[Show abstract][Hide abstract] ABSTRACT: Massive amounts of genome-wide gene expression data have become available, motivating the development of computational approaches that leverage this information to predict gene function. Among successful approaches, supervised machine learning methods, such as Support Vector Machines (SVMs), have shown superior prediction accuracy. However, these methods lack the simple biological intuition provided by co-expression networks (CNs), limiting their practical usefulness.
In this work, we present Discriminative Local Subspaces (DLS), a novel method that combines supervised machine learning and co-expression techniques with the goal of systematically predict genes involved in specific biological processes of interest. Unlike traditional CNs, DLS uses the knowledge available in Gene Ontology (GO) to generate informative training sets that guide the discovery of expression signatures: expression patterns that are discriminative for genes involved in the biological process of interest. By linking genes co-expressed with these signatures, DLS is able to construct a discriminative CN that links both, known and previously uncharacterized genes, for the selected biological process. This article focuses on the algorithm behind DLS and shows its predictive power using an Arabidopsis thaliana dataset and a representative set of 101 GO terms from the Biological Process Ontology. Our results show that DLS has a superior average accuracy than both SVMs and CNs. Thus, DLS is able to provide the prediction accuracy of supervised learning methods while maintaining the intuitive understanding of CNs.
A MATLAB® implementation of DLS is available at http://virtualplant.bio.puc.cl/cgi-bin/Lab/tools.cgi.
[Show abstract][Hide abstract] ABSTRACT: Genome sequencing has allowed to know almost every gene of many organisms. However, understanding the functions of most genes is still an open problem. In this paper, we present a novel machine learning method to predict functions of unknown genes in base of gene expression data and Gene Ontology annotations. Most function prediction al-gorithms developed in the past don't exploit the discriminative power of supervised learning. In contrast, our method uses this to find discriminative local subspaces that are suitable to perform gene functional prediction. Cross-validation test are done in artificial and real data and compared with a state-of-the-art method. Preliminary results shows that in overall, our method outperforms the other approach in terms of precision and recall, giving insights in the importance of a good selection of discriminative experiments.