Abstract
Approximate Bayesian computation (ABC) methods can be used to evaluate posterior distributions without having to calculate likelihoods. In this paper, we discuss and apply an ABC method based on sequential Monte Carlo (SMC) to estimate parameters of dynamical models. We show that ABC SMC provides information about the inferability of parameters and model sensitivity to changes in parameters, and tends to perform better than other ABC approaches. The algorithm is applied to several well-known biological systems, for which parameters and their credible intervals are inferred. Moreover, we develop ABC SMC as a tool for model selection; given a range of different mathematical descriptions, ABC SMC is able to choose the best model using the standard Bayesian model selection apparatus.
Footnotes
References
Anderson R.M& May R.M Infectious diseases of humans: dynamics and control. 1991New York, NY:Oxford University Press. Google ScholarBaker C, Bocharov G, Ford J, Lumb P.S.J, Norton C.A.H, Paul T, Junt P& Krebs B . 2005Ludewig computational approaches to parameter estimation and model selection in immunology. J. Comput. Appl. Math. 184, 50–76.doi:10.1016/j.cam.2005.02.003. . Crossref, ISI, Google ScholarBanks H, Grove S, Hu S& Ma Y . 2005A hierarchical Bayesian approach for parameter estimation in HIV models. Inverse Problems. 21, 1803–1822.doi:10.1088/0266-5611/21/6/001. . Crossref, ISI, Google ScholarBattogtokh D, Asch D.K, Case M.E, Arnold J& Schuttler H.-B . 2002An ensemble method for identifying regulatory circuits with special reference to the qa gene cluster of Neurospora crassa. Proc. Natl Acad. Sci. USA. 99, 16 904–16 909.doi:10.1073/pnas.262658899. . Crossref, ISI, Google Scholar- Beaumont, M. 2008aSimulations, genetics and human prehistory (eds S. Matsumura, P. Forester & C. Renfrew). McDonald Institute Monographs, University of Cambridge. Google Scholar
- Beaumont, M. A. 2008b A note on the ABC-PRC algorithm of Sissons et al. (2007). (http://arxiv.org/abs/0805.3079v1). Google Scholar
Beaumont M.A, Zhang W& Balding D.J . 2002Approximate Bayesian computation in population genetics. Genetics. 162, 2025–2035. PubMed, ISI, Google ScholarBortz D.M& Nelson P.W . 2006Model selection and mixed-effects modeling of HIV infection dynamics. Bull. Math. Biol. 68, 2005–2025.doi:10.1007/s11538-006-9084-x. . Crossref, PubMed, ISI, Google ScholarBrown K.S& Sethna J.P . 2003Statistical mechanical approaches to models with many poorly known parameters. Phys. Rev. E. 68, 021 904doi:10.1103/PhysRevE.68.021904. . Crossref, ISI, Google ScholarDel Moral P, Doucet A& Jasra A . 2006Sequential Monte Carlo samplers. J. R. Stat. Soc. B. 68, 411–432.doi:10.1111/j.1467-9868.2006.00553.x. . Crossref, Google ScholarElowitz M.B& Leibler S . 2000A synthetic oscillatory network of transcriptional regulators. Nature. 403, 335–338.doi:10.1038/35002125. . Crossref, PubMed, ISI, Google ScholarEnright W& Hu M . 1995Interpolating Runge–Kutta methods for vanishing delay differential equations. Computing. 55, 223–236.doi:10.1007/BF02238433. . Crossref, ISI, Google ScholarFagundes N, Ray N, Beaumont M, Neuenschwander S, Salzano F.M, Bonatto S.L& Excoffier L . 2007Statistical evaluation of alternative models of human evolution. Proc. Natl Acad. Sci. USA. 104, 17 614–17 619.doi:10.1073/pnas.0708280104. . Crossref, ISI, Google ScholarFields B.N, Knipe D.M& Howley P.M Fundamental virology. 1996Philadelphia, PA:Lippincott Williams & Wilkins. Google ScholarGalassi M GNU scientific library reference manual. 2nd edn.2003Cambridge, UK:Cambridge University Press. Google ScholarGillespie D . 1977Exact stochastic simulation of coupled chemical reactions. J. Phys. Chem. 81, 2340–2361.doi:10.1021/j100540a008. . Crossref, ISI, Google ScholarGolightly A& Wilkinson D . 2005Bayesian inference for stochastic kinetic models using a diffusion approximation. Biometrics. 61, 781–788.doi:10.1111/j.1541-0420.2005.00345.x. . Crossref, PubMed, ISI, Google ScholarGolightly A& Wilkinson D . 2006Bayesian sequential inference for stochastic kinetic biochemical network models. J. Comput. Biol. 13, 838–851.doi:10.1089/cmb.2006.13.838. . Crossref, PubMed, ISI, Google ScholarGutenkunst R, Waterfall J, Casey F, Brown K, Myers C& Sethna J . 2007Universally sloppy parameter sensitivities in systems biology models. PLoS Comput. Biol. 3, e189doi:10.1371/journal.pcbi.0030189. . Crossref, ISI, Google ScholarHammond B.J& Tyrrell D.A . 1971A mathematical model of common-cold epidemics on Tristan da Cunha. J. Hyg. 69, 423–433. Crossref, PubMed, Google ScholarHoeting J, Madigan D, Raftery A& Volinsky C . 1999Bayesian model averaging: a tutorial. Statist. Sci. 14, 382–401.doi:10.1214/ss/1009212519. . ISI, Google ScholarHorbelt W, Timmer J& Voss H . 2002Parameter estimation in nonlinear delayed feedback systems from noisy data. Phys. Lett. A. 299, 513–521.doi:10.1016/S0375-9601(02)00748-X. . Crossref, ISI, Google ScholarHuang Y, Liu D& Wu H . 2006Hierarchical Bayesian methods for estimation of parameters in a longitudinal HIV dynamic system. Biometrics. 62, 413–423.doi:10.1111/j.1541-0420.2005.00447.x. . Crossref, PubMed, ISI, Google ScholarJohannes M& Polson N MCMC methods for continuous-time financial econometrics. Handbook of financial econometrics, Ait-Sahalia Y& Hansen L . 2005Amsterdam, The Netherlands:Elsevier Science Ltd. Google ScholarKass R& Raftery A . 1995Bayes factors. J. Am. Stat. Assoc. 90, 773–795.doi:10.2307/2291091. . Crossref, ISI, Google ScholarKirkpatrick S, Gelatt C& Vecchi M . 1983Optimization by simulated annealing. Science. 220, 671–680.doi:10.1126/science.220.4598.671. . Crossref, PubMed, ISI, Google ScholarLiu J.S& Chen R . 1998Sequential Monte Carlo methods for dynamic systems. J. Am. Stat. Assoc. 93, 1032–1044.doi:10.2307/2669847. . Crossref, ISI, Google ScholarMarjoram P, Molitor J, Plagnol V& Tavare S . 2003Markov chain Monte Carlo without likelihoods. Proc. Natl Acad. Sci. USA. 100, 15 324–15 328.doi:10.1073/pnas.0306899100. . Crossref, ISI, Google ScholarMendes P& Kell D . 1998Non-linear optimization of biochemical pathways: applications to metabolic engineering and parameter estimation. Bioinformatics. 14, 869–883.doi:10.1093/bioinformatics/14.10.869. . Crossref, PubMed, ISI, Google ScholarMoles C, Mendes P& Banga J . 2003Parameter estimation in biochemical pathways: a comparison of global optimization methods. Genome Res. 13, 2467–2474.doi:10.1101/gr.1262503. . Crossref, PubMed, ISI, Google ScholarMuller T.G, Faller D, Timmer J, Swameye I, Sandra O& Klingmüller U . 2004Tests for cycling in a signalling pathway. J. R. Stat. Soc. Ser. C. 53, 557doi:10.1111/j.1467-9876.2004.05148.x. . Crossref, ISI, Google ScholarPaul C . 1992Developing a delay differential equation solver. Appl. Numer. Math. 9, 403–414.doi:10.1016/0168-9274(92)90030-H. . Crossref, ISI, Google ScholarPress W.H, Teukolsky S.A, Vetterling W.T& Flannery B.P Numerical recipes in C: the art of scientific computing. 2nd edn.1992Cambridge, UK:Cambridge University Press. Google ScholarPritchard J, Seielstad M.T, Perez-Lezaun A& Feldman M.W . 1999Population growth of human Y chromosomes: a study of Y chromosome microsatellites. Mol. Biol. Evol. 16, 1791–1798. Crossref, PubMed, ISI, Google ScholarPutter H, Heisterkamp S.H, Lange J.M.A& de Wolf F . 2002A Bayesian approach to parameter estimation in HIV dynamical models. Stat. Med. 21, 2199–2214.doi:10.1002/sim.1211. . Crossref, PubMed, ISI, Google ScholarReinker S, Altman R& Timmer J . 2006Parameter estimation in stochastic biochemical reactions. IEE Proc.Syst. Biol. 153, 168–178.doi:10.1049/ip-syb:20050105. . Crossref, ISI, Google ScholarRobert C.P& Casella G Monte Carlo statistical methods. 2nd edn.2004New York, NY:Springer. Google ScholarSaltelli A, Ratto M, Andres T, Campolongo F, Cariboni J, Gatelli D, Saisana M& Tarantola S Global sensitivity analysis: the primer. 2008New York, NY:Wiley. Google ScholarSanchez M& Blower S . 1997Uncertainty and sensitivity analysis of the basic reproductive rate: tuberculosis as an example. Am. J. Epidemiol. 145, 1127–1137. Crossref, PubMed, ISI, Google ScholarShibli M, Gooch S, Lewis H.E& Tyrrell D.A . 1971Common colds on Tristan da Cunha. J. Hyg. 69, 255. Crossref, PubMed, Google ScholarSisson S.A, Fan Y& Tanaka M.M . 2007Sequential Monte Carlo without likelihoods. Proc. Natl Acad. Sci. USA. 104, 1760–1765.doi:10.1073/pnas.0607208104. . Crossref, PubMed, ISI, Google ScholarStumpf M& Thorne T . 2006Multi-model inference of network properties from incomplete data. J. Integr. Bioinform. 3, 32. Crossref, Google ScholarTimmer J& Muller T . 2004Modeling the nonlinear dynamics of cellular signal transduction. Int. J. Bifurcat. Chaos. 14, 2069–2079.doi:10.1142/S0218127404010461. . Crossref, ISI, Google Scholarvan Kampen N.G Stochastic processes in physics and chemistry. 3rd edn.2007Amsterdam, The Netherlands:North-Holland. Google ScholarVolterra V . 1926Variazioni e fluttuazioni del numero d'individui in specie animali conviventi. Mem. R. Acad. Naz. dei Lincei. 2, 31–113. Google ScholarVyshemirsky V& Girolami M.A . 2008Bayesian ranking of biochemical system models. Bioinformatics. 24, 833–839.doi:10.1093/bioinformatics/btm607. . Crossref, PubMed, ISI, Google ScholarWilkinson D.J Stochastic modelling for systems biology. 2006London, UK:Chapman & Hall/CRC. Google Scholar- Wilkinson, R. D. 2007 Bayesian inference of primate divergence times. PhD thesis, University of Cambridge. Google Scholar
- Zucknick, M. 2004 Approximate Bayesian computation in population genetics and genomics. MSc thesis, Imperial College London. Google Scholar
S2.2 on page 3 is now present in its correct form.
MS2.2 on page 4 is now present in its correct form.
S2.2 on page 13 is now present in its correct form.17 July 2008


