Abstract
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.
Highlights
The genus Staphylococcus includes many commonly encountered and clinically important pathogenic species in nosocomial infections, such as Staphylococcus aureus and Staphylococcus epidermidis, etc. (McGavin and Heinrichs, 2012)
Average Raman Spectra Average Raman spectra with SE could clearly and quantitatively display the general trend and reflect the data variance in the Raman spectra, which were present in Figure 4 for all the nine Staphylococcus species explored in this study
Raman spectroscopy has been widely used in the diagnosis of bacterial pathogens in terms of species differentiation, antibiotic resistance detection, and virulence factor identification (Rebrošová et al, 2017)
Summary
The genus Staphylococcus includes many commonly encountered and clinically important pathogenic species in nosocomial infections, such as Staphylococcus aureus and Staphylococcus epidermidis, etc. (McGavin and Heinrichs, 2012). (McGavin and Heinrichs, 2012). Some of these Staphylococcus species could cause severe infectious diseases, especially in immune-compromised patients with the use of catheters and other medical implants (Schlievert et al, 2016). Raman spectroscopy (RS) is a widely used non-destructive, vibrational spectroscopic technique in the fields of biology and medicine, such as cell-drug interactions (Buckley and Ryder, 2017) and cancer diagnosis (D’Acunto et al, 2020), etc., which normally generates spectra of the analytes that can be further used for quantitative and qualitative analyses (Das and Agrawal, 2011). The basic principle of Raman spectroscopy relies on the photons in elastically scattered after interacting with vibrating molecules within the sample. It is very difficult for RS to obtain reliable spectra due to its comparatively poor reproducibility (Dong and Zhao, 2017)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
