Validating module network learning algorithms using simulated data

TL;DR

This paper introduces LeMoNe, a new software for learning gene expression modules using simulated data, featuring a novel hierarchical clustering approach and entropy-based regulator assignment, with advantages in speed and regulator prioritization.

Contribution

The paper presents LeMoNe, a module network learning algorithm with innovative bottom-up Bayesian clustering and entropy measures, validated on synthetic data and compared to existing methods.

Findings

LeMoNe performs comparably to Genomica on simulated data.

LeMoNe is faster for large datasets.

Regulator location and entropy can prioritize functional validation.

Abstract

In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. 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. Overall, application of Genomica and LeMoNe to simulated data sets gave comparable results. However, LeMoNe offers some advantages, one of them being that the learning process is considerably faster for larger data sets. Additionally, we show that the location of the regulators in the LeMoNe regulation programs and their conditional entropy may be used to prioritize regulators for functional validation, and that the combination of the bottom-up clustering strategy with the conditional entropy-based assignment of regulators improves the handling of missing or hidden regulators.