Maximin and bayesian robust experimental design for measurement set selection in modelling biochemical regulatory systems

Fei He, Martin Brown, Hong Yue

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Experimental design is important in system identification, especially when the models are complex and the measurement data are sparse and noisy, as often occurs in modelling of biochemical regulatory networks. The quality of conventional optimal experimental design largely depends on the accuracy of model parameter estimation, which is often either unavailable or poorly estimated at the stage of design. Robust experimental design (RED) algorithms have thus been proposed when model parametric uncertainties need to be addressed during the design process. In this paper, two robust design strategies are investigated and the comparative study has been made on signal pathway models. The first method is a maximin experimental design approach which is a worst-case design strategy, and the second method is the Bayesian experimental design that 'takes an average' of the parametric uncertainty effects. The limitations of the maximin design which describes the structural uncertainty using a local Taylor representation are quantitatively evaluated. To better quantitatively assess the differences between the maximin and the Bayesian REDs, a concept of effective design parameters is proposed, from which the advantages of the Bayesian design is demonstrated especially in the case of large model uncertainties.

Original languageEnglish
Pages (from-to)1059-1078
Number of pages20
JournalInternational Journal of Robust and Nonlinear Control
Volume20
Issue number9
Early online date23 Mar 2010
DOIs
Publication statusPublished - 1 Jun 2010
Externally publishedYes

Fingerprint

Design of experiments
Parameter estimation
Identification (control systems)
Uncertainty

Keywords

  • Bayesian design
  • Biochemical network modelling
  • Maximin design
  • Parameter estimation
  • Robust experimental design

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Chemical Engineering(all)
  • Biomedical Engineering
  • Aerospace Engineering
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

Maximin and bayesian robust experimental design for measurement set selection in modelling biochemical regulatory systems. / He, Fei; Brown, Martin; Yue, Hong.

In: International Journal of Robust and Nonlinear Control, Vol. 20, No. 9, 01.06.2010, p. 1059-1078.

Research output: Contribution to journalArticle

@article{8a175123d5b14c449eb0f56ba4c11297,
title = "Maximin and bayesian robust experimental design for measurement set selection in modelling biochemical regulatory systems",
abstract = "Experimental design is important in system identification, especially when the models are complex and the measurement data are sparse and noisy, as often occurs in modelling of biochemical regulatory networks. The quality of conventional optimal experimental design largely depends on the accuracy of model parameter estimation, which is often either unavailable or poorly estimated at the stage of design. Robust experimental design (RED) algorithms have thus been proposed when model parametric uncertainties need to be addressed during the design process. In this paper, two robust design strategies are investigated and the comparative study has been made on signal pathway models. The first method is a maximin experimental design approach which is a worst-case design strategy, and the second method is the Bayesian experimental design that 'takes an average' of the parametric uncertainty effects. The limitations of the maximin design which describes the structural uncertainty using a local Taylor representation are quantitatively evaluated. To better quantitatively assess the differences between the maximin and the Bayesian REDs, a concept of effective design parameters is proposed, from which the advantages of the Bayesian design is demonstrated especially in the case of large model uncertainties.",
keywords = "Bayesian design, Biochemical network modelling, Maximin design, Parameter estimation, Robust experimental design",
author = "Fei He and Martin Brown and Hong Yue",
year = "2010",
month = "6",
day = "1",
doi = "10.1002/rnc.1558",
language = "English",
volume = "20",
pages = "1059--1078",
journal = "International Journal of Robust and Nonlinear Control",
issn = "1049-8923",
publisher = "Wiley",
number = "9",

}

TY - JOUR

T1 - Maximin and bayesian robust experimental design for measurement set selection in modelling biochemical regulatory systems

AU - He, Fei

AU - Brown, Martin

AU - Yue, Hong

PY - 2010/6/1

Y1 - 2010/6/1

N2 - Experimental design is important in system identification, especially when the models are complex and the measurement data are sparse and noisy, as often occurs in modelling of biochemical regulatory networks. The quality of conventional optimal experimental design largely depends on the accuracy of model parameter estimation, which is often either unavailable or poorly estimated at the stage of design. Robust experimental design (RED) algorithms have thus been proposed when model parametric uncertainties need to be addressed during the design process. In this paper, two robust design strategies are investigated and the comparative study has been made on signal pathway models. The first method is a maximin experimental design approach which is a worst-case design strategy, and the second method is the Bayesian experimental design that 'takes an average' of the parametric uncertainty effects. The limitations of the maximin design which describes the structural uncertainty using a local Taylor representation are quantitatively evaluated. To better quantitatively assess the differences between the maximin and the Bayesian REDs, a concept of effective design parameters is proposed, from which the advantages of the Bayesian design is demonstrated especially in the case of large model uncertainties.

AB - Experimental design is important in system identification, especially when the models are complex and the measurement data are sparse and noisy, as often occurs in modelling of biochemical regulatory networks. The quality of conventional optimal experimental design largely depends on the accuracy of model parameter estimation, which is often either unavailable or poorly estimated at the stage of design. Robust experimental design (RED) algorithms have thus been proposed when model parametric uncertainties need to be addressed during the design process. In this paper, two robust design strategies are investigated and the comparative study has been made on signal pathway models. The first method is a maximin experimental design approach which is a worst-case design strategy, and the second method is the Bayesian experimental design that 'takes an average' of the parametric uncertainty effects. The limitations of the maximin design which describes the structural uncertainty using a local Taylor representation are quantitatively evaluated. To better quantitatively assess the differences between the maximin and the Bayesian REDs, a concept of effective design parameters is proposed, from which the advantages of the Bayesian design is demonstrated especially in the case of large model uncertainties.

KW - Bayesian design

KW - Biochemical network modelling

KW - Maximin design

KW - Parameter estimation

KW - Robust experimental design

UR - http://www.scopus.com/inward/record.url?scp=77953017679&partnerID=8YFLogxK

U2 - 10.1002/rnc.1558

DO - 10.1002/rnc.1558

M3 - Article

VL - 20

SP - 1059

EP - 1078

JO - International Journal of Robust and Nonlinear Control

JF - International Journal of Robust and Nonlinear Control

SN - 1049-8923

IS - 9

ER -