Application of artificial neural networks to describe the combined effect of pH and NaCl on the heat resistance of Bacillus stearothermophilus

Impact of shoulders on the calculus of heat sterilization treatments with different bacterial spores

To date, heat is still the most used technology in food preservation. The calculus of heat treatments is usually based on Bigelow observations i.e. treatment time is an exponential function of the heat treatment temperature. However, a number of researchers have reported deviations from linearity in heat inactivation curves that caused errors in the calculus. This research was designed to evaluate the variability of shoulder length among different sporulated species, the impact of treatment temperature on these shoulders and the relationship between the traditional D_T value and shoulder length. The heat inactivation kinetics of five bacterial spores of importance for the food industry was evaluated. B. weihenstephanensis and B. cereus did not show shoulders and D_T values calculated ranged from 0.99 to 0.23 and from 1.33 to 0.56 respectively at temperatures from 100 to 102.5 °C. On the other side B. subtilis, B. licheniformis and G. stearothermophilus showed shoulders of 1.75-0.42, 1.92-0.43 and 3.22-0.78 and D_T values of 1.52-0.32, 2.12-0.59 and 2.22-0.48 respectively in the range of temperatures tested. From the results obtained it was concluded that the presence and magnitude of shoulders depended on the bacterial spore species, the longest being those on the bacterial spores which showed greatest heat resistance. It has also been proved that shoulder lengths vary with treatment temperature in the same proportion of traditional D_T values, with the relationship Sl/D_T being constant. Thus, an equation which included the constant Sl/D_T was proposed.

An iTRAQ-Based Comparative Proteomics Analysis of the Biofilm and Planktonic States of Aeromonas veronii TH0426

Aeromonas veronii is a virulent fish pathogen that causes extensive economic losses in the aquaculture industry worldwide. In this study, a virulent strain of A. veronii TH0426 was used to establish an in vitro biofilm model. The results show that the biofilm-forming abilities of A. veronii TH0426 were similar in different media, peaking under conditions of 20 °C and pH 6. Further, isobaric tags for relative and absolute quantitation (iTRAQ)-based quantitative proteomics methods were used to compare the differential expression of A. veronii between the biofilm and planktonic cells. The results show alterations in 277 proteins, with 130 being upregulated and 147 downregulated. Pathway analysis and GO (Gene Ontology) annotations indicated that these proteins are mainly involved in metabolic pathways and the biosynthesis of secondary metabolites and antibiotics. These proteins are the main factors affecting the adaptability of A. veronii to its external environment. MRM (multiple reaction 27 monitoring) and qPCR (qPCR) were used to verify the differential proteins of the selected A. veronii. This is the first report on the biofilm and planktonic cells of A. veronii, thus contributing to studying the infection and pathogenesis of A. veronii.

Application of artificial neural networks to describe the combined effect of pH, time, NaCl and ethanol concentrations on the biofilm formation of Staphylococcus aureus

Biofilms are organized communities, adherent to the surface and resistant to adverse environmental and antimicrobial agents. So, its control is very important. Staphylococcus aureus is an opportunistic pathogen with the biofilm-forming ability that causes numerous problems in the medicine and food industry. Therefore, this study aimed to investigate the effect of pH, ethanol and NaCl concentrations after 24 and 48 h incubation times at 37 °C, also modeling the results with artificial neural network (ANN). For this purpose, after both incubation times, the effect of each parameter was studied, separately and also in combination at the levels in which the highest biofilm was formed. All results were modeled using multiple ANN and compared in terms of R-value and MSE. The highest biofilm formation ability was in neutral pH. Adding the ethanol and NaCl stimulated biofilm formation, but the inhibitory effect was observed at high concentrations of ethanol and NaCl and very acidic or highly alkaline pH levels. The more incubation time also led to an increase in biofilm formation. Eventually, the Feed-Forward, Back-Propagation Neural Network model with the Levenberg-Marquardt training algorithm and 4-12-1 topology was chosen (R-value = 0.995 and validation MSE = 0.011467). This ANN had high modeling ability because there was a high correlation between experimental data and modeling data. Therefore, it was concluded that pH, ethanol, NaCl, and time are effective parameters in the biofilm formation and there is a nonlinear relationship between these factors that the ANN is capable of modeling them.

Modeling growth limits of Bacillus spp. spores by using deep-learning algorithm

Growth/no growth boundary models for Bacillus spores that accounted for the effects of environmental pH, water activity (a_w), acetic acid, lactic acid, bacterial strain, and storage period were developed using conventional logistic regression and machine learning algorithms. Growth in tryptic soy broth at 317 conditions comprising nine levels of pH (4.0-6.5), six levels of a_w (0.85-1.00), six levels of acetic acid concentrations (0-0.8%), and five levels of lactic acid concentrations (0-0.8%) was examined to confirm growth limit conditions. All models developed using logistic regression, neural network, and deep learning on the basis of obtained datasets successfully described growth/no growth boundaries of three Bacillus species. Although the logistic regression model failed to describe growth limits under some conditions, neural network and deep learning approaches enabled to determine them in such cases. The developed models were evaluated by independent experimental data of growth in tryptic soy broth and in clam soup. The deep learning model enabled better prediction of independent data with smaller probabilistic variability values than those of the logistic regression and neural network models. The deep learning procedure can be utilized for growth boundary modeling to control bacterial growth safely and flexibly.

Prediction of the antimicrobial activity of walnut (Juglans regia L.) kernel aqueous extracts using artificial neural network and multiple linear regression

The mathematical model was established to determine the diameter of inhibition zone of the walnut extract on the twelve bacterial species. Type of extraction, concentration, and pathogens were taken as input variables. Two models were used with the aim of designing this system. One of them was developed with artificial neural networks (ANN), and the other was formed with multiple linear regression (MLR). Four common training algorithms were used. Levenberg-Marquardt (LM), Bayesian regulation (BR), scaled conjugate gradient (SCG) and resilient back propagation (RP) were investigated, and the algorithms were compared. Root mean squared error and correlation coefficient were evaluated as performance criteria. When these criteria were analyzed, ANN showed high prediction performance, while MLR showed low prediction performance. As a result, it is seen that when the different input values are provided to the system developed with ANN, the most accurate inhibition zone (IZ) estimates were obtained. The results of this study could offer new perspectives, particularly in the field of microbiology, because these could be applied to other type of extraction, concentrations, and pathogens, without resorting to experiments.

Development and validation of a predictive microbiology model for survival and growth of Salmonella on chicken stored at 4 to 12 °C

Salmonella spp. are a leading cause of foodborne illness. Mathematical models that predict Salmonella survival and growth on food from a low initial dose, in response to storage and handling conditions, are valuable tools for helping assess and manage this public health risk. The objective of this study was to develop and to validate the first predictive microbiology model for survival and growth of a low initial dose of Salmonella on chicken during refrigerated storage. Chicken skin was inoculated with a low initial dose (0.9 log) of a multiple antibiotic-resistant strain of Salmonella Typhimurium DT104 (ATCC 700408) and then stored at 4 to 12 °C for 0 to 10 days. A general regression neural network (GRNN) model that predicted log change of Salmonella Typhimurium DT104 as a function of time and temperature was developed. Percentage of residuals in an acceptable prediction zone, from -1 (fail-safe) to 0.5 (fail-dangerous) log, was used to validate the GRNN model by using a criterion of 70% acceptable predictions. Survival but not growth of Salmonella Typhimurium DT104 was observed at 4 to 8 °C. Maximum growth of Salmonella Typhimurium DT104 during 10 days of storage was 0.7 log at 9 °C, 1.1 log at 10 °C, 1.8 log at 11 °C, and 2.9 log at 12 °C. Performance of the GRNN model for predicting dependent data (n=163) was 85% acceptable predictions, for predicting independent data for interpolation (n=77) was 84% acceptable predictions, and for predicting independent data for extrapolation (n=70) to Salmonella Kentucky was 87% acceptable predictions. Thus, the GRNN model provided valid predictions for survival and growth of Salmonella on chicken during refrigerated storage, and therefore the model can be used with confidence to help assess and manage this public health risk.

General regression neural network and monte carlo simulation model for survival and growth of salmonella on raw chicken skin as a function of serotype, temperature, and time for use in risk assessment

A general regression neural network (GRNN) and Monte Carlo simulation model for predicting survival and growth of Salmonella on raw chicken skin as a function of serotype (Typhimurium, Kentucky, and Hadar), temperature (5 to 50 degrees C), and time (0 to 8 h) was developed. Poultry isolates of Salmonella with natural resistance to antibiotics were used to investigate and model survival and growth from a low initial dose (<1 log) on raw chicken skin. Computer spreadsheet and spreadsheet add-in programs were used to develop and simulate a GRNN model. Model performance was evaluated by determining the percentage of residuals in an acceptable prediction zone from -1 log (fail-safe) to 0.5 log (fail-dangerous). The GRNN model had an acceptable prediction rate of 92% for dependent data (n = 464) and 89% for independent data (n = 116), which exceeded the performance criterion for model validation of 70% acceptable predictions. Relative contributions of independent variables were 16.8% for serotype, 48.3% for temperature, and 34.9% for time. Differences among serotypes were observed, with Kentucky exhibiting less growth than Typhimurium and Hadar, which had similar growth levels. Temperature abuse scenarios were simulated to demonstrate how the model can be integrated with risk assessment, and the most common output distribution obtained was Pearson5. This study demonstrated that it is important to include serotype as an independent variable in predictive models for Salmonella. Had a cocktail of serotypes Typhimurium, Kentucky, and Hadar been used for model development, the GRNN model would have provided overly fail-safe predictions of Salmonella growth on raw chicken skin contaminated with serotype Kentucky. Thus, by developing the GRNN model with individual strains and then modeling growth as a function of serotype prevalence, more accurate predictions were obtained.

A radial basis function neural network approach to determine the survival of Listeria monocytogenes in Katiki, a traditional Greek soft cheese

A radial basis function neural network was developed to determine the kinetic behavior of Listeria monocytogenes in Katiki, a traditional white acid-curd soft spreadable cheese. The applicability of the neural network approach was compared with the reparameterized Gompertz, the modified Weibull, and the Geeraerd primary models. Model performance was assessed with the root mean square error of the residuals of the model (RMSE), the regression coefficient (R2), and the F test. Commercially prepared cheese samples were artificially inoculated with a five-strain cocktail of L. monocytogenes, with an initial concentration of 10(6) CFU g(-1) and stored at 5, 10, 15, and 20 degrees C for 40 days. At each storage temperature, a pathogen viability loss profile was evident and included a shoulder, a log-linear phase, and a tailing phase. The developed neural network described the survival of L. monocytogenes equally well or slightly better than did the three primary models. The performance indices for the training subset of the network were R2 = 0.993 and RMSE = 0.214. The relevant mean values for all storage temperatures were R2 = 0.981, 0.986, and 0.985 and RMSE = 0.344, 0.256, and 0.262 for the reparameterized Gompertz, modified Weibull, and Geeraerd models, respectively. The results of the F test indicated that none of the primary models were able to describe accurately the survival of the pathogen at 5 degrees C, whereas with the neural network all fvalues were significant. The neural network and primary models all were validated under constant temperature storage conditions (12 and 17 degrees C). First or second order polynomial models were used to relate the inactivation parameters to temperature, whereas the neural network was used a one-step modeling approach. Comparison of the prediction capability was based on bias and accuracy factors and on the goodness-of-fit index. The prediction performance of the neural network approach was equal to that of the primary models at both validation temperatures. The results of this work could increase the knowledge basis for the applicability of neural networks as an alternative tool in predictive microbiology.

Neural Network Analysis of Ex-vivo Expansion of Hematopoietic Stem Cells

The shortage of hematopoietic stem cells (HSCs) greatly limits their widespread clinical applications. Few studies however, investigated the relationship between the cellular expansion and the influencing factors although wide variety results of the ex-vivo expansion of HSCs existed in literature. Here, a back-propagation (BP) neural network model was employed to evaluate the ex-vivo expansions of nuclear cells (NCs), CD34(+) cells, and colony-forming units (CFU-Cs), where the output was the cellular expansion folds and the inputs include inoculated density, cytokines, resources, serum, stroma, culture time, and bioreactor types. Around 124, 86, and 90 samples were used to train the neural network for the expansion evaluations of NCs, CD34(+ )cells, and CFU-Cs, respectively, while 17, 14, and 10 samples were applied to predict respectively. The results show that for the training of network, the interval accuracy of the expansion folds for the different cells is 85.5, 86.1, and 86.7%, respectively, while the truth-value accuracy is still up to 59.7, 50.0, and 62.2%, respectively within a relative error (RE) of +/-20%. For the prediction of network, the interval accuracy can be up to 82.4, 71.4, and 70%, respectively, while the truth-value accuracy is only 29.4, 14.3, and 50.0%, respectively (RE = +/-20%). Moreover, six verification experiments were carried out based on our interval predicted values and the results proved that the five group predicted conditions lead to the correct expansion of the HSCs with the accuracy more than 80%. Considering the complexity of HSC expansion and complicated wide range of the experimental data, such relatively high interval accuracy for training and prediction as well as verification are satisfied. Therefore this nonlinear modeling makes it possible to describe quantitatively the effects of the culture conditions on the HSC expansion and to predict the optimal culture conditions for higher ex-vivo expansion of HSCs.