Home > Research > Publications & Outputs > Bayesian inference for hybrid discrete-continuo...

Research

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Bayesian inference for hybrid discrete-continuous stochastic kinetic models

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Bayesian inference for hybrid discrete-continuous stochastic kinetic models. / Sherlock, Christopher; Golightly, Andrew; Gillespie, Colin.
In: Inverse Problems, Vol. 30, No. 11, 114005, 11.2014.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Sherlock, C, Golightly, A & Gillespie, C 2014, 'Bayesian inference for hybrid discrete-continuous stochastic kinetic models', Inverse Problems, vol. 30, no. 11, 114005. https://doi.org/10.1088/0266-5611/30/11/114005

APA

Sherlock, C., Golightly, A., & Gillespie, C. (2014). Bayesian inference for hybrid discrete-continuous stochastic kinetic models. Inverse Problems, 30(11), Article 114005. https://doi.org/10.1088/0266-5611/30/11/114005

Vancouver

Sherlock C, Golightly A, Gillespie C. Bayesian inference for hybrid discrete-continuous stochastic kinetic models. Inverse Problems. 2014 Nov;30(11):114005. Epub 2014 Oct 28. doi: 10.1088/0266-5611/30/11/114005

Author

Sherlock, Christopher ; Golightly, Andrew ; Gillespie, Colin. / Bayesian inference for hybrid discrete-continuous stochastic kinetic models. In: Inverse Problems. 2014 ; Vol. 30, No. 11.

Bibtex

@article{2430bcc590984ad3ae4064a8fb4a8102,
title = "Bayesian inference for hybrid discrete-continuous stochastic kinetic models",
abstract = "We consider the problem of efficiently performing simulation and inference for stochastic kinetic models. Whilst it is possible to work directly with the resulting Markov jump process, computational cost can be prohibitive for networks of realistic size and complexity. In this paper, we consider an inference scheme based on a novel hybrid simulator that classifies reactions as either {"}fast{"} or {"}slow{"} with fast reactions evolving as a continuous Markov process whilst the remaining slow reaction occurrences are modelled through a Markov jump process with time dependent hazards. A linear noise approximation (LNA) of fast reaction dynamics is employed and slow reaction events are captured by exploiting the ability to solve the stochastic differential equation driving the LNA. This simulation procedure is used as a proposal mechanism inside a particle MCMC scheme, thus allowing Bayesian inference for the model parameters. We apply the scheme to a simple application and compare the output with an existing hybrid approach and also a scheme for performing inference for the underlying discrete stochastic model.",
author = "Christopher Sherlock and Andrew Golightly and Colin Gillespie",
year = "2014",
month = nov,
doi = "10.1088/0266-5611/30/11/114005",
language = "English",
volume = "30",
journal = "Inverse Problems",
issn = "0266-5611",
publisher = "IOP Publishing Ltd.",
number = "11",

}

RIS

TY - JOUR

T1 - Bayesian inference for hybrid discrete-continuous stochastic kinetic models

AU - Sherlock, Christopher

AU - Golightly, Andrew

AU - Gillespie, Colin

PY - 2014/11

Y1 - 2014/11

N2 - We consider the problem of efficiently performing simulation and inference for stochastic kinetic models. Whilst it is possible to work directly with the resulting Markov jump process, computational cost can be prohibitive for networks of realistic size and complexity. In this paper, we consider an inference scheme based on a novel hybrid simulator that classifies reactions as either "fast" or "slow" with fast reactions evolving as a continuous Markov process whilst the remaining slow reaction occurrences are modelled through a Markov jump process with time dependent hazards. A linear noise approximation (LNA) of fast reaction dynamics is employed and slow reaction events are captured by exploiting the ability to solve the stochastic differential equation driving the LNA. This simulation procedure is used as a proposal mechanism inside a particle MCMC scheme, thus allowing Bayesian inference for the model parameters. We apply the scheme to a simple application and compare the output with an existing hybrid approach and also a scheme for performing inference for the underlying discrete stochastic model.

AB - We consider the problem of efficiently performing simulation and inference for stochastic kinetic models. Whilst it is possible to work directly with the resulting Markov jump process, computational cost can be prohibitive for networks of realistic size and complexity. In this paper, we consider an inference scheme based on a novel hybrid simulator that classifies reactions as either "fast" or "slow" with fast reactions evolving as a continuous Markov process whilst the remaining slow reaction occurrences are modelled through a Markov jump process with time dependent hazards. A linear noise approximation (LNA) of fast reaction dynamics is employed and slow reaction events are captured by exploiting the ability to solve the stochastic differential equation driving the LNA. This simulation procedure is used as a proposal mechanism inside a particle MCMC scheme, thus allowing Bayesian inference for the model parameters. We apply the scheme to a simple application and compare the output with an existing hybrid approach and also a scheme for performing inference for the underlying discrete stochastic model.

U2 - 10.1088/0266-5611/30/11/114005

DO - 10.1088/0266-5611/30/11/114005

M3 - Journal article

VL - 30

JO - Inverse Problems

JF - Inverse Problems

SN - 0266-5611

IS - 11

M1 - 114005

ER -