Seeing the Forest for the Trees: Using the Gene Ontology to re-structure Hierarchical clustering. Export

@article{citeulike:4768675, abstract = {MOTIVATION: There is a growing interest in improving the cluster analysis of expression data by incorporating into it prior knowledge, such as the GO-annotations of genes, in order to improve the biological relevance of the clusters that are subjected to subsequent scrutiny. The structure of the Gene Ontology is another source of background knowledge that can be exploited through the use of semantic-similarity. RESULTS: We propose here a novel algorithm that integrates semantic-similarities (derived from the ontology structure) into the procedure of deriving clusters from the dendrogram constructed during expression-based hierarchical clustering. Our approach can handle the multiple annotations, from different levels of the GO-hierarchy, which most genes have. Moreover, it treats annotated and unanno-tated genes in a uniform manner. Consequently, the clusters ob-tained by our algorithm are characterized by significantly enriched annotations. In both cross-validation tests and when using an exter-nal index such as protein-protein interactions, our algorithm per-forms better than previous approaches. When applied to human-cancer expression data, our algorithm iden-tifies, among others, clusters of genes related to immune response and glucose metabolism. These clusters are also supported by pro-tein-protein interaction data.}, author = {Dotan-Cohen, Dikla and Kasif, Simon and Melkman, Avraham A A.}, citeulike-article-id = {4768675}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp327}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19497934}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19497934}, day = {3}, doi = {10.1093/bioinformatics/btp327}, issn = {1460-2059}, journal = {Bioinformatics (Oxford, England)}, keywords = {annotation, clustering}, month = {June}, posted-at = {2009-06-09 13:46:29}, priority = {2}, title = {Seeing the Forest for the Trees: Using the Gene Ontology to re-structure Hierarchical clustering.}, url = {http://dx.doi.org/10.1093/bioinformatics/btp327}, year = {2009} }

TY - JOUR ID - citeulike:4768675 L3 - citeulike-article-id:4768675 N2 - MOTIVATION: There is a growing interest in improving the cluster analysis of expression data by incorporating into it prior knowledge, such as the GO-annotations of genes, in order to improve the biological relevance of the clusters that are subjected to subsequent scrutiny. The structure of the Gene Ontology is another source of background knowledge that can be exploited through the use of semantic-similarity. RESULTS: We propose here a novel algorithm that integrates semantic-similarities (derived from the ontology structure) into the procedure of deriving clusters from the dendrogram constructed during expression-based hierarchical clustering. Our approach can handle the multiple annotations, from different levels of the GO-hierarchy, which most genes have. Moreover, it treats annotated and unanno-tated genes in a uniform manner. Consequently, the clusters ob-tained by our algorithm are characterized by significantly enriched annotations. In both cross-validation tests and when using an exter-nal index such as protein-protein interactions, our algorithm per-forms better than previous approaches. When applied to human-cancer expression data, our algorithm iden-tifies, among others, clusters of genes related to immune response and glucose metabolism. These clusters are also supported by pro-tein-protein interaction data. JF - Bioinformatics (Oxford, England) SN - 1460-2059 TI - Seeing the Forest for the Trees: Using the Gene Ontology to re-structure Hierarchical clustering. KW - annotation KW - clustering AU - Dotan-Cohen, Dikla AU - Kasif, Simon AU - Melkman, Avraham A PY - 2009/06/03/ UR - http://dx.doi.org/10.1093/bioinformatics/btp327 ER -