Selecting and Weighting Data for Building Consensus Gene Regulatory Networks

Authors:
Emma Steele;Allan Tucker
Affiliations:
School of Information Systems Computing and Maths, Brunel University, Uxbridge, UK UB8 3PH;School of Information Systems Computing and Maths, Brunel University, Uxbridge, UK UB8 3PH
Venue:
IDA '09 Proceedings of the 8th International Symposium on Intelligent Data Analysis: Advances in Intelligent Data Analysis VIII
Year:
2009

Citing 3
Cited 0

Inferring gene regulatory networks from multiple microarray datasets

Bioinformatics
A Novel Scalable and Data Efficient Feature Subset Selection Algorithm

ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Consensus and Meta-analysis regulatory networks for combining multiple microarray gene expression datasets

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Microarrays are the major source of data for gene expression activity, allowing the expression of thousands of genes to be measured simultaneously. Gene regulatory networks (GRNs) describe how the expression level of genes affect the expression of the other genes. Modelling GRNs from expression data is a topic of great interest in current bioinformatics research. Previously, we took advantage of publicly available gene expression datasets generated by similar biological studies by drawing together a richer and/or broader collection of data in order to produce GRN models that are more robust, have greater confidence and place less reliance on a single dataset. In this paper a new approach, Weighted Consensus Bayesian Networks, introduces the use of weights in order to place more influence on certain input networks or remove the least reliable networks from the input with encouraging results on both synthetic data and real world yeast microarray datasets.