@article{Carninci01062003,
author = {Carninci, Piero and Waki, Kazunori and Shiraki, Toshiyuki and Konno, Hideaki and Shibata, Kazuhiro and Itoh, Masayoshi and Aizawa, Katsunori and Arakawa, Takahiro and Ishii, Yoshiyuki and Sasaki, Daisuke and Bono, Hidemasa and Kondo, Shinji and Sugahara, Yuichi and Saito, Rintaro and Osato, Naoki and Fukuda, Shiro and Sato, Kenjiro and Watahiki, Akira and Hirozane-Kishikawa, Tomoko and Nakamura, Mari and Shibata, Yuko and Yasunishi, Ayako and Kikuchi, Noriko and Yoshiki, Atsushi and Kusakabe, Moriaki and Gustincich, Stefano and Beisel, Kirk and Pavan, William and Aidinis, Vassilis and Nakagawara, Akira and Held, William A. and Iwata, Hiroo and Kono, Tomohiro and Nakauchi, Hiromitsu and Lyons, Paul and Wells, Christine and Hume, David A. and Fagiolini, Michela and Hensch, Takao K. and Brinkmeier, Michelle and Camper, Sally and Hirota, Junji and Mombaerts, Peter and Muramatsu, Masami and Okazaki, Yasushi and Kawai, Jun and Hayashizaki, Yoshihide}, 
title = {Targeting a Complex Transcriptome: The Construction of the Mouse Full-Length cDNA Encyclopedia},
volume = {13}, 
number = {6b}, 
pages = {1273-1289}, 
year = {2003}, 
doi = {10.1101/gr.1119703}, 
abstract ={We report the construction of the mouse full-length cDNA encyclopedia,the  most extensive view of a complex transcriptome,on the basis of preparing and  sequencing 246 libraries. Before cloning,cDNAs were enriched in full-length by  Cap-Trapper,and in most cases,aggressively subtracted/normalized. We have  produced 1,442,236 successful 3′-end sequences clustered into 171,144  groups, from which 60,770 clones were fully sequenced cDNAs annotated in the  FANTOM-2 annotation. We have also produced 547,149 5′ end reads,which  clustered into 124,258 groups. Altogether, these cDNAs were further grouped in  70,000 transcriptional units (TU),which represent the best coverage of a  transcriptome so far. By monitoring the extent of normalization/subtraction,  we define the tentative equivalent coverage (TEC),which was estimated to be  equivalent to >12,000,000 ESTs derived from standard libraries. High  coverage explains discrepancies between the very large numbers of clusters  (and TUs) of this project,which also include non-protein-coding RNAs,and the  lower gene number estimation of genome annotations. Altogether,5′-end  clusters identify regions that are potential promoters for 8637 known genes  and 5′-end clusters suggest the presence of almost 63,000  transcriptional starting points. An estimate of the frequency of  polyadenylation signals suggests that at least half of the singletons in the  EST set represent real mRNAs. Clones accounting for about half of the  predicted TUs await further sequencing. The continued high-discovery rate  suggests that the task of transcriptome discovery is not yet complete.}, 
URL = {http://genome.cshlp.org/content/13/6b/1273.abstract}, 
eprint = {http://genome.cshlp.org/content/13/6b/1273.full.pdf+html}, 
journal = {Genome Research} 
}