SOLVING STOCHASTIC CHEMICAL KINETICS BY METROPOLIS-HASTINGS SAMPLING

Azam Mooasvi; Paul Tranquilli; Adrian Sandu

doi:10.11948/2016025

2016 Volume 6 Issue 2

Article Contents

Article navigation > Journal of Applied Analysis & Computation > 2016 > 6(2): 322-335

Next Article Previous Article

Azam Mooasvi, Paul Tranquilli, Adrian Sandu. SOLVING STOCHASTIC CHEMICAL KINETICS BY METROPOLIS-HASTINGS SAMPLING[J]. Journal of Applied Analysis & Computation, 2016, 6(2): 322-335. doi: 10.11948/2016025

Citation:

Azam Mooasvi, Paul Tranquilli, Adrian Sandu. SOLVING STOCHASTIC CHEMICAL KINETICS BY METROPOLIS-HASTINGS SAMPLING[J]. Journal of Applied Analysis & Computation, 2016, 6(2): 322-335. doi: 10.11948/2016025

SOLVING STOCHASTIC CHEMICAL KINETICS BY METROPOLIS-HASTINGS SAMPLING

Computational Science Laboratory, Department of Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA 24060. Phone:(540)231-2193, Fax:(540)231-6075

Abstract

Abstract

This study considers using Metropolis-Hastings algorithm for stochastic simulation of chemical reactions. The proposed method uses SSA (Stochastic Simulation Algorithm) distribution which is a standard method for solving well-stirred chemically reacting systems as a desired distribution. A new numerical solvers based on exponential form of exact and approximate solutions of CME (Chemical Master Equation) is employed for obtaining target and proposal distributions in Metropolis-Hastings algorithm to accelerate the accuracy of the tau-leap method. Samples generated by this technique have the same distribution as SSA and the histogram of samples show it's convergence to SSA.
- Metropolis-Hastings /
- SSA /
- CME /
- tau-leap
MSC: 92Bxx;49Mxx;62xx

FullText(HTML)

References

[1]	T. Ahn and A. Sandu, Implicit simulation methods for stochastic chemical kinetics, (2013). Http://arxiv.org/abs/1303.3614. Google Scholar
[2]	A. Altaleb and D. Chauveau, Bayesian analysis of the logit model and comparison of two metropolis-hastings strategies., Comput. Stat. Data Anal, 39(2002)(2), 137-152. Google Scholar
[3]	Y. Cao, R. Petzold, M.Rathinam and D. Gillespie, The numerical stability of leaping methods for stochastic simulation of chemically reacting systems., Journal of Chemical Physics, 121(2004)(24), 12169-12178. Google Scholar
[4]	A. Carpenter, A. Ruttan and R. Varga, Extended numerical computations on the 1/9 conjecture in rational approximation theory., Rational approximation and interpolation in lecture notes in mathematics, Springer., (1984)(1105), 383-411. Google Scholar
[5]	S. Chib and E. Greenberg, Understanding the metropolis-hastings algorithm., The American Statistician., 49(1995)(4), 327-335. Google Scholar
[6]	D. Gillespie, Exact stochastic simulation of coupled chemical reactions, Journal of Chemical Physics, 81(1977)(25), 2340-2361. Google Scholar
[7]	D. Gillespie, Approximate accelerated stochastic simulation of chemically reacting systems, Journal of Chemical Physics, 115(2001)(4), 1716-1733. Google Scholar
[8]	D. Gillespie and L. Petzold, Improved leap-size selection for accelerated stochastic simulation, Journal of Chemical Physics, 119(2003)(16), 8229-8234. Google Scholar
[9]	W. Hastings, Monte carlo sampling methods using markov chains and their applications, Biometrika, 57(1970). Google Scholar
[10]	N. J. Higham, The scaling and squaring method for the matrix exponential revisited., SIAM review., 51(2009)(4), 747-764. Google Scholar
[11]	D. Hitchcock, A history of the metropolis-hastings algorithm, The American Statistician, 75(2003)(4), 254-257. Google Scholar
[12]	C. Kastner, A. Braumann, L. Man et al., Bayesian parameter estimation for a jet-milling model using metropolishastings and wanglandau sampling, Chemical Engineering Science., 99(2013)(4), 244-257. Google Scholar
[13]	T. Kurtz, The relationship between stochastic and deterministic models for chemical reactions., Journal of Chemical Physics, 57(1972)(7), 2976-2978. Google Scholar
[14]	N. Metropolis, A. Rosenbluth, M. Rosenbluth et al., Equations of state calculations by fast computing machine, Journal of Chemical Physics, (1953)(21), 1087-1091. Google Scholar
[15]	C. Moler and C. Loan, Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later, SIAM Review, 45(2003)(1). Google Scholar
[16]	A. Mooasvi and A. Sandu, Approximate exponential algorithms to solve the chemical master equation, Mathematical Modelling and Analysis, 20(2015)(3), 382-395. Google Scholar
[17]	M. Pusa, Rational approximations to the matrix exponential in burn up calculations., Nuclear science and engineering., 169(2010)(2), 155-167. Google Scholar
[18]	M. Rathinam, L. Petzold, Y.Cao and D.Gillespie, Stiffness in stochastic chemically reacting systems:The implicit tau-leaping method, Journal of Chemical Physics, 119(2003), 784-12. Google Scholar
[19]	G. O. Roberts and A. F. M. Smith, Simple conditions for the convergence of the gibbs sampler and metropolis-hastings algorithms., Stochastic Processes and their Applications, 49(1994)(2), 207-216. Google Scholar
[20]	A. Sandu, A new look at chemical master equation, Numerical Algorithms, 65(2013)(3), 485-498. Google Scholar
[21]	R. Sidje, Expokit:A software package for computing matrix exponentials., ACM Trans. Software., 24(1998)(1), 130-156. Google Scholar