Petabyte-scale innovations at the European Nucleotide Archive. Export

@article{citeulike:3781645, abstract = {Dramatic increases in the throughput of nucleotide sequencing machines, and the promise of ever greater performance, have thrust bioinformatics into the era of petabyte-scale data sets. Sequence repositories, which provide the feed for these data sets into the worldwide computational infrastructure, are challenged by the impact of these data volumes. The European Nucleotide Archive (ENA; http://www.ebi.ac.uk/embl), comprising the EMBL Nucleotide Sequence Database and the Ensembl Trace Archive, has identified challenges in the storage, movement, analysis, interpretation and visualization of petabyte-scale data sets. We present here our new repository for next generation sequence data, a brief summary of contents of the ENA and provide details of major developments to submission pipelines, high-throughput rule-based validation infrastructure and data integration approaches.}, author = {Cochrane, Guy and Akhtar, Ruth and Bonfield, James and Bower, Lawrence and Demiralp, Fehmi and Faruque, Nadeem and Gibson, Richard and Hoad, Gemma and Hubbard, Tim and Hunter, Christopher and Jang, Mikyung and Juhos, Szilveszter and Leinonen, Rasko and Leonard, Steven and Lin, Quan and Lopez, Rodrigo and Lorenc, Dariusz and McWilliam, Hamish and Mukherjee, Gaurab and Plaister, Sheila and Radhakrishnan, Rajesh and Robinson, Stephen and Sobhany, Siamak and Hoopen, Petra Ten T. and Vaughan, Robert and Zalunin, Vadim and Birney, Ewan}, citeulike-article-id = {3781645}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/gkn765}, citeulike-linkout-1 = {http://nar.oxfordjournals.org/cgi/content/abstract/37/suppl_1/D19}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/18978013}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=18978013}, doi = {10.1093/nar/gkn765}, issn = {1362-4962}, journal = {Nucleic acids research}, keywords = {database, embl}, month = {January}, number = {Database issue}, pages = {D19--25}, posted-at = {2009-01-09 23:21:00}, priority = {2}, title = {Petabyte-scale innovations at the European Nucleotide Archive.}, url = {http://dx.doi.org/10.1093/nar/gkn765}, volume = {37}, year = {2009} }

TY - JOUR ID - citeulike:3781645 L3 - citeulike-article-id:3781645 N2 - Dramatic increases in the throughput of nucleotide sequencing machines, and the promise of ever greater performance, have thrust bioinformatics into the era of petabyte-scale data sets. Sequence repositories, which provide the feed for these data sets into the worldwide computational infrastructure, are challenged by the impact of these data volumes. The European Nucleotide Archive (ENA; http://www.ebi.ac.uk/embl), comprising the EMBL Nucleotide Sequence Database and the Ensembl Trace Archive, has identified challenges in the storage, movement, analysis, interpretation and visualization of petabyte-scale data sets. We present here our new repository for next generation sequence data, a brief summary of contents of the ENA and provide details of major developments to submission pipelines, high-throughput rule-based validation infrastructure and data integration approaches. IS - Database issue JF - Nucleic acids research SN - 1362-4962 EP - 25 TI - Petabyte-scale innovations at the European Nucleotide Archive. VL - 37 SP - D19 KW - database KW - embl AU - Cochrane, Guy AU - Akhtar, Ruth AU - Bonfield, James AU - Bower, Lawrence AU - Demiralp, Fehmi AU - Faruque, Nadeem AU - Gibson, Richard AU - Hoad, Gemma AU - Hubbard, Tim AU - Hunter, Christopher AU - Jang, Mikyung AU - Juhos, Szilveszter AU - Leinonen, Rasko AU - Leonard, Steven AU - Lin, Quan AU - Lopez, Rodrigo AU - Lorenc, Dariusz AU - McWilliam, Hamish AU - Mukherjee, Gaurab AU - Plaister, Sheila AU - Radhakrishnan, Rajesh AU - Robinson, Stephen AU - Sobhany, Siamak AU - Hoopen, Petra Ten AU - Vaughan, Robert AU - Zalunin, Vadim AU - Birney, Ewan PY - 2009/01/01/ UR - http://dx.doi.org/10.1093/nar/gkn765 ER -