Machine learning models for prediction of Escherichia coli O157:H7 growth in raw ground beef at different storage temperatures.

Shiga toxin-producing Escherichia coli (STEC) can be life-threatening and lead to major outbreaks. The prevention of STEC-related infections can be provided by control measures at all stages of the food chain. The growth performance of E. coli O157:H7 at different temperatures in raw ground beef spiked with cocktail inoculum was investigated using machine learning (ML) models to address this problem. After spiking, ground beef samples were stored at 4, 10, 20, 30 and 37 °C. Repeated E. coli O157 enumeration was performed at 0-96 h with 21 times repeated counting. The obtained microbiological data were evaluated with ML methods (Artificial Neural Network (ANN), Random Forest (RF), Support Vector Regression (SVR), and Multiple Linear Regression (MLR)) and statistically compared for valid prediction. The coefficient of determination (R2) and mean squared error (MSE) are two essential criteria used to evaluate the model performance regarding the comparison between the observed value and the prediction made by the model. RF model showed superior performance with 0.98 R2 and 0.08 MSE values for predicting the growth performance of E. coli O157 at different temperatures. MLR model predictions were obtained further from the observed values with 0.66 R2 and 2.7 MSE values. Our results indicate that ML methods can predict of E. coli O157:H7 growth in ground beef at different temperatures to strengthen food safety professionals and legal authorities to assess contamination risks and determine legal limits and criteria proactively.

Highly Accurate Identification of Bacteria's Antibiotic Resistance Based on Raman Spectroscopy and U-Net Deep Learning Algorithms.

Bacterial pathogens especially antibiotic-resistant ones are a public health concern worldwide. To oppose the morbidity and mortality associated with them, it is critical to select an appropriate antibiotic by performing a rapid bacterial diagnosis. Using a combination of Raman spectroscopy and deep learning algorithms to identify bacteria is a rapid and reliable method. Nevertheless, due to the loss of information during training a model, some deep learning algorithms suffer from low accuracy. Herein, we modify the U-Net architecture to fit our purpose of classifying the one-dimensional Raman spectra. The proposed U-Net model provides highly accurate identification of the 30 isolates of bacteria and yeast, empiric treatment groups, and antimicrobial resistance, thanks to its capability to concatenate and copy important features from the encoder layers to the decoder layers, thereby decreasing the data loss. The accuracies of the model for the 30-isolate level, empiric treatment level, and antimicrobial resistance level tasks are 86.3, 97.84, and 95%, respectively. The proposed deep learning model has a high potential for not only bacterial identification but also for other diagnostic purposes in the biomedical field.

Investigation of mammalian cells expressing SARS-CoV-2 proteins by surface-enhanced Raman scattering and multivariate analysis.

COVID-19 has caused millions of cases and deaths all over the world since late 2019. Rapid detection of the virus is crucial for controlling its spread through a population. COVID-19 is currently detected by nucleic acid-based tests and serological tests. However, these methods have limitations such as the requirement of high-cost reagents, false negative results and being time consuming. Surface-enhanced Raman scattering (SERS), which is a powerful technique that enhances the Raman signals of molecules using plasmonic nanostructures, can overcome these disadvantages. In this study, we developed a virus-infected cell model and analyzed this model by SERS combined with Principal Component Analysis (PCA). HEK293 cells were transfected with plasmids encoding the nucleocapsid (N), membrane (M) and envelope (E) proteins of SARS-CoV-2 via polyethyleneimine (PEI). Non-plasmid transfected HEK293 cells were used as the control group. Cellular uptake was optimized with green fluorescence protein (GFP) plasmids and evaluated by fluorescence microscopy and flow cytometry. The transfection efficiency was found to be around 60%. The expression of M, N, and E proteins was demonstrated by western blotting. The SERS spectra of the total proteins of transfected cells were obtained using a gold nanoparticle-based SERS substrate. Proteins of the transfected cells have peak positions at 646, 680, 713, 768, 780, 953, 1014, 1046, 1213, 1243, 1424, 2102, and 2124 cm-1. To reveal spectral differences between plasmid transfected cells and non-transfected control cells, PCA was applied to the spectra. The results demonstrated that SERS coupled with PCA might be a favorable and reliable way to develop a rapid, low-cost, and promising technique for the detection of COVID-19.

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

To combat antibiotic resistance, it is extremely important to select the right antibiotic by performing rapid diagnosis of pathogens. Traditional techniques require complicated sample preparation and time-consuming processes which are not suitable for rapid diagnosis. To address this problem, we used surface-enhanced Raman spectroscopy combined with machine learning techniques for rapid identification of methicillin-resistant and methicillin-sensitive Gram-positive Staphylococcus aureus strains and Gram-negative Legionella pneumophila (control group). A total of 10 methicillin-resistant S. aureus (MRSA), 3 methicillin-sensitive S. aureus (MSSA) and 6 L. pneumophila isolates were used. The obtained spectra indicated high reproducibility and repeatability with a high signal to noise ratio. Principal component analysis (PCA), hierarchical cluster analysis (HCA), and various supervised classification algorithms were used to discriminate both S. aureus strains and L. pneumophila. Although there were no noteworthy differences between MRSA and MSSA spectra when viewed with the naked eye, some peak intensity ratios such as 732/958, 732/1333, and 732/1450 proved that there could be a significant indicator showing the difference between them. The k-nearest neighbors (kNN) classification algorithm showed superior classification performance with 97.8% accuracy among the traditional classifiers including support vector machine (SVM), decision tree (DT), and naïve Bayes (NB). Our results indicate that SERS combined with machine learning can be used for the detection of antibiotic-resistant and susceptible bacteria and this technique is a very promising tool for clinical applications.