{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T11:10:53Z","timestamp":1772017853301,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2010,9,1]],"date-time":"2010-09-01T00:00:00Z","timestamp":1283299200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat Rev Genet"],"published-print":{"date-parts":[[2010,9]]},"DOI":"10.1038\/nrg2857","type":"journal-article","created":{"date-parts":[[2010,8,18]],"date-time":"2010-08-18T11:30:11Z","timestamp":1282131011000},"page":"647-657","source":"Crossref","is-referenced-by-count":495,"title":["Computational solutions to large-scale data management and analysis"],"prefix":"10.1038","volume":"11","author":[{"given":"Eric E.","family":"Schadt","sequence":"first","affiliation":[]},{"given":"Michael D.","family":"Linderman","sequence":"additional","affiliation":[]},{"given":"Jon","family":"Sorenson","sequence":"additional","affiliation":[]},{"given":"Lawrence","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Garry P.","family":"Nolan","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"BFnrg2857_CR1","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1126\/science.1162986","volume":"323","author":"J Eid","year":"2009","unstructured":"Eid, J. et al. Real-time DNA sequencing from single polymerase molecules. Science 323, 133\u2013138 (2009).","journal-title":"Science"},{"key":"BFnrg2857_CR2","doi-asserted-by":"publisher","first-page":"6813","DOI":"10.1021\/ac901049w","volume":"81","author":"DR Bandura","year":"2009","unstructured":"Bandura, D. R. et al. Mass cytometry: technique for real time single cell multitarget immunoassay based on inductively coupled plasma time-of-flight mass spectrometry. Anal. Chem. 81, 6813\u20136822 (2009).","journal-title":"Anal. Chem."},{"key":"BFnrg2857_CR3","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/nature06757","volume":"452","author":"Y Chen","year":"2008","unstructured":"Chen, Y. et al. Variations in DNA elucidate molecular networks that cause disease. Nature 452, 429\u2013435 (2008).","journal-title":"Nature"},{"key":"BFnrg2857_CR4","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1038\/nature06758","volume":"452","author":"V Emilsson","year":"2008","unstructured":"Emilsson, V. et al. Genetics of gene expression and its effect on disease. Nature 452, 423\u2013428 (2008).","journal-title":"Nature"},{"key":"BFnrg2857_CR5","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1126\/science.1156409","volume":"322","author":"D Altshuler","year":"2008","unstructured":"Altshuler, D., Daly, M. J. & Lander, E. S. Genetic mapping in human disease. Science 322, 881\u2013888 (2008).","journal-title":"Science"},{"key":"BFnrg2857_CR6","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1181498","volume":"327","author":"R Drmanac","year":"2010","unstructured":"Drmanac, R. et al. Human genome sequencing using unchained base reads on self-assembling DNA nanoarrays. Science 327, 78\u201381 (2010).","journal-title":"Science"},{"key":"BFnrg2857_CR7","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1038\/nbt0510-426","volume":"28","author":"DJ Munroe","year":"2010","unstructured":"Munroe, D. J. & Harris, T. J. Third-generation sequencing fireworks at Marco Island. Nature Biotech. 28, 426\u2013428 (2010).","journal-title":"Nature Biotech."},{"key":"BFnrg2857_CR8","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1038\/nmeth.1459","volume":"7","author":"BA Flusberg","year":"2010","unstructured":"Flusberg, B. A. et al. Direct detection of DNA methylation during single-molecule, real-time sequencing. Nature Methods 7, 461\u2013465 (2010). Shows how SMRT sequencing will add an important time dimension to DNA and RNA sequencing data. Maximizing the information that can be derived from the data will demand substantially increased data-storage requirements and computational resources.","journal-title":"Nature Methods"},{"key":"BFnrg2857_CR9","volume-title":"Computers and Intractability: A Guide to the Theory of NP-Completeness","author":"MR Garey","year":"1979","unstructured":"Garey, M. R. & Johnson, D. S. Computers and Intractability: A Guide to the Theory of NP-Completeness (W. H. Freeman, New York, 1979)."},{"key":"BFnrg2857_CR10","doi-asserted-by":"publisher","first-page":"e107","DOI":"10.1371\/journal.pbio.0060107","volume":"6","author":"EE Schadt","year":"2008","unstructured":"Schadt, E. E. et al. Mapping the genetic architecture of gene expression in human liver. PLoS Biol. 6, e107 (2008).","journal-title":"PLoS Biol."},{"key":"BFnrg2857_CR11","volume-title":"MPI-The Complete Reference","author":"M Snir","year":"1998","unstructured":"Snir, M. MPI-The Complete Reference 2nd edn (MIT Press, Cambridge, Massachusetts, 1998)."},{"key":"BFnrg2857_CR12","doi-asserted-by":"publisher","first-page":"e1000642","DOI":"10.1371\/journal.pcbi.1000642","volume":"6","author":"W Zhang","year":"2010","unstructured":"Zhang, W., Zhu, J., Schadt, E. E. & Liu, J. S. A Bayesian partition method for detecting pleiotropic and epistatic eQTL modules. PLoS Comput. Biol. 6, e1000642 (2010).","journal-title":"PLoS Comput. Biol."},{"key":"BFnrg2857_CR13","doi-asserted-by":"publisher","first-page":"1694","DOI":"10.1126\/science.1177486","volume":"326","author":"EK Costello","year":"2009","unstructured":"Costello, E. K. et al. Bacterial community variation in human body habitats across space and time. Science 326, 1694\u20131697 (2009).","journal-title":"Science"},{"key":"BFnrg2857_CR14","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1186\/gb-2010-11-5-210","volume":"11","author":"J Kuczynski","year":"2010","unstructured":"Kuczynski, J. et al. Direct sequencing of the human microbiome readily reveals community differences. Genome Biol. 11, 210 (2010).","journal-title":"Genome Biol."},{"key":"BFnrg2857_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nature08821","volume":"464","author":"J Qin","year":"2010","unstructured":"Qin, J. et al. A human gut microbial gene catalogue established by metagenomic sequencing. Nature 464, 59\u201365 (2010).","journal-title":"Nature"},{"key":"BFnrg2857_CR16","doi-asserted-by":"publisher","first-page":"W20","DOI":"10.1093\/nar\/gkh435","volume":"32","author":"S McGinnis","year":"2004","unstructured":"McGinnis, S. & Madden, T. L. BLAST: at the core of a powerful and diverse set of sequence analysis tools. Nucleic Acids Res. 32, W20\u2013W25 (2004).","journal-title":"Nucleic Acids Res."},{"key":"BFnrg2857_CR17","volume-title":"Above the Clouds: A Berkeley View of Cloud Computing","author":"M Armbrust","year":"2009","unstructured":"Armbrust, M. et al. Above the Clouds: A Berkeley View of Cloud Computing (University of California, Berkeley, 2009)."},{"key":"BFnrg2857_CR18","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/j.future.2008.12.001","volume":"25","author":"R Buyya","year":"2009","unstructured":"Buyya, R., Yeo, C. S., Venugopal, S., Broberg, J. & Brandic, I. Cloud computing and emerging IT platforms: vision, hype, and reality for delivering computing as the 5th utility. Future Generation Comput. Syst. 25, 599\u2013616 (2009).","journal-title":"Future Generation Comput. Syst."},{"key":"BFnrg2857_CR19","volume-title":"6th Symp. on Operating Systems Design and Implementation","author":"J Dean","year":"2004","unstructured":"Dean, J. & Ghemawat, S. MapReduce: simplified data processing on large clusters. 6th Symp. on Operating Systems Design and Implementation [online] , (2004). Introduces the MapReduce concept, which was developed at Google. MapReduce is one of the leading large-scale parallel computing technologies, both in terms of the size of data it can handle and the size of the computational infrastructure that is available to process such data."},{"key":"BFnrg2857_CR20","first-page":"222","volume-title":"4th IEEE International Conference on eScience","author":"A Matsunaga","year":"2008","unstructured":"Matsunaga, A., Tsugawa, M. & Fortes, J. in 4th IEEE International Conference on eScience. 222\u2013229 (IEEE, Indianapolis, Indiana, 2008)."},{"key":"BFnrg2857_CR21","doi-asserted-by":"publisher","first-page":"R134","DOI":"10.1186\/gb-2009-10-11-r134","volume":"10","author":"B Langmead","year":"2009","unstructured":"Langmead, B., Schatz, M. C., Lin, J., Pop, M. & Salzberg, S. L. Searching for SNPs with cloud computing. Genome Biol. 10, R134 (2009). An early example in genomics of using standard cloud-based services to detect SNPs \u2014 in this case, by aligning whole-genome sequence data to a reference genome.","journal-title":"Genome Biol."},{"key":"BFnrg2857_CR22","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1093\/bioinformatics\/btp236","volume":"25","author":"MC Schatz","year":"2009","unstructured":"Schatz, M. C. CloudBurst: highly sensitive read mapping with MapReduce. Bioinformatics 25, 1363\u20131369 (2009).","journal-title":"Bioinformatics"},{"key":"BFnrg2857_CR23","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1038\/nbt0110-13","volume":"28","author":"C Sansom","year":"2010","unstructured":"Sansom, C. Up in a cloud? Nature Biotech. 28, 13\u201315 (2010).","journal-title":"Nature Biotech."},{"key":"BFnrg2857_CR24","first-page":"B1","volume-title":"New York Times","author":"A Vance","year":"2009","unstructured":"Vance, A. Training to climb an Everest of digital data. New York Times B1 (11 Oct 2009)."},{"key":"BFnrg2857_CR25","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1038\/nrg2414","volume":"9","author":"LD Stein","year":"2008","unstructured":"Stein, L. D. Towards a cyberinfrastructure for the biological sciences: progress, visions and challenges. Nature Rev. Genet. 9, 678\u2013688 (2008). A comprehensive review of the informatics infrastructure that will be required to achieve success in biological research, both now and in the future.","journal-title":"Nature Rev. Genet."},{"key":"BFnrg2857_CR26","doi-asserted-by":"publisher","first-page":"e1000309","DOI":"10.1371\/journal.pbio.1000309","volume":"8","author":"H Constable","year":"2010","unstructured":"Constable, H., Guralnick, R., Wieczorek, J., Spencer, C. & Peterson, A. T. VertNet: a new model for biodiversity data sharing. PLoS Biol. 8, e1000309 (2010).","journal-title":"PLoS Biol."},{"key":"BFnrg2857_CR27","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.jbi.2009.08.014","volume":"43","author":"A Rosenthal","year":"2009","unstructured":"Rosenthal, A. et al. Cloud computing: a new business paradigm for biomedical information sharing. J. Biomed. Inform. 43, 342\u2013353 (2009).","journal-title":"J. Biomed. Inform."},{"key":"BFnrg2857_CR28","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","volume":"26","author":"JD Owens","year":"2007","unstructured":"Owens, J. D. et al. A survey of general-purpose computation on graphics hardware. Comput. Graph. Forum 26, 80\u2013113 (2007).","journal-title":"Comput. Graph. Forum"},{"key":"BFnrg2857_CR29","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1002\/jcc.21209","volume":"30","author":"MS Friedrichs","year":"2009","unstructured":"Friedrichs, M. S. et al. Accelerating molecular dynamic simulation on graphics processing units. J. Comput. Chem. 30, 864\u2013872 (2009).","journal-title":"J. Comput. Chem."},{"key":"BFnrg2857_CR30","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1002\/jcc.21054","volume":"30","author":"E Luttmann","year":"2009","unstructured":"Luttmann, E. et al. Accelerating molecular dynamic simulation on the cell processor and Playstation 3. J. Comput. Chem. 30, 268\u2013274 (2009).","journal-title":"J. Comput. Chem."},{"key":"BFnrg2857_CR31","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1186\/1471-2105-8-474","volume":"8","author":"MC Schatz","year":"2007","unstructured":"Schatz, M. C., Trapnell, C., Delcher, A. L. & Varshney, A. High-throughput sequence alignment using Graphics Processing Units. BMC Bioinformatics 8, 474 (2007). One of the first genomics applications to use GPUs to substantially speed up the process of high-throughput sequence alignments.","journal-title":"BMC Bioinformatics"},{"key":"BFnrg2857_CR32","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/1756-0500-2-73","volume":"2","author":"Y Liu","year":"2009","unstructured":"Liu, Y., Maskell, D. L. & Schmidt, B. CUDASW++: optimizing Smith\u2013Waterman sequence database searches for CUDA-enabled graphics processing units. BMC Res. Notes 2, 73 (2009).","journal-title":"BMC Res. Notes"},{"key":"BFnrg2857_CR33","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1093\/bioinformatics\/btp157","volume":"25","author":"EP Nawrocki","year":"2009","unstructured":"Nawrocki, E. P., Kolbe, D. L. & Eddy, S. R. Infernal 1.0: inference of RNA alignments. Bioinformatics 25, 1335\u20131337 (2009). One of the first GPU-based RNA sequence aligners.","journal-title":"Bioinformatics"},{"key":"BFnrg2857_CR34","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/1810085.1810101","volume-title":"Proc. of the 24th ACM Int. Conf. on Supercomputing (Tsukuba, Ibaraki, Japan; 2\u20134 Jun 2010)","author":"MD Linderman","year":"2010","unstructured":"Linderman, M. D. et al. High-throughput Bayesian network learning using heterogeneous multicore computers. in Proc. of the 24th ACM Int. Conf. on Supercomputing (Tsukuba, Ibaraki, Japan; 2\u20134 Jun 2010). 95\u2013104, http:\/\/doi.acm.org\/10.1145\/1810085.1810101 (ACM, New York, 2010). Describes a high-throughput GPU-based application for Bayesian network learning. The network learner was built with a novel software tool, the Merge compiler, that helps programmers to integrate multiple implementations of the same algorithm, targeting different processors, into a single application that optimally chooses at run-time which implementation to use based on the problem and hardware available."},{"key":"BFnrg2857_CR35","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J Nickolls","year":"2008","unstructured":"Nickolls, J., Buck, I., Garland, M. & Skadron, K. Scalable parallel programming with CUDA. Queue 6, 40\u201353 (2008).","journal-title":"Queue"},{"key":"BFnrg2857_CR36","unstructured":"Zhang, B. & Horvath, S. A general framework for weighted gene co-expression network analysis. Stat. Appl. Genet. Mol. Biol. 4, Article17 (2005)."},{"key":"BFnrg2857_CR37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-01722-3","volume-title":"The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines","author":"LA Barroso","year":"2009","unstructured":"Barroso, L. A. & Holzle, U. The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines. 1\u2013108 (Morgan & Claypool Publishers, 2009). Highlights the important future role of large-scale data centres in hosting big data sets and facilitating computing on those sets."},{"key":"BFnrg2857_CR38","volume-title":"Microsoft Research","author":"G Bell","year":"2005","unstructured":"Bell, G. & Gray, J. Petascale computational systems: balanced cyberinfrastructure in a data-centric world Microsoft Research [online] , (2005)."},{"key":"BFnrg2857_CR39","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1038\/ng.167","volume":"40","author":"J Zhu","year":"2008","unstructured":"Zhu, J. et al. Integrating large-scale functional genomic data to dissect the complexity of yeast regulatory networks. Nature Genet. 40, 854\u2013861 (2008). An example of an integrative genomics network-reconstruction method that is among the most computationally demanding methods in biological research.","journal-title":"Nature Genet."},{"key":"BFnrg2857_CR40","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1038\/nrd2826","volume":"8","author":"EE Schadt","year":"2009","unstructured":"Schadt, E. E., Friend, S. H. & Shaywitz, D. A. A network view of disease and compound screening. Nature Rev. Drug Discov. 8, 286\u2013295 (2009).","journal-title":"Nature Rev. Drug Discov."}],"container-title":["Nature Reviews Genetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.nature.com\/articles\/nrg2857.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/nrg2857","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.nature.com\/articles\/nrg2857.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T22:20:10Z","timestamp":1685744410000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/nrg2857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,9]]},"references-count":40,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2010,9]]}},"alternative-id":["BFnrg2857"],"URL":"https:\/\/doi.org\/10.1038\/nrg2857","relation":{},"ISSN":["1471-0056","1471-0064"],"issn-type":[{"value":"1471-0056","type":"print"},{"value":"1471-0064","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,9]]}}}