The subsystems approach to genome annotation and its use in the project to annotate 1000 genomes. Export

@article{citeulike:402295, abstract = {The release of the 1000th complete microbial genome will occur in the next two to three years. In anticipation of this milestone, the Fellowship for Interpretation of Genomes (FIG) launched the Project to Annotate 1000 Genomes. The project is built around the principle that the key to improved accuracy in high-throughput annotation technology is to have experts annotate single subsystems over the complete collection of genomes, rather than having an annotation expert attempt to annotate all of the genes in a single genome. Using the subsystems approach, all of the genes implementing the subsystem are analyzed by an expert in that subsystem. An annotation environment was created where populated subsystems are curated and projected to new genomes. A portable notion of a populated subsystem was defined, and tools developed for exchanging and curating these objects. Tools were also developed to resolve conflicts between populated subsystems. The SEED is the first annotation environment that supports this model of annotation. Here, we describe the subsystem approach, and offer the first release of our growing library of populated subsystems. The initial release of data includes 180 177 distinct proteins with 2133 distinct functional roles. This data comes from 173 subsystems and 383 different organisms.}, address = {Fellowship for Interpretation of Genomes, 15W155 81st Street, Burr Ridge, IL 60527, USA.}, author = {Overbeek, Ross and Begley, Tadhg and Butler, Ralph M. and Choudhuri, Jomuna V. and Chuang, Han-Yu Y. and Cohoon, Matthew and de Cr\'{e}cy-Lagard, Val\'{e}rie and Diaz, Naryttza and Disz, Terry and Edwards, Robert and Fonstein, Michael and Frank, Ed D. and Gerdes, Svetlana and Glass, Elizabeth M. and Goesmann, Alexander and Hanson, Andrew and Iwata-Reuyl, Dirk and Jensen, Roy and Jamshidi, Neema and Krause, Lutz and Kubal, Michael and Larsen, Niels and Linke, Burkhard and McHardy, Alice C. and Meyer, Folker and Neuweger, Heiko and Olsen, Gary and Olson, Robert and Osterman, Andrei and Portnoy, Vasiliy and Pusch, Gordon D. and Rodionov, Dmitry A. and R\"{u}ckert, Christian and Steiner, Jason and Stevens, Rick and Thiele, Ines and Vassieva, Olga and Ye, Yuzhen and Zagnitko, Olga and Vonstein, Veronika}, citeulike-article-id = {402295}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/gki866}, citeulike-linkout-1 = {http://nar.oxfordjournals.org/cgi/content/abstract/33/17/5691}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/16214803}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=16214803}, doi = {10.1093/nar/gki866}, issn = {1362-4962}, journal = {Nucleic acids research}, keywords = {database, pathway}, number = {17}, pages = {5691--5702}, posted-at = {2009-05-18 11:46:21}, priority = {2}, title = {The subsystems approach to genome annotation and its use in the project to annotate 1000 genomes.}, url = {http://dx.doi.org/10.1093/nar/gki866}, volume = {33}, year = {2005} }

TY - JOUR ID - citeulike:402295 L3 - citeulike-article-id:402295 N2 - The release of the 1000th complete microbial genome will occur in the next two to three years. In anticipation of this milestone, the Fellowship for Interpretation of Genomes (FIG) launched the Project to Annotate 1000 Genomes. The project is built around the principle that the key to improved accuracy in high-throughput annotation technology is to have experts annotate single subsystems over the complete collection of genomes, rather than having an annotation expert attempt to annotate all of the genes in a single genome. Using the subsystems approach, all of the genes implementing the subsystem are analyzed by an expert in that subsystem. An annotation environment was created where populated subsystems are curated and projected to new genomes. A portable notion of a populated subsystem was defined, and tools developed for exchanging and curating these objects. Tools were also developed to resolve conflicts between populated subsystems. The SEED is the first annotation environment that supports this model of annotation. Here, we describe the subsystem approach, and offer the first release of our growing library of populated subsystems. The initial release of data includes 180 177 distinct proteins with 2133 distinct functional roles. This data comes from 173 subsystems and 383 different organisms. IS - 17 JF - Nucleic acids research SN - 1362-4962 AD - Fellowship for Interpretation of Genomes, 15W155 81st Street, Burr Ridge, IL 60527, USA. EP - 5702 TI - The subsystems approach to genome annotation and its use in the project to annotate 1000 genomes. VL - 33 SP - 5691 KW - database KW - pathway AU - Overbeek, Ross AU - Begley, Tadhg AU - Butler, Ralph AU - Choudhuri, Jomuna AU - Chuang, Han-Yu AU - Cohoon, Matthew AU - de Crécy-Lagard, Valérie AU - Diaz, Naryttza AU - Disz, Terry AU - Edwards, Robert AU - Fonstein, Michael AU - Frank, Ed AU - Gerdes, Svetlana AU - Glass, Elizabeth AU - Goesmann, Alexander AU - Hanson, Andrew AU - Iwata-Reuyl, Dirk AU - Jensen, Roy AU - Jamshidi, Neema AU - Krause, Lutz AU - Kubal, Michael AU - Larsen, Niels AU - Linke, Burkhard AU - McHardy, Alice AU - Meyer, Folker AU - Neuweger, Heiko AU - Olsen, Gary AU - Olson, Robert AU - Osterman, Andrei AU - Portnoy, Vasiliy AU - Pusch, Gordon AU - Rodionov, Dmitry AU - Rückert, Christian AU - Steiner, Jason AU - Stevens, Rick AU - Thiele, Ines AU - Vassieva, Olga AU - Ye, Yuzhen AU - Zagnitko, Olga AU - Vonstein, Veronika PY - 2005/// UR - http://dx.doi.org/10.1093/nar/gki866 ER -