Transcript annotation in FANTOM3: mouse gene catalog based on physical cDNAs.

@article{citeulike:2491383, abstract = {The international FANTOM consortium aims to produce a comprehensive picture of the mammalian transcriptome, based upon an extensive cDNA collection and functional annotation of full-length enriched cDNAs. The previous dataset, FANTOM2, comprised 60,770 full-length enriched cDNAs. Functional annotation revealed that this cDNA dataset contained only about half of the estimated number of mouse protein-coding genes, indicating that a number of cDNAs still remained to be collected and identified. To pursue the complete gene catalog that covers all predicted mouse genes, cloning and sequencing of full-length enriched cDNAs has been continued since FANTOM2. In FANTOM3, 42,031 newly isolated cDNAs were subjected to functional annotation, and the annotation of 4,347 FANTOM2 cDNAs was updated. To accomplish accurate functional annotation, we improved our automated annotation pipeline by introducing new coding sequence prediction programs and developed a Web-based annotation interface for simplifying the annotation procedures to reduce manual annotation errors. Automated coding sequence and function prediction was followed with manual curation and review by expert curators. A total of 102,801 full-length enriched mouse cDNAs were annotated. Out of 102,801 transcripts, 56,722 were functionally annotated as protein coding (including partial or truncated transcripts), providing to our knowledge the greatest current coverage of the mouse proteome by full-length cDNAs. The total number of distinct non-protein-coding transcripts increased to 34,030. The FANTOM3 annotation system, consisting of automated computational prediction, manual curation, and final expert curation, facilitated the comprehensive characterization of the mouse transcriptome, and could be applied to the transcriptomes of other species.}, address = {Genome Science Laboratory, Discovery Research Institute, RIKEN Wako Institute, Wako, Japan. rgscerg@gsc.riken.jp}, author = {Maeda, N. and Kasukawa, T. and Oyama, R. and Gough, J. and Frith, M. and Engstr\"{o}m, P. G. and Lenhard, B. and Aturaliya, R. N. and Batalov, S. and Beisel, K. W. and Bult, C. J. and Fletcher, C. F. and Forrest, A. R. and Furuno, M. and Hill, D. and Itoh, M. and Kanamori-Katayama, M. and Katayama, S. and Katoh, M. and Kawashima, T. and Quackenbush, J. and Ravasi, T. and Ring, B. Z. and Shibata, K. and Sugiura, K. and Takenaka, Y. and Teasdale, R. D. and Wells, C. A. and Zhu, Y. and Kai, C. and Kawai, J. and Hume, D. A. and Carninci, P. and Hayashizaki, Y. }, citeulike-article-id = {2491383}, doi = {10.1371/journal.pgen.0020062}, issn = {1553-7404}, journal = {PLoS Genet}, keywords = {annotation, cdna, genome-wide, mouse, transcriptome}, month = {April}, number = {4}, posted-at = {2008-03-08 23:22:51}, priority = {2}, title = {Transcript annotation in FANTOM3: mouse gene catalog based on physical cDNAs.}, url = {http://dx.doi.org/10.1371/journal.pgen.0020062}, volume = {2}, year = {2006} }

TY - JOUR ID - citeulike:2491383 L3 - citeulike-article-id:2491383 TI - Transcript annotation in FANTOM3: mouse gene catalog based on physical cDNAs. JF - PLoS Genet VL - 2 IS - 4 AD - Genome Science Laboratory, Discovery Research Institute, RIKEN Wako Institute, Wako, Japan. rgscerg@gsc.riken.jp SN - 1553-7404 N2 - The international FANTOM consortium aims to produce a comprehensive picture of the mammalian transcriptome, based upon an extensive cDNA collection and functional annotation of full-length enriched cDNAs. The previous dataset, FANTOM2, comprised 60,770 full-length enriched cDNAs. Functional annotation revealed that this cDNA dataset contained only about half of the estimated number of mouse protein-coding genes, indicating that a number of cDNAs still remained to be collected and identified. To pursue the complete gene catalog that covers all predicted mouse genes, cloning and sequencing of full-length enriched cDNAs has been continued since FANTOM2. In FANTOM3, 42,031 newly isolated cDNAs were subjected to functional annotation, and the annotation of 4,347 FANTOM2 cDNAs was updated. To accomplish accurate functional annotation, we improved our automated annotation pipeline by introducing new coding sequence prediction programs and developed a Web-based annotation interface for simplifying the annotation procedures to reduce manual annotation errors. Automated coding sequence and function prediction was followed with manual curation and review by expert curators. A total of 102,801 full-length enriched mouse cDNAs were annotated. Out of 102,801 transcripts, 56,722 were functionally annotated as protein coding (including partial or truncated transcripts), providing to our knowledge the greatest current coverage of the mouse proteome by full-length cDNAs. The total number of distinct non-protein-coding transcripts increased to 34,030. The FANTOM3 annotation system, consisting of automated computational prediction, manual curation, and final expert curation, facilitated the comprehensive characterization of the mouse transcriptome, and could be applied to the transcriptomes of other species. KW - annotation KW - cdna KW - genome-wide KW - mouse KW - transcriptome AU - Maeda, N AU - Kasukawa, T AU - Oyama, R AU - Gough, J AU - Frith, M AU - Engström, PG AU - Lenhard, B AU - Aturaliya, RN AU - Batalov, S AU - Beisel, KW AU - Bult, CJ AU - Fletcher, CF AU - Forrest, AR AU - Furuno, M AU - Hill, D AU - Itoh, M AU - Kanamori-Katayama, M AU - Katayama, S AU - Katoh, M AU - Kawashima, T AU - Quackenbush, J AU - Ravasi, T AU - Ring, BZ AU - Shibata, K AU - Sugiura, K AU - Takenaka, Y AU - Teasdale, RD AU - Wells, CA AU - Zhu, Y AU - Kai, C AU - Kawai, J AU - Hume, DA AU - Carninci, P AU - Hayashizaki, Y PY - 2006/04// UR - http://dx.doi.org/10.1371/journal.pgen.0020062 ER -