@article{Vettore01122003,
author = {Vettore, André L. and da Silva, Felipe R. and Kemper, Edson L. and Souza, Glaucia M. and da Silva, Aline M. and Ferro, Maria Inês T. and Henrique-Silva, Flavio and Giglioti, Éder A. and Lemos, Manoel V.F. and Coutinho, Luiz L. and Nobrega, Marina P. and Carrer, Helaine and França, Suzelei C. and Bacci, Maurício and Goldman, Maria Helena S. and Gomes, Suely L. and Nunes, Luiz R. and Camargo, Luis E.A. and Siqueira, Walter J. and Van Sluys, Marie-Anne and Thiemann, Otavio H. and Kuramae, Eiko E. and Santelli, Roberto V. and Marino, Celso L. and Targon, Maria L.P.N. and Ferro, Jesus A. and Silveira, Henrique C.S. and Marini, Danyelle C. and Lemos, Eliana G.M. and Monteiro-Vitorello, Claudia B. and Tambor, José H.M. and Carraro, Dirce M. and Roberto, Patrícia G. and Martins, Vanderlei G. and Goldman, Gustavo H. and de Oliveira, Regina C. and Truffi, Daniela and Colombo, Carlos A. and Rossi, Magdalena and de Araujo, Paula G. and Sculaccio, Susana A. and Angella, Aline and Lima, Marleide M.A. and de Rosa, Vicente E. and Siviero, Fábio and Coscrato, Virginia E. and Machado, Marcos A. and Grivet, Laurent and Di Mauro, Sonia M.Z. and Nobrega, Francisco G. and Menck, Carlos F.M. and Braga, Marilia D.V. and Telles, Guilherme P. and Cara, Frank A.A. and Pedrosa, Guilherme and Meidanis, João and Arruda, Paulo}, 
title = {Analysis and Functional Annotation of an Expressed Sequence Tag Collection for Tropical Crop Sugarcane},
volume = {13}, 
number = {12}, 
pages = {2725-2735}, 
year = {2003}, 
doi = {10.1101/gr.1532103}, 
abstract ={To contribute to our understanding of the genome complexity of sugarcane, we undertook a large-scale expressed sequence tag (EST) program. More than 260,000 cDNA clones were partially sequenced from 26 standard cDNA libraries generated from different sugarcane tissues. After the processing of the sequences, 237,954 high-quality ESTs were identified. These ESTs were assembled into 43,141 putative transcripts. Of the assembled sequences, 35.6% presented no matches with existing sequences in public databases. A global analysis of the whole SUCEST data set indicated that 14,409 assembled sequences (33% of the total) contained at least one cDNA clone with a full-length insert. Annotation of the 43,141 assembled sequences associated almost 50% of the putative identified sugarcane genes with protein metabolism, cellular communication/signal transduction, bioenergetics, and stress responses. Inspection of the translated assembled sequences for conserved protein domains revealed 40,821 amino acid sequences with 1415 Pfam domains. Reassembling the consensus sequences of the 43,141 transcripts revealed a 22% redundancy in the first assembling. This indicated that possibly 33,620 unique genes had been identified and indicated that >90% of the sugarcane expressed genes were tagged.}, 
URL = {http://genome.cshlp.org/content/13/12/2725.abstract}, 
eprint = {http://genome.cshlp.org/content/13/12/2725.full.pdf+html}, 
journal = {Genome Research} 
}