Machine Learning Protocol for Surface-Enhanced Raman Spectroscopy

2019 ◽  
Vol 10 (20) ◽  
pp. 6026-6031 ◽  
Author(s):  
Wei Hu ◽  
Sheng Ye ◽  
Yujin Zhang ◽  
Tianduo Li ◽  
Guozhen Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Surface Enhanced Raman Spectroscopy ◽  
Surface Enhanced ◽  
Surface Enhanced Raman

Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy

The Analyst ◽  
2020 ◽  
Vol 145 (14) ◽  
pp. 4827-4835 ◽  
Author(s):  
Shizhuang Weng ◽  
Hecai Yuan ◽  
Xueyan Zhang ◽  
Pan Li ◽  
Ling Zheng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Deep Learning ◽  
Surface Enhanced Raman Spectroscopy ◽  
Learning Networks ◽  
Biological Detection ◽  
Machine Learning Methods ◽  
Intelligent Analysis ◽  
Surface Enhanced ◽  
Surface Enhanced Raman

Surface-enhanced Raman spectroscopy (SERS) based on machine learning methods has been applied in material analysis, biological detection, food safety, and intelligent analysis.

Identification of methicillin-resistant Staphylococcus aureus bacteria using surface-enhanced Raman spectroscopy and machine learning techniques

The Analyst ◽  
2020 ◽  
Vol 145 (23) ◽  
pp. 7559-7570
Author(s):  
Fatma Uysal Ciloglu ◽  
Ayse Mine Saridag ◽  
Ibrahim Halil Kilic ◽  
Mahmut Tokmakci ◽  
Mehmet Kahraman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Staphylococcus Aureus ◽  
Raman Spectroscopy ◽  
Methicillin Resistant Staphylococcus Aureus ◽  
Surface Enhanced Raman Spectroscopy ◽  
Machine Learning Techniques ◽  
Methicillin Resistant ◽  
Learning Techniques ◽  
Surface Enhanced ◽  
Surface Enhanced Raman

Herein, surface-enhanced Raman spectroscopy (SERS) combined with supervised and unsupervised machine learning techniques were used for the identification of methicillin-resistant and methicillin-sensitive Staphylococcus aureus.

scholarly journals Comparative Analysis of Machine Learning Algorithms on Surface Enhanced Raman Spectra of Clinical Staphylococcus Species

2021 ◽  
Vol 12 ◽  
Author(s):  
Jia-Wei Tang ◽  
Qing-Hua Liu ◽  
Xiao-Cong Yin ◽  
Ya-Cheng Pan ◽  
Peng-Bo Wen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Raman Spectra ◽  
Surface Enhanced Raman Spectroscopy ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Surface Enhanced ◽  
Surface Enhanced Raman

Raman spectroscopy (RS) is a widely used analytical technique based on the detection of molecular vibrations in a defined system, which generates Raman spectra that contain unique and highly resolved fingerprints of the system. However, the low intensity of normal Raman scattering effect greatly hinders its application. Recently, the newly emerged surface enhanced Raman spectroscopy (SERS) technique overcomes the problem by mixing metal nanoparticles such as gold and silver with samples, which greatly enhances signal intensity of Raman effects by orders of magnitudes when compared with regular RS. In clinical and research laboratories, SERS provides a great potential for fast, sensitive, label-free, and non-destructive microbial detection and identification with the assistance of appropriate machine learning (ML) algorithms. However, choosing an appropriate algorithm for a specific group of bacterial species remains challenging, because with the large volumes of data generated during SERS analysis not all algorithms could achieve a relatively high accuracy. In this study, we compared three unsupervised machine learning methods and 10 supervised machine learning methods, respectively, on 2,752 SERS spectra from 117 Staphylococcus strains belonging to nine clinically important Staphylococcus species in order to test the capacity of different machine learning methods for bacterial rapid differentiation and accurate prediction. According to the results, density-based spatial clustering of applications with noise (DBSCAN) showed the best clustering capacity (Rand index 0.9733) while convolutional neural network (CNN) topped all other supervised machine learning methods as the best model for predicting Staphylococcus species via SERS spectra (ACC 98.21%, AUC 99.93%). Taken together, this study shows that machine learning methods are capable of distinguishing closely related Staphylococcus species and therefore have great application potentials for bacterial pathogen diagnosis in clinical settings.

scholarly journals SERS multiplexing of methylxanthine drug isomers via host-guest size matching and machine learning

2021 ◽  
Author(s):  
Weng-I Katherine Chio ◽  
Jia Liu ◽  
Tabitha Jones ◽  
Jayakumar Perumal ◽  
U. S. Dinish ◽  
...  
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Surface Enhanced Raman Spectroscopy ◽  
Multiplexed Detection ◽  
Drug Molecules ◽  
Similar Drug ◽  
Surface Enhanced ◽  
Surface Enhanced Raman ◽  
Detection And Quantification

Multiplexed detection and quantification of structurally similar drug molecules, methylxanthine MeX, incl. theobromine TBR, theophylline TPH and caffeine CAF, have been demonstrated via solution-based surface-enhanced Raman spectroscopy (SERS), achieving highly...

scholarly journals Differentiation of different antifungals with various mechanisms using dynamic surface-enhanced Raman spectroscopy combined with machine learning

2021 ◽  
pp. 2141002
Author(s):  
Hao Li ◽  
Yongbing Cao ◽  
Feng Lu
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Principal Component ◽  
Surface Enhanced Raman Spectroscopy ◽  
New Drugs ◽  
Dynamic Surface ◽  
Raman Spectrometer ◽  
Surface Enhanced ◽  
Surface Enhanced Raman ◽  
Portable Raman

With the increase in mortality caused by pathogens worldwide and the subsequent serious drug resistance owing to the abuse of antibiotics, there is an urgent need to develop versatile analytical techniques to address this public issue. Vibrational spectroscopy, such as infrared (IR) or Raman spectroscopy, is a rapid, noninvasive, nondestructive, real-time, low-cost, and user-friendly technique that has recently gained considerable attention. In particular, surface-enhanced Raman spectroscopy (SERS) can provide a highly sensitive readout for bio-detection with ultralow or even trace content. Nevertheless, extra attachment cost, nonaqueous acquisition, and low reproducibility require the conventional SERS (C-SERS) to further optimize the conditions. The emergence of dynamic SERS (D-SERS) sheds light on C-SERS because of the dispensable substrate design, superior enhancement and stability of Raman signals, and solvent protection. The powerful sensitivity enables D-SERS to perform only with a portable Raman spectrometer with moderate spatial resolution and precision. Moreover, the assistance of machine learning methods, such as principal component analysis (PCA), further broadens its research depth through data mining of the information within the spectra. Therefore, in this study, D-SERS, a portable Raman spectrometer, and PCA were used to determine the phenotypic variations of fungal cells Candida albicans (C. albicans) under the influence of different antifungals with various mechanisms, and unknown antifungals were predicted using the established PCA model. We hope that the proposed technique will become a promising candidate for finding and screening new drugs in the future.

scholarly journals SERSNet: Surface-Enhanced Raman Spectroscopy Based Biomolecule Detection Using Deep Neural Network

Biosensors ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 490
Author(s):  
Seongyong Park ◽  
Jaeseok Lee ◽  
Shujaat Khan ◽  
Abdul Wahab ◽  
Minseok Kim
Keyword(s):  
Machine Learning ◽  
Raman Spectroscopy ◽  
Test Performance ◽  
Model Development ◽  
Surface Enhanced Raman Spectroscopy ◽  
Learning Models ◽  
Biomolecule Detection ◽  
Surface Enhanced ◽  
Surface Enhanced Raman ◽  
Machine Learning Models

Surface-Enhanced Raman Spectroscopy (SERS)-based biomolecule detection has been a challenge due to large variations in signal intensity, spectral profile, and nonlinearity. Recent advances in machine learning offer great opportunities to address these issues. However, well-documented procedures for model development and evaluation, as well as benchmark datasets, are lacking. Towards this end, we provide the SERS spectral benchmark dataset of Rhodamine 6G (R6G) for a molecule detection task and evaluate the classification performance of several machine learning models. We also perform a comparative study to find the best combination between the preprocessing methods and the machine learning models. Our best model, coined as the SERSNet, robustly identifies R6G molecule with excellent independent test performance. In particular, SERSNet shows 95.9% balanced accuracy for the cross-batch testing task.

Bacterial detection and differentiation via direct volatile organic compound sensing with surface enhanced Raman spectroscopy

2017 ◽  
Author(s):  
Caitlin S. DeJong ◽  
David I. Wang ◽  
Aleksandr Polyakov ◽  
Anita Rogacs ◽  
Steven J. Simske ◽  
...  
Keyword(s):  
Raman Spectroscopy ◽  
Bacterial Infections ◽  
Direct Detection ◽  
Point Of Care ◽  
Surface Enhanced Raman Spectroscopy ◽  
E Coli ◽  
Recent Emergence ◽  
Surface Enhanced ◽  
Volatile Organic ◽  
Surface Enhanced Raman

Through the direct detection of bacterial volatile organic compounds (VOCs), via surface enhanced Raman spectroscopy (SERS), we report here a reconfigurable assay for the identification and monitoring of bacteria. We demonstrate differentiation between highly clinically relevant organisms: <i>Escherichia coli</i>, <i>Enterobacter cloacae</i>, and <i>Serratia marcescens</i>. This is the first differentiation of bacteria via SERS of bacterial VOC signatures. The assay also detected as few as 10 CFU/ml of <i>E. coli</i> in under 12 hrs, and detected <i>E. coli</i> from whole human blood and human urine in 16 hrs at clinically relevant concentrations of 10<sup>3</sup> CFU/ml and 10<sup>4</sup> CFU/ml, respectively. In addition, the recent emergence of portable Raman spectrometers uniquely allows SERS to bring VOC detection to point-of-care settings for diagnosing bacterial infections.

Sign in / Sign up

Export Citation Format

Share Document