PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Discovering condition-dependent Bayesian networks for gene regulation
Antti Ajanki, Janne Nikkila and Samuel Kaski
In: Fifth IEEE International Workshop on Genomic Signal Processing and Statistics, 10-12 June 2007, Tuusula, Finland.


Among the main interests in many biological studies are the structure of gene regulatory network, and in particular differences in the regulatory interactions between differ- ent conditions. However, since the number of available samples is always very small and estimating the network structure is extremely hard, most current algorithms have to assume that the gene regulation does not change be- tween conditions. We propose a new Bayesian network algorithm which (i) utilizes all the samples for estimat- ing regulatory relations that remain the same across con- ditions, and (ii) explicitly searches for regulatory relation- ships that are active only in one of the conditions. The result is an easily interpretable map of changes in regula- tion in several conditions.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:3347
Deposited By:Antti Ajanki
Deposited On:08 February 2008