A tree kernel to analyse phylogenetic profiles
| Autor: | Jean-Philippe Vert |
|---|---|
| Přispěvatelé: | Bioinformatics Center (KEGG), Kyoto University [Kyoto], Vert, Jean-Philippe |
| Rok vydání: | 2002 |
| Předmět: |
Graph kernel
genetic structures 02 engineering and technology Biochemistry Kernel principal component analysis Pattern Recognition Automated MESH: Saccharomyces cerevisiae Proteins String kernel 0202 electrical engineering electronic engineering information engineering MESH: Pattern Recognition Automated MESH: Models Genetic MESH: Phylogeny Phylogeny MESH: Evolution Molecular [INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM] Mathematics 0303 health sciences [SDV.BIBS] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Phylogenetic tree food and beverages MESH: Gene Expression Regulation MESH: Saccharomyces cerevisiae [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Computer Science Applications Computational Mathematics Kernel method Computational Theory and Mathematics Kernel (statistics) 020201 artificial intelligence & image processing Tree kernel Algorithms Statistics and Probability Saccharomyces cerevisiae Proteins information science MESH: Algorithms Saccharomyces cerevisiae Evolution Molecular MESH: Gene Expression Profiling 03 medical and health sciences Artificial Intelligence MESH: Artificial Intelligence Molecular Biology 030304 developmental biology Models Statistical Models Genetic business.industry Gene Expression Profiling Pattern recognition Support vector machine ComputingMethodologies_PATTERNRECOGNITION Gene Expression Regulation Artificial intelligence [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] business MESH: Models Statistical |
| Zdroj: | ISMB Bioinformatics Bioinformatics, Oxford University Press (OUP), 2002, 18 Suppl 1, pp.S276-84 Scopus-Elsevier |
| ISSN: | 1367-4811 1367-4803 |
| DOI: | 10.1093/bioinformatics/18.suppl_1.s276 |
| Popis: | Motivation: The phylogenetic profile of a protein is a string that encodes the presence or absence of the protein in every fully sequenced genome. Because proteins that participate in a common structural complex or metabolic pathway are likely to evolve in a correlated fashion, the phylogenetic profiles of such proteins are often ‘similar’ or at least ‘related’ to each other. The question we address in this paper is the following: how to measure the ‘similarity’ between two profiles, in an evolutionarily relevant way, in order to develop efficient function prediction methods? Results: We show how the profiles can be mapped to a high-dimensional vector space which incorporates evolutionarily relevant information, and we provide an algorithm to compute efficiently the inner product in that space, which we call the tree kernel. The tree kernel can be used by any kernel-based analysis method for classification or data mining of phylogenetic profiles. As an application a Support Vector Machine (SVM) trained to predict the functional class of a gene from its phylogenetic profile is shown to perform better with the tree kernel than with a naive kernel that does not include any information about the phylogenetic relationships among species. Moreover a kernel principal component analysis (KPCA) of the phylogenetic profiles illustrates the sensitivity of the tree kernel to evolutionarily relevant variations. Availability: All data and software used are freely and publicly available upon request. Contact: Jean-Philippe.Vert@mines.org Keywords: phylogenetic profile; tree; kernel; support vector machine; gene function prediction. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|