TU Darmstadt / ULB / TUbiblio

Influence of Noise on the Inference of Dynamic Bayesian Networks from Short Time Series

Emmert-Streib, Frank and Dehmer, Matthias and Bakir, H. G. and Mühlhäuser, Max (2005):
Influence of Noise on the Inference of Dynamic Bayesian Networks from Short Time Series.
In: Proceedings of the VIII. International Conference on Enformatika, Systems Sciences and Engineering, Krakow/Poland, Enformatika 10, enformatika, ISBN 975-98458-9-X,
[Conference or Workshop Item]

Abstract

In this paper we investigate the influence of external noise on the inference of network structures. The purpose of our simulations is to gain insights in the experimental design of microarray experiments to infer, e.g., transcription regulatory networks from microarray experiments. Here external noise means, that the dynamics of the system under investigation, e.g., temporal changes of mRNA concentration, is affected by measurement errors. Additionally to external noise another problem occurs in the context of microarray experiments. Practically, it is not possible to monitor the mRNA concentration over an arbitrary long time period as demanded by the statistical methods used to learn the underlying network structure. For this reason, we use only short time series to make our simulations more biologically plausible.

Item Type: Conference or Workshop Item
Erschienen: 2005
Creators: Emmert-Streib, Frank and Dehmer, Matthias and Bakir, H. G. and Mühlhäuser, Max
Title: Influence of Noise on the Inference of Dynamic Bayesian Networks from Short Time Series
Language: German
Abstract:

In this paper we investigate the influence of external noise on the inference of network structures. The purpose of our simulations is to gain insights in the experimental design of microarray experiments to infer, e.g., transcription regulatory networks from microarray experiments. Here external noise means, that the dynamics of the system under investigation, e.g., temporal changes of mRNA concentration, is affected by measurement errors. Additionally to external noise another problem occurs in the context of microarray experiments. Practically, it is not possible to monitor the mRNA concentration over an arbitrary long time period as demanded by the statistical methods used to learn the underlying network structure. For this reason, we use only short time series to make our simulations more biologically plausible.

Title of Book: Proceedings of the VIII. International Conference on Enformatika, Systems Sciences and Engineering, Krakow/Poland, Enformatika 10
Publisher: enformatika
ISBN: 975-98458-9-X
Uncontrolled Keywords: Dynamic Bayesian networks, structure learning, gene networks, Markov chain Monte Carlo, microarray data
Divisions: 20 Department of Computer Science > Telecooperation
20 Department of Computer Science
Date Deposited: 31 Dec 2016 12:59
Identification Number: EDBM:2005
Export:

Optionen (nur für Redakteure)

View Item View Item