed DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
title_short DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
title_sort DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins
topic Raman spectroscopy
CNN
Fourier transform
Progressive fourier transform
Scalogram
SVM
k-NN
ImageNet
Dense CNN
url http://dx.doi.org/10.1016/j.heliyon.2025.e42550
https://www.sciencedirect.com/science/article/pii/S2405844025009302
http://hdl.handle.net/10576/64058