Protein function prediction via graph kernels.

@article{Borgwardt2005, abstract = {MOTIVATION: Computational approaches to protein function prediction infer protein function by finding proteins with similar sequence, structure, surface clefts, chemical properties, amino acid motifs, interaction partners or phylogenetic profiles. We present a new approach that combines sequential, structural and chemical information into one graph model of proteins. We predict functional class membership of enzymes and non-enzymes using graph kernels and support vector machine classification on these protein graphs. RESULTS: Our graph model, derivable from protein sequence and structure only, is competitive with vector models that require additional protein information, such as the size of surface pockets. If we include this extra information into our graph model, our classifier yields significantly higher accuracy levels than the vector models. Hyperkernels allow us to select and to optimally combine the most relevant node attributes in our protein graphs. We have laid the foundation for a protein function prediction system that integrates protein information from various sources efficiently and effectively. AVAILABILITY: More information available via www.dbs.ifi.lmu.de/Mitarbeiter/borgwardt.html. CONTACT: borgwardt@dbs.ifi.lmu.de.}, address = {Institute for Computer Science, Ludwig-Maximilians-University Munich Oettingenstra{\ss}s e 67, 80538 Munich, Germany.}, author = {Borgwardt, Karsten M. M. and Cheng and Sch\"{o}nauer, Stefan and Vishwanathan, Sv N. V. and Smola, Alex J. J. and Kriegel, Hans-Peter P. }, citeulike-article-id = {241163}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {bioinformatics, classification, clustering, protein\_function}, month = {June}, number = {suppl\_1}, posted-at = {2006-02-17 20:36:39}, priority = {2}, title = {Protein function prediction via graph kernels.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/15961493}, volume = {21}, year = {2005} }

TY - JOUR ID - Borgwardt2005 L3 - citeulike-article-id:241163 TI - Protein function prediction via graph kernels. JF - Bioinformatics VL - 21 IS - suppl_1 AD - Institute for Computer Science, Ludwig-Maximilians-University Munich Oettingenstraßs e 67, 80538 Munich, Germany. SN - 1367-4803 N2 - MOTIVATION: Computational approaches to protein function prediction infer protein function by finding proteins with similar sequence, structure, surface clefts, chemical properties, amino acid motifs, interaction partners or phylogenetic profiles. We present a new approach that combines sequential, structural and chemical information into one graph model of proteins. We predict functional class membership of enzymes and non-enzymes using graph kernels and support vector machine classification on these protein graphs. RESULTS: Our graph model, derivable from protein sequence and structure only, is competitive with vector models that require additional protein information, such as the size of surface pockets. If we include this extra information into our graph model, our classifier yields significantly higher accuracy levels than the vector models. Hyperkernels allow us to select and to optimally combine the most relevant node attributes in our protein graphs. We have laid the foundation for a protein function prediction system that integrates protein information from various sources efficiently and effectively. AVAILABILITY: More information available via www.dbs.ifi.lmu.de/Mitarbeiter/borgwardt.html. CONTACT: borgwardt@dbs.ifi.lmu.de. KW - bioinformatics KW - classification KW - clustering KW - protein_function AU - Borgwardt, Karsten AU - Cheng AU - Schönauer, Stefan AU - Vishwanathan, Sv AU - Smola, Alex AU - Kriegel, Hans-Peter PY - 2005/06/01/ UR - http://view.ncbi.nlm.nih.gov/pubmed/15961493 ER -