Abstract
We develop Bayesian methodologies for constructing and estimating a stochastic quasi-chemical model (QCM) for bacterial growth. The deterministic QCM, described as a nonlinear system of ODEs, is treated as a dynamical system with random parameters, and a variational approach is used to approximate their probability distributions and explore the propagation of uncertainty through the model. The approach consists of approximating the parameters’ posterior distribution by a probability measure chosen from a parametric family, through minimization of their Kullback–Leibler divergence.
Similar content being viewed by others
References
Banks, H., Bihari, K.: Modelling and estimating uncertainty in parameter estimation. Inverse Prob. 17, 95 (2001)
Banks, H., Browning, W., Catenacci, J., Wood, T.: Analysis of a Quasi-chemical Kinetic Food Chemistry Model. Center for Research in Scientific Computation Technical Report CRSC-TR16-05. NC State University, Raleigh, NC (2016)
Baranyi, J., Roberts, T.: A dynamic approach to predicting bacterial growth in food. Int. J. Food Microbiol. 23, 277–294 (1994)
Baranyi, J., Roberts, T., McClure, P.: A non-autonomous differential equation to model bacterial growth. Food Microbiol. 10, 43–59 (1993)
Bickel, P., Doksum, K.: Mathematical Statistics: Basic Ideas and Selected Topics, vol. 2. CRC Press, Boca Raton (2015)
Bishop, C.: Pattern Recognition and Machine Learning, Information Science and Statistics. Springer, New York (2006)
Browning, W.J.: Near real-time quantification of stochastic model parameters. Tech. rep., prepared by Applied Mathematics Inc., Small Business Technology Transfer, Phase II Final Report, Army STTR Topic A13A-009 (28 September 2016)
Buchanan, R.: Predictive microbiology: Mathematical modeling of microbial growth in foods. In: ACS Symposium Series-American Chemical Society, (1992)
Buchanan, R., Whiting, R., Damert, W.: When is simple good enough: a comparison of the Gompertz. Baranyi, and three-phase linear models for fitting bacterial growth curves. Food Microbiol. 14, 313–326 (1997)
Byrd, R., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comput. 16, 1190–1208 (1995)
Chaloner, K., Verdinelli, I.: Bayesian experimental design: a review. Stat. Sci. 10(3), 273–304 (1995)
Chaspari, T., Tsiartas, A., Tsilifis, P., Narayanan, S.: Markov chain monte carlo inference of parametric dictionaries for sparse bayesian approximations. IEEE Trans. Signal Process. 64, 3077–3092 (2016)
Chen, P., Zabaras, N., Bilionis, I.: Uncertainty propagation using infinite mixture of gaussian processes and variational bayesian inference. J. Comput. Phys. 284, 291–333 (2015)
Doona, C., Feeherry, F., Ross, E.: A quasi-chemical model for the growth and death of microorganisms in foods by non-thermal and high-pressure processing. Int. J. Food Microbiol. 100, 21–32 (2005)
Doona, C., Feeherry, F., Ross, E., Kustin, K.: Inactivation kinetics of listeria monocytogenes by highpressure processing: pressure and temperature variation. J. Food Sci. 77, M458–M465 (2012)
Gershman, S., Hoffman, M., Blei, D.: Nonparametric variational inference. In: International Conference on Machine Learning (2012)
Goldbeter, A.: Biochemical Oscillations and Cellular Rhythms: The Molecular Bases of Periodic and Chaotic Behaviour. Cambridge University Press, Cambridge (1997)
Gompertz, B.: On the nature of the function expressive of the law of human mortality and on a new mode of determining the value of life contingencies. Philos. Trans. R. Soc. Lond. 115, 513–583 (1825)
Haario, H., Saksman, E., Tamminen, J.: An adaptive Metropolis algorithm. Bernoulli 7, 223–242 (2001)
Hastings, W.: Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57, 97–109 (1970)
Huber, M., Bailey, T., Durrant-Whyte, H., Hanebeck, U.: On entropy approximation for Gaussian mixture random vectors, In: IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2008, (pp. 181–188). IEEE, (2008)
Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22, 79–86 (1951)
McMeekin, T., Brown, J., Krist, K., Miles, D., Neumeyer, K., Nichols, D., Olley, J., Presser, K., Ratkowsky, D., Ross, T., Salter, M.: Quantitative microbiology: a basis for food safety. Emerg. Infect. Dis. 3, 541 (1997)
Metropolis, N., Rosenbluth, A., Rosenbluth, M., Teller, A., Teller, E.: Equations of state calculations by fast computing machines. J. Chem. Phys. 21, 1087–1091 (1953)
Pinski, F., Simpson, G., Stuart, A., Weber, H.: Algorithms for Kullback–Leibler approximation of probability measures in infinite dimensions. SIAM J. Sci. Comput. 37, A2733–A2757 (2015)
Ricker, W.: Growth rates and models. Fish Physiol. 8, 677–743 (1979)
Robert, C., Casella, G.: Monte Carlo Statistical Methods. Springer, Berlin (2013)
Roberts, G., Rosenthal, J.: Optimal scaling of discrete approximations to Langevin diffusions. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 60, 255–268 (1998)
Ross, E., Taub, I., Doona, C., Feeherry, F., Kustin, K.: The mathematical properties of the quasi-chemical model for microorganism growth-death kinetics in foods. Int. J. Food Microbiol. 99, 157–171 (2005)
Schnute, J.: A versatile growth model with statistically stable parameters. Can. J. Fish. Aquat. Sci. 38, 1128–1140 (1981)
Silverman, B.: Density estimation for statistics and data analysis, vol. 26. CRC Press, Boca Raton (1986)
Stuart, A.: Inverse problems: a bayesian perspective. Acta Numer. 19, 451–559 (2010)
Tarantola, A.: Inverse Problem Theory and Methods for Model Parameter Estimation. SIAM, Philadelphia (2005)
Taub, I., Ross, E., Feeherry, F.: Model for predicting the growth and death of pathogenic organisms. In: Van Impe, J.F.M., Gernaerts, K. (eds.) Proceedings of the Third International Conference on Predictive Modeling in Foods (2000)
Taub, I., Feeherry, F., Ross, E., Kustin, K., Doona, C.: A quasi-chemical kinetics model for the growth and death of Staphylococcus aureus in intermediate moisture bread. J. Food Sci. 68, 2530–2537 (2003)
Tsilifis, P., Bilionis, I., Katsounaros, I., Zabaras, N.: Computationally efficient variational approximations for bayesian inverse problems. J. Verif. Valid. Uncertain. Quantif. 1, 031004 (2016)
Tsilifis, P., Ghanem, R., Hajali, P.: Efficient bayesian experimentation using an expected information gain lower bound. SIAM/ASA J. Uncertain. Quantif. 5, 30–62 (2017)
Vrettas, M., Cornford, D., Opper, M.: Estimating parameters in stochastic systems: a variational bayesian approach. Phys. D 240, 1877–1900 (2011)
Whiting, R.: Modeling bacterial survival in unfavorable environments. J. Ind. Microbiol. 12, 240–246 (1993)
Whiting, R., Sackitey, S., Calderone, S., Morely, K., Phillips, J.: Model for the survival of Staphylococcus aureus in nongrowth environments. Int. J. Food Microbiol. 31, 231–243 (1996)
Ye, J., Rey, D., Kadakia, N., Eldridge, M., Morone, U., Rozdeba, P., Abarbanel, H., Quinn, J.: Systematic variational method for statistical nonlinear state and parameter estimation. Phys. Rev. E 92, 052901 (2015)
Zwietering, M., Jongenburger, I., Rombouts, F., Van’t Riet, K.: Modeling of the bacterial growth curve. Appl. Environ. Microbiol. 56, 1875–1881 (1990)
Acknowledgements
The authors gratefully acknowledge support from US Army Research Office Contract W911NF-14-C-0151.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Charles R. Doering.
Appendix A: Gradient Computation of the Log-joint Distribution \(\log p(\mathbf {y}, \varvec{\theta })\)
Appendix A: Gradient Computation of the Log-joint Distribution \(\log p(\mathbf {y}, \varvec{\theta })\)
In order to perform gradient-based optimization of the ELBO approximation \(\mathcal {F}_2[q]\) with respect to \(\{\varvec{\mu }\}_i, \{\varvec{\Sigma }_i\}_i, i= 1,\dots , L\), we need to compute its gradient vector with entries
where \(\zeta = (\varvec{\mu }_i)_j, (\varvec{\Sigma }_i)_{jk}\), for \(i= 1,\dots ,L, j,k = 1,\dots , d\) and \(r = 0,2\). Below we provide the details in computing the gradient of \(\mathcal {L}_r[q], r=0,2\).
1.1 A.1: Gradient of \(\mathcal {L}_r[q]\)
For convenience, we set \(J(\varvec{\theta }) := \log p(\mathbf {y}, \varvec{\theta })\). Then for \(r=0\), the derivatives of \(\mathcal {L}_0[q]\) with respect to \(\zeta = (\varvec{\mu }_i)_j\) are
and with respect to \(\zeta = (\varvec{\Sigma })_{jk}\) are
For \(r = 2\) and \(\zeta = (\varvec{\Sigma }_i)_{jk}\), we get
As mentioned above, the derivatives of \(\mathcal {L}_2[q]\) with respect to \((\varvec{\mu }_i)_j\) are not used in our optimization scheme and therefore are not computed here.
1.2 A.2: Derivatives of \(J(\varvec{\theta })\)
First we rewrite \(\varvec{\theta }= (\varvec{\xi }, \omega )\) and expand
Throughout our numerical examples, we work with an isotropic Gaussian likelihood (\(\varvec{\epsilon }\sim \mathcal {N}(\mathbf {0}, \sigma \mathbf {I}_N)\)); therefore, we set
and using the chain rule, we have
In the above expressions, it becomes clear that the Jacobian and Hessian of the forward model \(\mathcal {G}(\varvec{\xi })\) need to be computed. As mentioned in our application, the covariance matrices of the Gaussian mixtures components are taken to be diagonal which implies that only the diagonal elements of the Hessian of \(\mathcal {G}(\varvec{\xi })\) are necessary.
1.3 A.3: Log-Likelihood Derivatives
The derivatives of the log-likelihood function required for the expression in the previous subsection are given as follows:
1.4 A.4: Derivatives of the Quasi-chemical Model
For the sake of generality and due to the presence of a nonlinear term in the quasi-chemical model, we present the general derivation of the system of ODEs satisfied by the derivatives of a solution \(\mathbf {u}(t; \varvec{\xi })\) of the QCM with respect to its parameters. Assume \(\mathbf {u}(t;\varvec{\xi })\) satisfies
where \(\varvec{\xi }\in \mathbb {R}^4\) are parameters and the initial condition is fixed and independent of \(\varvec{\xi }\). By simply differentiating the above system of equations, one can derive the following initial value problem satisfied by \(v_{ij} = \partial u_i/\partial \xi _j\):
Similarly, for the second derivatives \(w_{ijk} = \partial ^2 u_i / (\partial \xi _j\partial \xi _k)\) we get
In practice, during numerical implementation one need to first solve (A.17) and then solve (A.19) using the solution of the former as forcing. At last, (A.21) can be solved by using both the QCM solution and its gradient as forcing.
Rights and permissions
About this article
Cite this article
Tsilifis, P., Browning, W.J., Wood, T.E. et al. The Stochastic Quasi-chemical Model for Bacterial Growth: Variational Bayesian Parameter Update. J Nonlinear Sci 28, 371–393 (2018). https://doi.org/10.1007/s00332-017-9411-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00332-017-9411-4