Validating module network learning algorithms using simulated data

Abstract

Background: In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. Despite the demonstrated success of such algorithms in uncovering biologically relevant regulatory relations, further developments in the area are hampered by a lack of tools to compare the performance of alternative module network learning strategies. Here, we demonstrate the use of the synthetic data generator SynTReN for the purpose of testing and comparing module network learning algorithms. We introduce a software package for learning module networks, called LeMoNe, which incorporates a novel strategy for learning regulatory programs. Novelties include the use of a bottom-up Bayesian hierarchical clustering to construct the regulatory programs, and the use of a conditional entropy measure to assign regulators to the regulation program nodes. Using SynTReN data, we test the performance of LeMoNe in a completely controlled situation and assess the effect of the methodological changes we made with respect to an existing software package, namely Genomica. Additionally, we assess the effect of various parameters, such as the size of the data set and the amount of noise, on the inference performance.

VisuaLRTC: A New View on Lateral Root Initiation by Combining Specific Transcriptome Data Sets

“…Also, generated top lists can be intersected to include or exclude certain genes. Finally, they can be grouped in compendiums to be analyzed by intricate clustering algorithms and to elaborate modules and networks (Michoel et al, 2007).…”

Inferring Causal Relations from Multivariate Time Series: A Fast Method for Large-Scale Gene Expression Data

“…SynTReN is well suited for testing module network algorithms [13]. By using topologies generated based on previously described source networks, SynTReN allows good approximation of the statistical properties of real biological networks.…”

Computational and Systems Biology

“…In order to anticipate these complexities in an intelligent way, we developed the LeMoNe (learning module networks) algorithm. 6,7 LeMoNe is a probabilistic module networks framework, like Genomica, 3 in which coregulated genes share the same parents and conditional distributions in a Bayesian network, hence limiting the number of variables, reducing the complexity of the learning and leading to more robust solutions. Using Gibbs sampling, LeMoNe groups genes in coexpression modules and then using a fuzzy decision tree, it assigns regulators to these gene modules, based on how well the regulators explain the condition-dependent expression behavior of the module.…”