Dataset Information

Drug-resistant Staphylococcus aureus bacteria detection by combining surface-enhanced Raman spectroscopy (SERS) and deep learning techniques.

ABSTRACT: Over the past year, the world's attention has focused on combating COVID-19 disease, but the other threat waiting at the door-antimicrobial resistance should not be forgotten. Although making the diagnosis rapidly and accurately is crucial in preventing antibiotic resistance development, bacterial identification techniques include some challenging processes. To address this challenge, we proposed a deep neural network (DNN) that can discriminate antibiotic-resistant bacteria using surface-enhanced Raman spectroscopy (SERS). Stacked autoencoder (SAE)-based DNN was used for the rapid identification of methicillin-resistant Staphylococcus aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) bacteria using a label-free SERS technique. The performance of the DNN was compared with traditional classifiers. Since the SERS technique provides high signal-to-noise ratio (SNR) data, some subtle differences were found between MRSA and MSSA in relative band intensities. SAE-based DNN can learn features from raw data and classify them with an accuracy of 97.66%. Moreover, the model discriminates bacteria with an area under curve (AUC) of 0.99. Compared to traditional classifiers, SAE-based DNN was found superior in accuracy and AUC values. The obtained results are also supported by statistical analysis. These results demonstrate that deep learning has great potential to characterize and detect antibiotic-resistant bacteria by using SERS spectral data.

SUBMITTER: Ciloglu FU

PROVIDER: S-EPMC8446005 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Drug-resistant pathogenic bacteria are a major cause of infectious diseases in the world and they have become a major threat through the reduced efficacy of developed antibiotics. This issue can be addressed by using bacteriophages, which can kill lethal bacteria and prevent them from causing infections. Surface-enhanced Raman spectroscopy (SERS) is a promising technique for studying the degradation of infectious bacteria by the interaction of bacteriophages to break the vicious cycle of drug-resistant bacteria and help to develop chemotherapy-independent remedial strategies. The phage (viruses)-sensitive Staphylococcus aureus (S. aureus) bacteria are exposed to bacteriophages (Siphoviridae family) in the time frame from 0 min (control) to 50 minutes with intervals of 5 minutes and characterized by SERS using silver nanoparticles as SERS substrate. This allows us to explore the effects of the bacteriophages against lethal bacteria (S. aureus) at different time intervals. The differentiating SERS bands are observed at 575 (C-C skeletal mode), 620 (phenylalanine), 649 (tyrosine, guanine (ring breathing)), 657 (guanine (COO deformation)), 728-735 (adenine, glycosidic ring mode), 796 (tyrosine (C-N stretching)), 957 (C-N stretching (amide lipopolysaccharides)), 1096 (PO2 (nucleic acid)), 1113 (phenylalanine), 1249 (CH2 of amide III, N-H bending and C-O stretching (amide III)), 1273 (CH2, N-H, C-N, amide III), 1331 (C-N stretching mode of adenine), 1373 (in nucleic acids (ring breathing modes of the DNA/RNA bases)) and 1454 cm-1 (CH2 deformation of saturated lipids), indicating the degradation of bacteria and replication of bacteriophages. Multivariate data analysis was performed by employing principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA) to study the biochemical differences in the S. aureus bacteria infected by the bacteriophage. The SERS spectral data sets were successfully differentiated by PLS-DA with 94.47% sensitivity, 98.61% specificity, 94.44% precision, 98.88% accuracy and 81.06% area under the curve (AUC), which shows that at 50 min interval S. aureus bacteria is degraded by the replicating bacteriophages.

Dataset Information

Drug-resistant Staphylococcus aureus bacteria detection by combining surface-enhanced Raman spectroscopy (SERS) and deep learning techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets