Dynamic Bayesian networks in modelling cellular systems

A critical appraisal on simulated data

Fulvia Ferrazzi, Paola Sebastiani, Isaac S. Kohane, Marco F. Ramoni, Riccardo Bellazzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Dynamic Bayesian networks offer a powerful modelling tool to unravel cellular mechanisms. In particular, Gaussian Networks have recently been used to model gene expression data, thanks to their capability to avoid information loss associated with discretization and their good computational efficiency. Gaussian Networks typically describe the conditional mean of a node as a linear regression of the parent variables. Such model can be generalized by using a linear regression of nonlinear transformations of the parent values. In this paper we investigate the use of both models and evaluate the performance of Gaussian Networks in learning the complex dynamic interactions among genes and proteins. To this aim, we analyzed simulated data produced by a mathematical model of cell cycle control in budding yeast. The results obtained allowed us to appraise the performance of the different models and confirmed the suitability of dynamic Bayesian networks for a first level, genome-wide analysis of high throughput dynamic data.

Original languageEnglish
Title of host publicationProceedings - IEEE Symposium on Computer-Based Medical Systems
Pages544-549
Number of pages6
Volume2006
DOIs
Publication statusPublished - 2006
Event19th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2006 - Salt Lake City, UT, United States
Duration: Jun 22 2006Jun 23 2006

Other

Other19th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2006
CountryUnited States
CitySalt Lake City, UT
Period6/22/066/23/06

Fingerprint

Bayesian networks
Linear regression
Genes
Computational efficiency
Gene expression
Yeast
Cells
Throughput
Mathematical models
Proteins

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ferrazzi, F., Sebastiani, P., Kohane, I. S., Ramoni, M. F., & Bellazzi, R. (2006). Dynamic Bayesian networks in modelling cellular systems: A critical appraisal on simulated data. In Proceedings - IEEE Symposium on Computer-Based Medical Systems (Vol. 2006, pp. 544-549). [1647627] https://doi.org/10.1109/CBMS.2006.81

Dynamic Bayesian networks in modelling cellular systems : A critical appraisal on simulated data. / Ferrazzi, Fulvia; Sebastiani, Paola; Kohane, Isaac S.; Ramoni, Marco F.; Bellazzi, Riccardo.

Proceedings - IEEE Symposium on Computer-Based Medical Systems. Vol. 2006 2006. p. 544-549 1647627.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ferrazzi, F, Sebastiani, P, Kohane, IS, Ramoni, MF & Bellazzi, R 2006, Dynamic Bayesian networks in modelling cellular systems: A critical appraisal on simulated data. in Proceedings - IEEE Symposium on Computer-Based Medical Systems. vol. 2006, 1647627, pp. 544-549, 19th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2006, Salt Lake City, UT, United States, 6/22/06. https://doi.org/10.1109/CBMS.2006.81
Ferrazzi F, Sebastiani P, Kohane IS, Ramoni MF, Bellazzi R. Dynamic Bayesian networks in modelling cellular systems: A critical appraisal on simulated data. In Proceedings - IEEE Symposium on Computer-Based Medical Systems. Vol. 2006. 2006. p. 544-549. 1647627 https://doi.org/10.1109/CBMS.2006.81
Ferrazzi, Fulvia ; Sebastiani, Paola ; Kohane, Isaac S. ; Ramoni, Marco F. ; Bellazzi, Riccardo. / Dynamic Bayesian networks in modelling cellular systems : A critical appraisal on simulated data. Proceedings - IEEE Symposium on Computer-Based Medical Systems. Vol. 2006 2006. pp. 544-549
@inproceedings{744318e8f731440ab08e09cdfb29e612,
title = "Dynamic Bayesian networks in modelling cellular systems: A critical appraisal on simulated data",
abstract = "Dynamic Bayesian networks offer a powerful modelling tool to unravel cellular mechanisms. In particular, Gaussian Networks have recently been used to model gene expression data, thanks to their capability to avoid information loss associated with discretization and their good computational efficiency. Gaussian Networks typically describe the conditional mean of a node as a linear regression of the parent variables. Such model can be generalized by using a linear regression of nonlinear transformations of the parent values. In this paper we investigate the use of both models and evaluate the performance of Gaussian Networks in learning the complex dynamic interactions among genes and proteins. To this aim, we analyzed simulated data produced by a mathematical model of cell cycle control in budding yeast. The results obtained allowed us to appraise the performance of the different models and confirmed the suitability of dynamic Bayesian networks for a first level, genome-wide analysis of high throughput dynamic data.",
author = "Fulvia Ferrazzi and Paola Sebastiani and Kohane, {Isaac S.} and Ramoni, {Marco F.} and Riccardo Bellazzi",
year = "2006",
doi = "10.1109/CBMS.2006.81",
language = "English",
isbn = "0769525172",
volume = "2006",
pages = "544--549",
booktitle = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",

}

TY - GEN

T1 - Dynamic Bayesian networks in modelling cellular systems

T2 - A critical appraisal on simulated data

AU - Ferrazzi, Fulvia

AU - Sebastiani, Paola

AU - Kohane, Isaac S.

AU - Ramoni, Marco F.

AU - Bellazzi, Riccardo

PY - 2006

Y1 - 2006

N2 - Dynamic Bayesian networks offer a powerful modelling tool to unravel cellular mechanisms. In particular, Gaussian Networks have recently been used to model gene expression data, thanks to their capability to avoid information loss associated with discretization and their good computational efficiency. Gaussian Networks typically describe the conditional mean of a node as a linear regression of the parent variables. Such model can be generalized by using a linear regression of nonlinear transformations of the parent values. In this paper we investigate the use of both models and evaluate the performance of Gaussian Networks in learning the complex dynamic interactions among genes and proteins. To this aim, we analyzed simulated data produced by a mathematical model of cell cycle control in budding yeast. The results obtained allowed us to appraise the performance of the different models and confirmed the suitability of dynamic Bayesian networks for a first level, genome-wide analysis of high throughput dynamic data.

AB - Dynamic Bayesian networks offer a powerful modelling tool to unravel cellular mechanisms. In particular, Gaussian Networks have recently been used to model gene expression data, thanks to their capability to avoid information loss associated with discretization and their good computational efficiency. Gaussian Networks typically describe the conditional mean of a node as a linear regression of the parent variables. Such model can be generalized by using a linear regression of nonlinear transformations of the parent values. In this paper we investigate the use of both models and evaluate the performance of Gaussian Networks in learning the complex dynamic interactions among genes and proteins. To this aim, we analyzed simulated data produced by a mathematical model of cell cycle control in budding yeast. The results obtained allowed us to appraise the performance of the different models and confirmed the suitability of dynamic Bayesian networks for a first level, genome-wide analysis of high throughput dynamic data.

UR - http://www.scopus.com/inward/record.url?scp=33845584323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845584323&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2006.81

DO - 10.1109/CBMS.2006.81

M3 - Conference contribution

SN - 0769525172

SN - 9780769525174

VL - 2006

SP - 544

EP - 549

BT - Proceedings - IEEE Symposium on Computer-Based Medical Systems

ER -