GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation

Evgeny Tankhilevich, Jonathan Ish-Horowicz, Tara Hameed, Elisabeth Roesch, Istvan Kleijn, Michael PH Stumpf, Fei He

Research output: Contribution to journal › Article

Abstract

Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often limits ABC to models that are relatively quick to simulate in practice. We here present a Julia package, GpABC, that implements parameter inference and model selection for deterministic or stochastic models using i) standard rejection ABC or ABC-SMC, or ii) ABC with Gaussian process emulation. The latter significantly reduces the computational cost.
Original languageEnglish
Pages (from-to)769299
Number of pages1
JournalbioRxiv
DOIs
Publication statusPublished - 18 Sep 2019

Fingerprint

Biological systems
Stochastic models
Costs
Systems Biology

Cite this

Tankhilevich, E., Ish-Horowicz, J., Hameed, T., Roesch, E., Kleijn, I., Stumpf, M. PH., & He, F. (2019). GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation. bioRxiv, 769299. https://doi.org/10.1101/769299

GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation. / Tankhilevich, Evgeny; Ish-Horowicz, Jonathan; Hameed, Tara; Roesch, Elisabeth; Kleijn, Istvan; Stumpf, Michael PH; He, Fei.

In: bioRxiv, 18.09.2019, p. 769299.

Research output: Contribution to journal › Article

Tankhilevich, E, Ish-Horowicz, J, Hameed, T, Roesch, E, Kleijn, I, Stumpf, MPH & He, F 2019, 'GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation' bioRxiv, pp. 769299. https://doi.org/10.1101/769299
Tankhilevich E, Ish-Horowicz J, Hameed T, Roesch E, Kleijn I, Stumpf MPH et al. GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation. bioRxiv. 2019 Sep 18;769299. https://doi.org/10.1101/769299
Tankhilevich, Evgeny ; Ish-Horowicz, Jonathan ; Hameed, Tara ; Roesch, Elisabeth ; Kleijn, Istvan ; Stumpf, Michael PH ; He, Fei. / GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation. In: bioRxiv. 2019 ; pp. 769299.
@article{9aa3fdcf55694581b5368fe35aaa3239,
title = "GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation",
abstract = "Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often limits ABC to models that are relatively quick to simulate in practice. We here present a Julia package, GpABC, that implements parameter inference and model selection for deterministic or stochastic models using i) standard rejection ABC or ABC-SMC, or ii) ABC with Gaussian process emulation. The latter significantly reduces the computational cost.",
author = "Evgeny Tankhilevich and Jonathan Ish-Horowicz and Tara Hameed and Elisabeth Roesch and Istvan Kleijn and Stumpf, {Michael PH} and Fei He",
year = "2019",
month = "9",
day = "18",
doi = "10.1101/769299",
language = "English",
pages = "769299",
journal = "bioRxiv",
publisher = "Cold Spring Harbor Laboratory Press",

}

TY - JOUR

T1 - GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation

AU - Tankhilevich, Evgeny

AU - Ish-Horowicz, Jonathan

AU - Hameed, Tara

AU - Roesch, Elisabeth

AU - Kleijn, Istvan

AU - Stumpf, Michael PH

AU - He, Fei

PY - 2019/9/18

Y1 - 2019/9/18

N2 - Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often limits ABC to models that are relatively quick to simulate in practice. We here present a Julia package, GpABC, that implements parameter inference and model selection for deterministic or stochastic models using i) standard rejection ABC or ABC-SMC, or ii) ABC with Gaussian process emulation. The latter significantly reduces the computational cost.

AB - Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often limits ABC to models that are relatively quick to simulate in practice. We here present a Julia package, GpABC, that implements parameter inference and model selection for deterministic or stochastic models using i) standard rejection ABC or ABC-SMC, or ii) ABC with Gaussian process emulation. The latter significantly reduces the computational cost.

U2 - 10.1101/769299

DO - 10.1101/769299

M3 - Article

SP - 769299

JO - bioRxiv

JF - bioRxiv

ER -

Access to Document