Graph-driven features extraction from microarray data

Gene function prediction from microarray data is a first step toward better understanding the machinery of the cell from relatively cheap and easy-to-produce data. In this paper we investigate whether the knowledge of many metabolic pathways and their catalyzing enzymes accumulated over the years can help improve the performance of classifiers for this problem. The complex network of known biochemical reactions in the cell results in a representation where genes are nodes of a graph. Formulating the problem as a graph-driven features extraction problem, based on the simple idea that relevant features are likely to exhibit correlation with respect to the topology of the graph, we end up with an algorithm which involves encoding the network and the set of expression profiles into kernel functions, and performing a regularized form of canonical correlation analysis in the corresponding reproducible kernel Hilbert spaces. Function prediction experiments for the genes of the yeast S. Cerevisiae validate this approach by showing a consistent increase in performance when a state-of-the-art classifier uses the vector of features instead of the original expression profile to predict the functional class of a gene.