Application of recurrent neural network to predict bacterial growth in dynamic conditions

Video frame prediction of microbial growth with a recurrent neural network

The recent explosion of interest and advances in machine learning technologies has opened the door to new analytical capabilities in microbiology. Using experimental data such as images or videos, machine learning, in particular deep learning with neural networks, can be harnessed to provide insights and predictions for microbial populations. This paper presents such an application in which a Recurrent Neural Network (RNN) was used to perform prediction of microbial growth for a population of two Pseudomonas aeruginosa mutants. The RNN was trained on videos that were acquired previously using fluorescence microscopy and microfluidics. Of the 20 frames that make up each video, 10 were used as inputs to the network which outputs a prediction for the next 10 frames of the video. The accuracy of the network was evaluated by comparing the predicted frames to the original frames, as well as population curves and the number and size of individual colonies extracted from these frames. Overall, the growth predictions are found to be accurate in metrics such as image comparison, colony size, and total population. Yet, limitations exist due to the scarcity of available and comparable data in the literature, indicating a need for more studies. Both the successes and challenges of our approach are discussed.

Application of deep neural techniques in predictive modelling for the estimation of Escherichia coli growth rate

AIMS

To develop a predictive model for Escherichia coli using deep neural networks.

METHODS AND RESULTS

Batch experiments are conducted at different temperatures closer to optimum value (36·5°C, 37°C, 37·5°C, 38°C and 38·5°C) to obtain the growth curves of E .coli K-12. Two primary models namely modified Gompertz and new logistic are chosen. Three secondary models namely Gaussian, nonlinear autoregressive eXogenous (NARX) model and long short-term memory (LSTM) are developed. The novelty in this paper is the development of secondary models using artificial neural network (ANN) and deep network. The performance measures chosen to compare the developed primary and secondary models are correlation coefficient (R² ), root-mean-square error (RMSE) and accuracy factor (A_f ). Results show that modified Gompertz model has better R² (0·99) and RMSE (0·019) when compared to new logistic model. Also, the deep network model outperforms other secondary models. Based on the primary and novel secondary model, a predictive model (tertiary model) is developed with improved accuracy and is validated.

CONCLUSIONS

The proposed predictive model exhibit good validation results in terms of RMSE and R² values and can be applied for determining the growth rate of E. coli at a particular temperature value.

SIGNIFICANCE AND IMPACT OF THE STUDY

The proposed model can be used in food processing industries during enzyme production such as Chymosin, to predict the growth rate of E. coli as a function of temperature. Also, the developed LSTM and NARX models can be used to predict maximum specific growth rate of other microbial strains with proper training.

Modeling the Effects of the Preculture Temperature on the Lag Phase of Listeria monocytogenes at 25°C

In predictive microbiology, the study of the microbial lag phase, i.e., the time needed for bacteria to adapt to a new environment before multiplying, has received a great deal of attention in the research literature. The microbial lag phase is more difficult to estimate than the specific growth rate because the lag phase is impacted by the previous and actual growth environments. In this study, the growth of Listeria monocytogenes preincubated at 0, 5, 10, and 15°C and subsequently grown at 25°C was investigated at the single-cell and population levels. The population lag phase of L. monocytogenes was obtained by fitting the Baranyi model, and the single-cell lag time was estimated by the time to detection method. The lag phase at the single-cell and population levels of L. monocytogenes presented a downward trend as the preculture temperature ranged from 0 to 15°C. The population lag phase of L. monocytogenes was lower than the single-cell lag time at the same preculture temperature. In addition, except for the zero-lag distribution at a preculture temperature of 15°C, all the single-cell lag time distributions of L. monocytogenes followed a Weibull distribution under all preculture temperatures. The preculture temperature had a significant impact on the rapid variation in the single-cell lag time distribution. Thus, the influence of preculture temperature on the lag phase needs to be quantitatively analyzed for better assessment of microbiological risk.

Promoter activity dynamics in the lag phase of Escherichia coli

Background

Lag phase is a period of time with no growth that occurs when stationary phase bacteria are transferred to a fresh medium. Bacteria in lag phase seem inert: their biomass does not increase. The low number of cells and low metabolic activity make it difficult to study this phase. As a consequence, it has not been studied as thoroughly as other bacterial growth phases. However, lag phase has important implications for bacterial infections and food safety. We asked which, if any, genes are expressed in the lag phase of Escherichia coli, and what is their dynamic expression pattern.

Results

We developed an assay based on imaging flow cytometry of fluorescent reporter cells that overcomes the challenges inherent in studying lag phase. We distinguish between lag1 phase- in which there is no biomass growth, and lag2 phase- in which there is biomass growth but no cell division. We find that in lag1 phase, most promoters are not active, except for the enzymes that utilize the specific carbon source in the medium. These genes show promoter activities that increase exponentially with time, despite the fact that the cells do not measurably increase in size. An oxidative stress promoter, katG, is also active. When cells enter lag2 and begin to grow in size, they switch to a full growth program of promoter activity including ribosomal and metabolic genes.

Conclusions

The observed exponential increase in enzymes for the specific carbon source followed by an abrupt switch to production of general growth genes is a solution of an optimal control model, known as bang-bang control. The present approach contributes to the understanding of lag phase, the least studied of bacterial growth phases.

Implications of salt and sodium reduction on microbial food safety

Excess sodium consumption has been cited as a primary cause of hypertension and cardiovascular diseases. Salt (sodium chloride) is considered the main source of sodium in the human diet, and it is estimated that processed foods and restaurant foods contribute 80% of the daily intake of sodium in most of the Western world. However, ample research demonstrates the efficacy of sodium chloride against pathogenic and spoilage microorganisms in a variety of food systems. Notable examples of the utility and necessity of sodium chloride include the inhibition of growth and toxin production by Clostridium botulinum in processed meats and cheeses. Other sodium salts contributing to the overall sodium consumption are also very important in the prevention of spoilage and/or growth of microorganisms in foods. For example, sodium lactate and sodium diacetate are widely used in conjunction with sodium chloride to prevent the growth of Listeria monocytogenes and lactic acid bacteria in ready-to-eat meats. These and other examples underscore the necessity of sodium salts, particularly sodium chloride, for the production of safe, wholesome foods. Key literature on the antimicrobial properties of sodium chloride in foods is reviewed here to address the impact of salt and sodium reduction or replacement on microbiological food safety and quality.

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.

Model on the microbial quality change of seasoned soybean sprouts for on-line shelf life prediction

The growth of aerobic bacteria on Korean seasoned soybean sprouts was modelled as a function of temperature to estimate microbial spoilage and shelf life on a real-time basis under dynamic storage conditions. Counts of aerobic bacteria on seasoned soybean sprouts stored at constant temperatures between 0 degrees C and 15 degrees C were recorded. The bootstrapping method was applied to generate many resampled data sets of mean microbial plate counts that were then used to estimate the parameters of the microbial growth model of Baranyi and Roberts. The distributions of the model parameters were quantified, and their temperature dependencies were expressed as mathematical functions. When the temperature functions of the parameters were incorporated into differential equations describing microbial growth, predictions of microbial growth under fluctuating temperature conditions were similar to observed microbial growth.

Use of unsupervised and supervised artificial neural networks for the identification of lactic acid bacteria on the basis of SDS-PAGE patterns of whole cell proteins

Conventional multivariate statistical techniques (hierarchical cluster analysis, linear discriminant analysis) and unsupervised (Kohonen Self Organizing Map) and supervised (Bayesian network) artificial neural networks were compared for as tools for the classification and identification of 352 SDS-PAGE patterns of whole cell proteins of lactic acid bacteria belonging to 22 species of the genera Lactobacillus, Leuconostoc, Enterococcus, Lactococcus and Streptococcus including 47 reference strains. Electrophoretic data were pre-treated using the logistic weighting function described by Piraino et al. [Piraino, P., Ricciardi, A., Lanorte, M. T., Malkhazova, I., Parente, E., 2002. A new procedure for data reduction in electrophoretic fingerprints of whole-cell proteins. Biotechnol. Lett. 24, 1477-1482]. Hierarchical cluster analysis provided a satisfactory classification of the patterns but was unable to discriminate some species (Leuconostoc, Lb. sakei/Lb. curvatus, Lb. acidophilus/Lb. helveticus, Lb. plantarum/Lb. paraplantarum, Lc. lactis/Lc. raffinolactis). A 7x7 Kohonen self-organizing map (KSOM), trained with the patterns of the reference strains, provided a satisfactory classification of the patterns and was able to discriminate more species than hierarchical cluster analysis. The map was used in predictive mode to identify unknown strains and provided results which in 85.5% of cases matched the classification obtained by hierarchical cluster analysis. Two supervised tools, linear discriminant analysis and a 23:5:2 Bayesian network were proven to be highly effective in the discrimination of SDS-PAGE patterns of Lc. lactis from those of other species. We conclude that data reduction by logistic weighting coupled to traditional multivariate statistical analysis or artificial neural networks provide an effective tool for the classification and identification of lactic acid bacteria on the basis of SDS-PAGE patterns of whole cell proteins.

Effect of preincubation temperature and pH on the individual cell lag phase of Listeria monocytogenes, cultured at refrigeration temperatures

The impact of precultural temperature and pH on the distribution of the lag phase of individual Listeria monocytogenes cells was assessed during preincubation at 7 degrees C, using a dilution protocol to obtain single cells, and optical density measurements to estimate the individual lag phase. Firstly, the pure temperature effect (37, 15, 10, 7, 4 and 2 degrees C) was investigated on a subsequent growth at 7 degrees C and pH 7.4. Secondly, low precultural temperatures (10, 7 and 4 degrees C) were combined with a controlled pH at 7.4 and 5.7 with a subsequent growth at 7 degrees C and at different pH values (7.4, 6.0 and 5.5). For all temperature-pH combinations, the individual cell lag phase was determined using a three-phase linear growth model. It was observed that at low precultural temperatures (2, 4 and 7 degrees C), a high proportion of L. monocytogenes cells were able to grow at 7 degrees C with almost no lag phase, consequently, the resulting distributions were positively skewed. Beside this, the variability observed was lower than at higher precultural temperatures. Regarding the precultural pH effect, at pH 7.4 the mean values of the lag phases were shorter at lower preincubation temperatures; while at pH 5.7 small pH transitions produced shorter individual lag phases at all precultural temperatures. The quantification of the effect of precultural conditions on the individual cell lag phase duration would improve the accuracy of the existing growth models, especially when a series of processing and storage steps are linked together in a process model or exposure assessment. Distributions will be fitted to the data for every set of conditions, generating useful tools for further risk assessment purposes.

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

A model for prediction of bacterial spore inactivation was developed. The influence of temperature, pH and NaCl on the heat resistance of Bacillus stearothermophilus spores was described using low-complexity, black box models based on artificial neural networks. Literature data were used to build and train the neural network, and new experimental data were used to evaluate it. The neural network models gave better predictions than the classical quadratic response surface model in all the experiments tried. When the neural networks were evaluated using new experimental data, also good predictions were obtained, providing fail-safe predictions of D values in all cases. The weights and biases values of neurons of the neural network that gave the best results are presented, so the reader can use the model for their own purposes. The use of this non-linear modelling technique makes it possible to describe more accurately interacting effects of environmental factors when compared with classical predictive microbial models.

A hybrid Bayesian-neural network approach for probabilistic modeling of bacterial growth/no-growth interface

A hybrid probabilistic modeling approach that integrates artificial neural networks (ANNs) with statistical Bayesian conditional probability estimation is proposed. The suggested approach benefits from the power of ANNs as highly flexible nonlinear mapping paradigms, and the Bayes' theorem for computing probabilities of bacterial growth with the aid of Parzen's probability distribution function estimators derived for growth and no-growth (G/NG) states. The proposed modeling approach produces models that can predict the probability of growth of targeted microorganism as affected by a set of parameters pertaining to extrinsic factors and operating conditions. The models also can be used to define the probabilistic boundary (interface) between growth and no-growth, and as such can define and predict the values of critical parameters required to keep a desired pre-specified bacterial growth risk in check. A modular system incorporating the various computational modules was constructed to illustrate the application of the hybrid approach to the probabilistic modeling of growth of pathogenic Escherichia coli strain as affected by temperature and water activity. The proposed approach was compared to other techniques including the traditional linear and nonlinear logistic regression. Results indicated that the hybrid approach outperforms the other approaches in its accuracy as well as flexibility to extract the implicit interrelationships between the various parameters. Advantages and limitations of the approach were also discussed and compared to those of other techniques.