Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

Yang, Yanjun; Xu, Beibei; Haverstick, James; Ibtehaz, Nabil; Muszyński, Artur; Chen, Xianyan; Chowdhury, Muhammad E. H.; Zughaier, Susu M.; Zhao, Yiping

doi:10.1039/d2nr01277d

Cited by 27 publications

(28 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For ML and DL models, all the original spectra were preprocessed using a procedure described in Section S4 . SVM, random forest (RF), back-propagation (BP), CNN, and RNN were constructed to predict the classification of the SERS spectra and the status of the patient specimens.…”

Section: Methodsmentioning

confidence: 99%

“…For ML and DL models, all the original spectra were preprocessed using a procedure described in Section S4 . 42 SVM, random forest (RF), back-propagation (BP), CNN, and RNN were constructed to predict the classification of the SERS spectra and the status of the patient specimens. For all these models, SERS spectra were randomly chosen as the training spectral set and testing spectral set with a ratio of 7:3, that is, 1758 SERS spectra from 28 positive specimens and 1652 SERS spectra from 84 negative specimens were used for the training spectral set, while the remaining 754 SERS spectra from 12 positive specimens and 708 SERS spectra from 36 negative specimens were used for the testing spectral set.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Rapid Detection of SARS-CoV-2 RNA in Human Nasopharyngeal Specimens Using Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

Yang

Jones

et al. 2022

ACS Sens.

Self Cite

View full text Add to dashboard Cite

A rapid and cost-effective method to detect the infection of SARS-CoV-2 is fundamental to mitigating the current COVID-19 pandemic. Herein, a surface-enhanced Raman spectroscopy (SERS) sensor with a deep learning algorithm has been developed for the rapid detection of SARS-CoV-2 RNA in human nasopharyngeal swab (HNS) specimens. The SERS sensor was prepared using a silver nanorod array (AgNR) substrate by assembling DNA probes to capture SARS-CoV-2 RNA. The SERS spectra of HNS specimens were collected after RNA hybridization, and the corresponding SERS peaks were identified. The RNA detection range was determined to be 10 3 −10 9 copies/mL in saline sodium citrate buffer. A recurrent neural network (RNN)-based deep learning model was developed to classify 40 positive and 120 negative specimens with an overall accuracy of 98.9%. For the blind test of 72 specimens, the RNN model gave a 97.2% accuracy prediction for positive specimens and a 100% accuracy for negative specimens. All the detections were performed in 25 min. These results suggest that the DNA-functionalized AgNR array SERS sensor combined with a deep learning algorithm could serve as a potential rapid point-of-care COVID-19 diagnostic platform.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Rapid Detection of SARS-CoV-2 RNA in Human Nasopharyngeal Specimens Using Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

Yang

Jones

et al. 2022

ACS Sens.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The emergence of RamanNet has also given a strong impetus to the use of machine learning in Raman data analysis. [56] …”

Section: The Application Of Sers Combined With Machine Learning In Me...mentioning

confidence: 99%

“…Zhao and his group utilized AgNR arrays deposited as SERS substrates to obtain Raman signals and used RamanNet, a deep learning algorithm designed for Raman spectroscopy data analysis, to classify bacterial endotoxins, and the classifier showed 100 % accuracy. The emergence of RamanNet has also given a strong impetus to the use of machine learning in Raman data analysis [56] …”

Section: The Application Of Sers Combined With Machine Learning In Me...mentioning

confidence: 99%

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

et al. 2023

View full text Add to dashboard Cite

Surface‐enhanced Raman spectroscopy (SERS) has shown strength in non‐invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi‐quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed.

show abstract

“…Thereby numerous LAL-reagent-free methods have been developed. These alternative platforms include optical (fluorescence [18][19][20][21][22][23][24][25] , SPR [26][27][28] , IR 29 , and SERS [30][31][32][33][34] , electrochemical 15,[35][36][37][38][39][40][41] , thermal 42 , colorimetric [43][44][45] , microwave methods 46 , and Mass spectroscopy 47 . Various affinity molecules such as protein [48][49][50][51] , peptide [52][53][54][55] (especially polymyxin B, PMB), and aptamer 4,13,56 have also been explored, as well as distinct nanomaterials systems including quantum dots 57 , nanoparticles [58][59][60][61][62][63] , MXenes 64 and hybrid system 65-68 for signal amplification.…”

mentioning

confidence: 99%

Single-Molecule Discrimination and the Specific Binding Properties of the Lipopolysaccharides with a Solid-State Nanopore sensor

Zhu

Liang

Zheng

et al. 2022

Preprint

View full text Add to dashboard Cite

Lipopolysaccharides (LPS) are the major constituent on the cell envelope of all gram-negative bacteria. They are ubiquitous in water, air, and food, and are toxic inflammatory stimulators and optimal biomarkers for some urinary disorders and sepsis. A good many optical, electrical, thermal, and electrochemical sensors based on the intermolecular interplay of LPS with proteins, peptides, and aptamers are reported, they are generally complicated methods. We demonstrate the single-molecule nanopore approach for the identification of LPS from distinct bacteria as well as the discrimination of serotypes from the same bacterium. With a 4 nm nanopore, we achieve a LOD of 10 ng/mL and a linear response up to 10,000 ng/mL. Both the antibiotic PMB and DNA aptamer display good binding affinity to LPS, and the complexes exhibit distinct nanopore translocation behaviors compared with the individual LPS. The real sample tests in both human serum and tap water show good performance characteristics in the identification of LPS in complicated media with a nanopore platforms. Our work shows a highly-sensitive and easy-to-handle scheme for clinical and environmental biomarkers determination and provides a promising screening tool for early warning of contamination in food, water, and medical supplies.

show abstract

Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

Abstract: Bacterial endotoxin, a major component of the Gram-negative bacterial outer membrane leaflet, is a lipopolysaccharide shed from bacteria during its growth and infection and can be utilized as a biomarker...

Cited by 27 publications

References 47 publications

Rapid Detection of SARS-CoV-2 RNA in Human Nasopharyngeal Specimens Using Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

Rapid Detection of SARS-CoV-2 RNA in Human Nasopharyngeal Specimens Using Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

SERS‐Based Biosensors Combined with Machine Learning for Medical Application**

Single-Molecule Discrimination and the Specific Binding Properties of the Lipopolysaccharides with a Solid-State Nanopore sensor

Contact Info

Product

Resources

About