@inproceedings{pestian07cmcdataset,
        title = {A Shared Task Involving Multi-label Classification of Clinical Free Text},
        address = {Prague},
        author = {JP Pestian and C Brew and P Matykiewicz and DJ Hovermale and N. Johnson and K. Bretonnel Cohen and W. Duch},
        booktitle = {Proceedings of ACL BioNLP},
        editor = { ACL},
        month = {June},
        organization = {Association of Computational Linguistics},
        year = 2007,
        biburl = {http://www.bibsonomy.org/bibtex/22226dfeef2ca4037bc100cf70ef14c08/sb3000},
	keywords = {data text-classification bioinformatics}
}

@article{wolstencroft06protein,
        title = {Protein classification using ontology classification.},
        address = {School of Computer Science, University of Manchester UK.},
        author = {K. Wolstencroft and P. Lord and L. Tabernero and A. Brass and R. Stevens},
        journal = {Bioinformatics},
        month = {July},
        number = 14,
        volume = 22,
        year = 2006,
        url = {http://dx.doi.org/10.1093/bioinformatics/btl208},
        issn = {1460-2059},
	biburl = {http://www.bibsonomy.org/bibtex/258bbdbe65011841b5375c300f2a84b4e/sb3000},
	keywords = {classification bioinformatics ontologies}
}

@article{vert02treekernel,
        title = {{A tree kernel to analyse phylogenetic profiles}},
        author = {Jean-Philippe Vert},
        journal = {Bioinformatics},
        number = {S1},
        pages = {S276-284},
        volume = 18,
        year = 2002,
        url = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/18/suppl_1/S276},
        abstract = {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.
},
	biburl = {http://www.bibsonomy.org/bibtex/2f2b420d46545a608cd616dc952330b7f/sb3000},
	keywords = {tree-kernels bioinformatics}
}

@article{go04geneontology,
        title = {The Gene Ontology (GO) database and informatics resource.},
        author = { {Gene Ontology Consortium}},
        journal = {Nucleic acids research},
        month = {JAN},
        number = 1,
        pages = {D258-D261},
        volume = 32,
        year = 2004,
        biburl = {http://www.bibsonomy.org/bibtex/2c31129d87ba02e09ec59eb9c4831be63/sb3000},
	keywords = {bioinformatics ontologies}
}