Akademik Veri Yönetim Sistemi
BioTürkiye International Biotechnology Congress, İstanbul, Türkiye, 28 Eylül - 30 Aralık 2023, ss.50-51
Introduction: Antimicrobial resistance (AMR) in bacteria is a global health crisis due to the rapid emergence of multidrug-resistant bacteria and the lengthy development of new antimicrobials. The first step to limit antibiotic resistance is to reduce the use of antibiotics. For this, the bacteria causing the infection and their antibiotic resistance profiles must be detected quickly. Currently, culture-based diagnosis method, polymerase chain reaction (PCR) and antibody-based methods like enzyme-linked immunosorbent assays (ELISA) make up most of the techniques currently in use. However, these methods have several limitations, such as being expensive, timeconsuming, and requiring specialized personnel. Therefore, there is an urgent need for new methods with rapid results to prevent the wrong and unnecessary consumption of antibiotics. Nanotechnology, with its ability to manipulate materials at the nanoscale, is a promising strategy to address the detection of antimicrobial resistance. A potent approach in this direction is Surface-enhanced Raman spectroscopy (SERS), a powerful technique based on the interaction of nanoparticles and analytes for sensitive label-free analysis of biological samples. SERS can be used for rapid detection and identification of bacterial strains. However, distinguishing the antibiotic-resistant and susceptible bacteria by SERS spectra is challenging due to the high molecular similarity of the bacterial strains. To overcome this challenge, we proposed to use artificial intelligence (AI) methods to assist SERS-based diagnostics of AMR bacteria. Materials and methods: In this study, we used SERS to detect methicillin, erythromycin, and cefoxitin-resistant and susceptible Staphylococcus aureus, and applied a range of machine learning algorithms, including deep learning and traditional approaches, to distinguish between the bacterial species. Results and Discussion: SERS spectra of the bacteria were collected by using silver substrate and compared by analyzing in range of 400-1800 cm-1. Collected spectra will be classified with artificial intelligence to highlight the difference between different antibiotic resistance bacteria. Conclusion: In conclusion, the utilization of SERS and artificial intelligence holds promise as a sensitive and specific method for the detection of antibiotic resistance bacteria.
Keywords: Antimicrobial Resistance, Surface-enhanced Raman spectroscopy, Machine Learnings, S. aureus,
Nanotechnology