Proceeding talk – Theme: Systems.
Abstract
Reconstructing regulatory networks from expression and interaction data is a major goal of systems biology. Relatively little work has focused on inferring the regulation of microRNAs (miRNAs) by transcription factors (TFs). Prediction of such interactions is challenging due to the very small positive training set currently available, and the fact that a large fraction of miRNAs are encoded within genes making it hard to determine the specific way in which they are regulated. We extended semi-supervised machine learning approaches to integrate a large set of different types of data including sequence, expression, ChIP-Seq, and epigenetic data. These methods achieve good performance on both a labeled test set, and when analyzing general co-expression networks. We next analyze mRNA and miRNA cancer expression data, demonstrating the advantage of using the predicted set of interactions for identifying more coherent and relevant modules, genes and miRNAs.
Authors
Matthew Ruffalo, Carnegie Mellon University, United States
Ziv Bar-Joseph, Carnegie Mellon University, United States