2002/06/17 by Jean-Philippe Vert, Jean‐Philippe Vert, Minoru Kanehisa +2 · 1 citation
Biochemistry, Genetics and Molecular Biology · Physics and Astronomy · #Bioinformatics and Genomic Networks #Biological Physics (physics.bio-ph) #Cell Image Analysis Techniques #Data Analysis #FOS: Biological sciences #FOS: Physical sciences #Gene expression and cancer classification #Molecular Networks (q-bio.MN) #Statistics and Probability (physics.data-an) #physics.bio-ph #physics.data-an #q-bio.MN
paper · pdf · doi:10.48550/arxiv.physics/0206055
31 pages, 2 figures
arxiv created 2002/06/17 · openalex publication_date 2002/06/17 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.