×

Bayesian model calibration and uncertainty quantification for an HIV model using adaptive Metropolis algorithms. (English) Zbl 1390.92086

Summary: In this paper, we discuss Bayesian model calibration and use adaptive Metropolis algorithms to construct densities for input parameters in a previously developed HIV model. To quantify the uncertainty in the parameters, we employ two MCMC algorithms: delayed rejection adaptive metropolis (DRAM) and differential evolution adaptive metropolis (DREAM). The densities obtained using these methods are compared to those obtained through direct evaluation of Bayes formula. We also employ uncertainties in input parameters and observation errors to construct prediction intervals for a model response. We verify the accuracy of the Metropolis algorithms by comparing chains, densities and correlations obtained using DRAM, DREAM and direct numerical evaluation of Bayes’ formula. We also perform similar analysis for credible and prediction intervals for responses.

MSC:

92C60 Medical epidemiology
62F15 Bayesian inference
62P10 Applications of statistics to biology and medical sciences; meta analysis
92C50 Medical applications (general)

Software:

energy; MCSim; MCMC
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Gutenkunst RN, Casey FP, Waterfall JJ, et al. Extracting falsifiable predictions from sloppy models. Ann N Y Acad Sci. 2007;1115:203-211.
[2] Adams BM, Banks HT, Davidian M, et al. HIV dynamics: modeling, data analysis, and optimal treatment protocols. J Comput Appl Math. 2005;184:10-49. · Zbl 1075.92030
[3] Adams BM, Banks HT, Davidian M, et al. Model fitting and prediction with HIV treatment interruption data. Bull Math Biol. 2007;69(2):563-584. · Zbl 1139.92304
[4] Banks HT, Davidian M, Hu S, et al. Modeling HIV immune response and validation with clinical data. J Biol Dyn. 2008;2:357-385. · Zbl 1315.92050
[5] Ferguson NM, deWolf F, Ghani AC, et al. Antigen-driven CD41 T cell and HIV-1 dynamics: residual viral replication under highly active antiretroviral therapy. Proc Nat Acad Sci USA. 1999;96(26):15167-16172.
[6] Mitter JE, Markowitz M, Ho DD, Perelson AS. Improved estimates for HIV-1 clearance rate and intracellular delay. AIDS. 1999;13(11):1415-1417.
[7] Perelson AS, Essunger P, Cao Y, Vesanen M, et al. Decay characteristics of HIV-1-infected compartments during combination therapy. Nature. 1996;378:188-191.
[8] Ramratnam B, Bonhoeffer S, Binley J, Hurley A, et al. Rapid production and clearance of HIV-1 and hepatitis C virus assessed by large volume plasma apheresis. Lancet. 1999;354:1782-1785.
[9] Callaway DS, Perelson AS. HIV-1 infection and low steady state viral loads. Bull Math Biol. 2002;64:29-64. · Zbl 1334.92227
[10] Haario H, Laine M, Mira A, et al. DRAM: efficient adaptive MCMC. Stat Comput. 2006;16(4):339-354.
[11] Vrugt JA, ter Braak CJF, Clark MP, et al. Treatment of input uncertainty in hydrological modeling: doing hydrology backward with Markov chain Monte Carlo simulation. Water Res Resour. 2008;44(12):W00B09. DOI:10.1029/2007WR006720
[12] Vrugt JA, terBraak CJF, Gupta HV, et al. Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling? Stoch Environ Res Risk Assess. 2008;23(7):1011-1026.
[13] Smith RC. Uncertainty quantification: Theory, implementation, and applications. Philadelphia (PA): SIAM; 2014. · Zbl 1284.65019
[14] Huang Y, Liu D, Wu H. Hierarchical Bayesian methods for estimation of parameters in a longitudinal HIV dynamic system. Biometrics. 2006;62:413-423. · Zbl 1097.62128
[15] Gelman A, Bois FY, Jian J. Physiological pharmacokinetic analysis using population modeling and informative prior distributions. J Am Stat Assoc. 1996;91:1400-1414. · Zbl 0882.62103
[16] Campbell D, Steele RJ. Smooth functional tempering for nonlinear differential equation models. Stat Comput. 2001;22(2):429-433. DOI:10.1007/s11222-011-9234-3 · Zbl 1322.62011
[17] Calderhead B, Girolami M, Lawrence ND. Accelerating Bayesian inference over nonlinear differential equations with Gaussian processes. Adv Neural Inform Process Syst. 2009;21:217-224.
[18] Siekman I, Wagner LE II, Yule D, et al. MCMC Estimation of Markov Models for Ion Channels. Biophys J. 2001;100:1919-1929.
[19] Grenander U, Miller M. Representations of knowledge in complex systems. J R Stat Soc Ser B. 1994;56:549-603. · Zbl 0814.62009
[20] Bois FY. GNU MCSim: Bayesian statistical inference for SBML-coded systems biology models. Bioinformatics. 2009;25(11):1453-1454.
[21] Laine M. Adaptive Markov Chain Monte Carlo methods. Finnish centre of excellence in inverse problems research. Available from: https://wiki.helsinki.fi/display/inverse/Adaptive+MCMC.
[22] Laine M. MCMC Toolbox for Matlab. Available from: http://helios.fmi.fi/lainema/mcmc/.
[23] Brooks SP, Roberts GO. Convergence assessment techniques for Markov chain Monte Carlo. Stat Comput. 1998;8(4):319-335.
[24] Vrugt JA, ter Braak CJF, Diks CFH, et al. Accelerating Markov chain Monte Carlo simulation by differential evolution with self-adaptive randomized subspace samplings. Int J Nonlinear Sci Numer Simul. 2009;10(3):273-290.
[25] Gelman A, Rubin DB. Inference from iterative simulation using multiple sequences. Stat Sci. 1992;7(4):457-472. · Zbl 1386.65060
[26] Vrugt JA. Software: matlab packages. University of California Irvine. Available from: http://faculty.sites.uci.edu/jasper/sample/.
[27] Székely GJ, Rizzo ML. Testing for equal distributions in high dimensions. InterStat. 2004.
[28] Székely GJ, Rizzo ML. Energy statistics: a class of statistics based on distances. J Stat Plan Inference. 2013;143:1249-1272. · Zbl 1278.62072
[29] Rizzo ML, Székely GJ. DISCO analysis: a nonparametric extension of analysis of variance. Ann Appl Stat. 2010;4(2):1034-1055. · Zbl 1194.62054
[30] Raue A, Kreutz C, Maiwald T, et al. Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood. Bioinformatics. 2009;25:1923-1929.
[31] Haario H, Kalachev L, Laine M. Reduced models of algae growth. Bull Math Biol. 2009;71(7):1626-1648. · Zbl 1173.92033
[32] Wentworth MT, Smith RC, Banks HT. Parameter selection and verification techniques based on global sensitivity analysis illustrated for an HIV model. SIAM/ASA J Uncert Quant. 2016;4(1):266-297. · Zbl 1341.92080
[33] Bang Y, Abdel-Khalik HS, Hite JM. Hybrid reduced order modeling applied to nonlinear models. Int J Numer Methods Eng. 2012;91:929-949. · Zbl 07694396
[34] Constantine PG. Active subspaces: emerging ideas for dimension reduction in parameter studies. Philadelphia (PA): SIAM Spotlights; 2015. · Zbl 1431.65001
[35] Constantine PG, Dow E, Wang Q. Active subspace methods in theory and practice: applications to kriging surfaces. SIAM J Sci Comput. 2014;36(4):A1500-A1524. · Zbl 1464.62049
[36] Barenco M, Tomescu D, Brewer D, et al. Ranked prediction of p53 targets using hidden variable dynamic modeling. Genome Biol. 2006;7(3):R25.
[37] Rogers S, Khanin R, Girolami M. Bayesian model-based inference of transcription factor activity. BMC Bioinform. 2007;8:S2.
[38] Klinke DJ. An empirical Bayesian approach for model-based inference of cellular signaling networks. BMC Bioinform. 2009;10:371.
[39] Lu D, Ye M, Hill MC, et al. A computer program for uncertainty analysis integrating regression and Bayesian methods. Environ Model Soft. 2014;60:45-56.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.