Gene Functional Annotation with Dynamic Hierarchical Classification Guided by Orthologs
This paper proposes an approach to automating Gene Ontology (GO) annotation in the framework of hierarchical classification that uses known, already annotated functions of the orthologs of a given gene. The proposed approach exploits such known functions as constraints and dynamically builds classifiers based on the training data available under the constraints. In addition, two unsupervised approaches are applied to complement the classification framework. The validity and effectiveness of the proposed approach are empirically demonstrated.
KeywordsGene ontology String matching Information retrieval
Unable to display preview. Download preview PDF.
- 2.Hersh, W., Bhuptiraju, R.T., Ross, L., Cohen, A.M., Kraemer, D.F.: TREC 2004 genomics track overview. In: Proc. of the 13th Text REtrieval Conference (2004)Google Scholar
- 6.Stoica, E., Hearst, M.: newblock Predicting gene functions from text using a cross-species approach. In: Proc. of the Pacific Symposium on Biocomputing, pp. 88–99 (2006)Google Scholar
- 7.McCallum, A., Rosenfeld, R., Mitchell, T.M., Ng, A.Y.: Improving text classification by shrinkage in a hierarchy of classes. In: Proc. of the 15th International Conference on Machine Learning, pp. 359–367 (1998)Google Scholar
- 9.Chiang, J., Yu, H.: Extracting functional annotations of proteins based on hybrid text mining approaches. In: Proc. of the BioCreAtIvE (2004)Google Scholar