@article{Pruitt01072009,
author = {Pruitt, Kim D. and Harrow, Jennifer and Harte, Rachel A. and Wallin, Craig and Diekhans, Mark and Maglott, Donna R. and Searle, Steve and Farrell, Catherine M. and Loveland, Jane E. and Ruef, Barbara J. and Hart, Elizabeth and Suner, Marie-Marthe and Landrum, Melissa J. and Aken, Bronwen and Ayling, Sarah and Baertsch, Robert and Fernandez-Banet, Julio and Cherry, Joshua L. and Curwen, Val and DiCuccio, Michael and Kellis, Manolis and Lee, Jennifer and Lin, Michael F. and Schuster, Michael and Shkeda, Andrew and Amid, Clara and Brown, Garth and Dukhanina, Oksana and Frankish, Adam and Hart, Jennifer and Maidak, Bonnie L. and Mudge, Jonathan and Murphy, Michael R. and Murphy, Terence and Rajan, Jeena and Rajput, Bhanu and Riddick, Lillian D. and Snow, Catherine and Steward, Charles and Webb, David and Weber, Janet A. and Wilming, Laurens and Wu, Wenyu and Birney, Ewan and Haussler, David and Hubbard, Tim and Ostell, James and Durbin, Richard and Lipman, David}, 
title = {The consensus coding sequence (CCDS) project: Identifying a common protein-coding gene set for the human and mouse genomes},
volume = {19}, 
number = {7}, 
pages = {1316-1323}, 
year = {2009}, 
doi = {10.1101/gr.080531.108}, 
abstract ={Effective use of the human and mouse genomes requires reliable identification of genes and their products. Although multiple public resources provide annotation, different methods are used that can result in similar but not identical representation of genes, transcripts, and proteins. The collaborative consensus coding sequence (CCDS) project tracks identical protein annotations on the reference mouse and human genomes with a stable identifier (CCDS ID), and ensures that they are consistently represented on the NCBI, Ensembl, and UCSC Genome Browsers. Importantly, the project coordinates on manually reviewing inconsistent protein annotations between sites, as well as annotations for which new evidence suggests a revision is needed, to progressively converge on a complete protein-coding set for the human and mouse reference genomes, while maintaining a high standard of reliability and biological accuracy. To date, the project has identified 20,159 human and 17,707 mouse consensus coding regions from 17,052 human and 16,893 mouse genes. Three evaluation methods indicate that the entries in the CCDS set are highly likely to represent real proteins, more so than annotations from contributing groups not included in CCDS. The CCDS database thus centralizes the function of identifying well-supported, identically-annotated, protein-coding regions.}, 
URL = {http://genome.cshlp.org/content/19/7/1316.abstract}, 
eprint = {http://genome.cshlp.org/content/19/7/1316.full.pdf+html}, 
journal = {Genome Research} 
}