''Data Fusion of Everything''

Have you ever been overwhelmed by data---not only by their volume but by their sheer multitude? Since you are a researcher at Donnelly Center, you most certainly have. In life science, the data abounds. One of the grand challenges in bioinformatics is to infer a predictive model by jointly considering, say, gene expression, interactions, functional annotations, phenotype information, various ontologies, disease markers, structural properties of chemicals, and Facebook (ok, I perhaps went too far with the last item). That is, by considering all available information, even if only circumstantially related to the problem at hand. At University of Ljubljana we have developed a computational approach that uses collective matrix tri-factorization and can consider such diverse data sets. Tri-factorization infers a joint latent data model. The model can be used for various data mining tasks, such as class prediction and ranking. Our experiments show that through a broad integration of heterogeneous data sets we can substantially increase the accuracy. In the talk, I will present the intuition behind data fusion by matrix tri-factorization, and show how it was used to find new bacterial response genes in social amoeba Dictyostelium.