Functional annotation of the Arabidopsis genome using controlled vocabularies. Export

@article{citeulike:637405, abstract = {Controlled vocabularies are increasingly used by databases to describe genes and gene products because they facilitate identification of similar genes within an organism or among different organisms. One of The Arabidopsis Information Resource's goals is to associate all Arabidopsis genes with terms developed by the Gene Ontology Consortium that describe the molecular function, biological process, and subcellular location of a gene product. We have also developed terms describing Arabidopsis anatomy and developmental stages and use these to annotate published gene expression data. As of March 2004, we used computational and manual annotation methods to make 85,666 annotations representing 26,624 unique loci. We focus on associating genes to controlled vocabulary terms based on experimental data from the literature and use The Arabidopsis Information Resource-developed PubSearch software to facilitate this process. Each annotation is tagged with a combination of evidence codes, evidence descriptions, and references that provide a robust means to assess data quality. Annotation of all Arabidopsis genes will allow quantitative comparisons between sets of genes derived from sources such as microarray experiments. The Arabidopsis annotation data will also facilitate annotation of newly sequenced plant genomes by using sequence similarity to transfer annotations to homologous genes. In addition, complete and up-to-date annotations will make unknown genes easy to identify and target for experimentation. Here, we describe the process of Arabidopsis functional annotation using a variety of data sources and illustrate several ways in which this information can be accessed and used to infer knowledge about Arabidopsis and other plant species.}, address = {Carnegie Institution, Department of Plant Biology, Stanford, California 94305, USA.}, author = {Berardini, T. Z. and Mundodi, S. and Reiser, L. and Huala, E. and Garcia-Hernandez, M. and Zhang, P. and Mueller, L. A. and Yoon, J. and Doyle, A. and Lander, G. and Moseyko, N. and Yoo, D. and Xu, I. and Zoeckler, B. and Montoya, M. and Miller, N. and Weems, D. and Rhee, S. Y.}, citeulike-article-id = {637405}, citeulike-linkout-0 = {http://dx.doi.org/10.1104/pp.104.040071}, citeulike-linkout-1 = {http://www.plantphysiol.org/cgi/content/abstract/135/2/745}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/15173566}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=15173566}, doi = {10.1104/pp.104.040071}, issn = {0032-0889}, journal = {Plant Physiol}, keywords = {arabidopsis, ontology}, month = {June}, number = {2}, pages = {745--755}, posted-at = {2007-11-06 10:14:39}, priority = {2}, title = {Functional annotation of the Arabidopsis genome using controlled vocabularies.}, url = {http://dx.doi.org/10.1104/pp.104.040071}, volume = {135}, year = {2004} }

TY - JOUR ID - citeulike:637405 L3 - citeulike-article-id:637405 N2 - Controlled vocabularies are increasingly used by databases to describe genes and gene products because they facilitate identification of similar genes within an organism or among different organisms. One of The Arabidopsis Information Resource's goals is to associate all Arabidopsis genes with terms developed by the Gene Ontology Consortium that describe the molecular function, biological process, and subcellular location of a gene product. We have also developed terms describing Arabidopsis anatomy and developmental stages and use these to annotate published gene expression data. As of March 2004, we used computational and manual annotation methods to make 85,666 annotations representing 26,624 unique loci. We focus on associating genes to controlled vocabulary terms based on experimental data from the literature and use The Arabidopsis Information Resource-developed PubSearch software to facilitate this process. Each annotation is tagged with a combination of evidence codes, evidence descriptions, and references that provide a robust means to assess data quality. Annotation of all Arabidopsis genes will allow quantitative comparisons between sets of genes derived from sources such as microarray experiments. The Arabidopsis annotation data will also facilitate annotation of newly sequenced plant genomes by using sequence similarity to transfer annotations to homologous genes. In addition, complete and up-to-date annotations will make unknown genes easy to identify and target for experimentation. Here, we describe the process of Arabidopsis functional annotation using a variety of data sources and illustrate several ways in which this information can be accessed and used to infer knowledge about Arabidopsis and other plant species. IS - 2 JF - Plant Physiol SN - 0032-0889 AD - Carnegie Institution, Department of Plant Biology, Stanford, California 94305, USA. EP - 755 TI - Functional annotation of the Arabidopsis genome using controlled vocabularies. VL - 135 SP - 745 KW - arabidopsis KW - ontology AU - Berardini, TZ AU - Mundodi, S AU - Reiser, L AU - Huala, E AU - Garcia-Hernandez, M AU - Zhang, P AU - Mueller, LA AU - Yoon, J AU - Doyle, A AU - Lander, G AU - Moseyko, N AU - Yoo, D AU - Xu, I AU - Zoeckler, B AU - Montoya, M AU - Miller, N AU - Weems, D AU - Rhee, SY PY - 2004/06// UR - http://dx.doi.org/10.1104/pp.104.040071 ER -