Tackling the DREAM challenge for gene regulatory networks reverse engineering

Authors:
Alessia Visconti;Roberto Esposito;Francesca Cordero
Affiliations:
Department of Computer Science, University of Torino and Interdepartmental Centre for Molecular Systems Biology, University of Torino;Department of Computer Science, University of Torino and Interdepartmental Centre for Molecular Systems Biology, University of Torino;Department of Computer Science, University of Torino and Department of Clinical and Biological Sciences, University of Torino and Interdepartmental Centre for Molecular Systems Biology, University ...
Venue:
AI*IA'11 Proceedings of the 12th international conference on Artificial intelligence around man and beyond
Year:
2011

Citing 4
Cited 0

Bayesian learning in undirected graphical models: approximate MCMC algorithms

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Inference of gene regulatory networks and compound mode of action from time course gene expression profiles

Bioinformatics
maSigPro: a method to identify significantly differential expression profiles in time-course microarray experiments

Bioinformatics
Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning

Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

The construction and the understanding of Gene Regulatory Networks (GRNs) are among the hardest tasks faced by systems biology. The inference of a GRN from gene expression data (the GRN reverse engineering), is a challenging task that requires the exploitation of diverse mathematical and computational techniques. The DREAM conference proposes several challenges about the inference of biological networks and/or the prediction of how they are influenced by perturbations. This paper describes a method for GRN reverse engineering that the authors submitted to the 2010 DREAM challenge. The methodology is based on a combination of well known statistical methods into a Naive Bayes classifier. Despite its simplicity the approach fared fairly well when compared to other proposals on real networks.