Mining gene regulatory networks by neural modeling of expression time-series

M. RUBIOLO; D. MILONE; G. STEGMAYER

Buenos Aires

Simposio; 45 Jornadas Argentinas de Informática - XVII Simposio Argentino de Inteligencia Artificial; 2016

SADIO

Discovering gene regulatory networks from data is one of the most studied topics in recent years. Neural networks can successfully model expression profiles as times series to infer an underlying gene network. This work proposes a novel method based on a pool of neural networks for obtaining a network of interactions between variables from a dataset. They can model each possible interaction between pairs of variables in the dataset, and a set of mining rules is applied to accurately detect the subjacent relations among them. The results obtained on artificial and real datasets confirm the method effectiveness for discovering gene regulatory networks from a proper modeling of the temporal dynamics of gene expression profiles. This approach could be used not only in Bioinformatics but also in any field of knowledge in which time series are the input data.