{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T08:05:07Z","timestamp":1725869107162},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319448800"},{"type":"electronic","value":"9783319448817"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-44881-7_13","type":"book-chapter","created":{"date-parts":[[2016,10,27]],"date-time":"2016-10-27T03:11:13Z","timestamp":1477537873000},"page":"265-277","source":"Crossref","is-referenced-by-count":0,"title":["Big Biological Data Management"],"prefix":"10.1007","author":[{"given":"Edvard","family":"Pedersen","sequence":"first","affiliation":[]},{"given":"Lars Ailo","family":"Bongo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,28]]},"reference":[{"issue":"2","key":"13_CR1","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1145\/2845915","volume":"59","author":"D Abadi","year":"2016","unstructured":"Abadi, D., Agrawal, R., Ailamaki, A., Balazinska, M., Bernstein, P.A., Carey, M.J., Chaudhuri, S., Chaudhuri, S., Dean, J., Doan, A., Franklin, M.J., Gehrke, J., Haas, L.M., Halevy, A.Y., Hellerstein, J.M., Ioannidis, Y.E., Jagadish, H.V., Kossmann, D., Madden, S., Mehrotra, S., Milo, T., Naughton, J.F., Ramakrishnan, R., Markl, V., Olston, C., Ooi, B.C., R\u00e9, C., Suciu, D., Stonebraker, M., Walter, T., Widom, J.: The beckman report on database research. Commun. ACM 59(2), 92\u201399 (2016)","journal-title":"Commun. ACM"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Abu-Doleh, A., Atalyrek, V.: Spaler: Spark and graphx based de novo genome assembler. In: 2015 IEEE International Conference on Big Data (Big Data), pp. 1013\u20131018 (2015)","DOI":"10.1109\/BigData.2015.7363853"},{"key":"13_CR3","unstructured":"Apache: Apache HBase. http:\/\/hbase.apache.org . Cited 18 April 2016"},{"key":"13_CR4","unstructured":"Apache: Avro. http:\/\/avro.apache.org . Cited 18 April 2016"},{"key":"13_CR5","unstructured":"Apache: Cassandra. http:\/\/cassandra.apache.org . Cited 18-April-2016"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Bhatotia, P., Wieder, A., Rodrigues, R., Acar, U.A., Pasquini, R.: Incoop: MapReduce for Incremental Computations. In: Proceedings of the 2nd ACM Symposium on Cloud Computing, p.\u00a07. ACM Press (2011)","DOI":"10.1145\/2038916.2038923"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Bongo, L.A., Pedersen, E., Ernstsen, M.: Data-intensive computing infrastructure systems for unmodified biological data analysis pipelines. In: Computational Intelligence Methods for Bioinformatics and Biostatistics, LNBI, vol. 8623 (2014)","DOI":"10.1007\/978-3-319-24462-4_22"},{"issue":"1","key":"13_CR8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce. Commun. ACM 51(1), 107 (2008)","journal-title":"Commun. ACM"},{"key":"13_CR9","unstructured":"Diao, Y., Roy, A., Bloom, T.: Building highly-optimized, low-latency pipelines for genomic data analysis. In: Proceedings of 7th Biennial Conference on Innovative Data Systems Research (2015)"},{"issue":"1","key":"13_CR10","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1093\/nar\/30.1.207","volume":"30","author":"R Edgar","year":"2002","unstructured":"Edgar, R., Domrachev, M., Lash, A.E.: Gene expression omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res. 30(1), 207\u2013210 (2002)","journal-title":"Nucleic Acids Res."},{"key":"13_CR11","unstructured":"EMBL-European Bioinformatics Institute: EMBL-EBI Annual Scientific Report 2014. http:\/\/www.ebi.ac.uk\/about\/brochures . Cited 18 April 2016"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Su\u00e1rez, X.M., Rigden, D.J., Galperin, M.Y.: The 2014 nucleic acids research database issue and an updated NAR online molecular biology database collection. Nucleic Acids Res. 42(Database issue), D1\u20136 (2014)","DOI":"10.1093\/nar\/gkt1282"},{"key":"13_CR13","unstructured":"Fitzpatrick, B.: Distributed caching with memcached. Linux J. 2004(124), 5 (2004)"},{"issue":"10","key":"13_CR14","doi-asserted-by":"crossref","first-page":"R80","DOI":"10.1186\/gb-2004-5-10-r80","volume":"5","author":"RC Gentleman","year":"2004","unstructured":"Gentleman, R.C., Carey, V.J., Bates, D.M., Bolstad, B., Dettling, M., Dudoit, S., Ellis, B., Gautier, L., Ge, Y., Gentry, J., Hornik, K., Hothorn, T., Huber, W., Iacus, S., Irizarry, R., Leisch, F., Li, C., Maechler, M., Rossini, A.J., Sawitzki, G., Smith, C., Smyth, G., Tierney, L., Yang, J.Y.H., Zhang, J.: Bioconductor: open software development for computational biology and bioinformatics. Genome Biol. 5(10), R80 (2004)","journal-title":"Genome Biol."},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.T.: The google file system. In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles. SOSP \u201903, pp. 29\u201343. ACM, New York, NY, USA (2003)","DOI":"10.1145\/945445.945450"},{"issue":"8","key":"13_CR16","doi-asserted-by":"crossref","first-page":"R86","DOI":"10.1186\/gb-2010-11-8-r86","volume":"11","author":"J Goecks","year":"2010","unstructured":"Goecks, J., Nekrutenko, A., Taylor, J.: Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences. Genome Biol. 11(8), R86 (2010)","journal-title":"Genome Biol."},{"key":"13_CR17","unstructured":"Gonzalez, J.E., Xin, R.S., Dave, A., Crankshaw, D., Franklin, M.J., Stoica, I.: Graphx: Graph processing in a distributed dataflow framework. In: 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14), pp. 599\u2013613. USENIX Association, Broomfield, CO (2014)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, A., Agarwal, D., Tan, D., Kulesza, J., Pathak, R., Stefani, S., Srinivasan, V.: Amazon redshift and the case for simpler data warehouses. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201915, pp. 1917\u20131923. ACM, New York, NY, USA (2015)","DOI":"10.1145\/2723372.2742795"},{"issue":"24","key":"13_CR19","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.1093\/bioinformatics\/btt549","volume":"29","author":"CT Have","year":"2013","unstructured":"Have, C.T., Jensen, L.J.: Are graph databases ready for bioinformatics? Bioinformatics 29(24), 3107\u20133108 (2013)","journal-title":"Bioinformatics"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Kornacker, M., Behm, A., Bittorf, V., Bobrovytsky, T., Ching, C., Choi, A., Erickson, J., Grund, M., Hecht, D., Jacobs, M., Joshi, I., Kuff, L., Kumar, D., Leblang, A., Li, N., Pandis, I., Robinson, H., Rorke, D., Rus, S., Russell, J., Tsirogiannis, D., Wanderman-Milne, S., Yoder, M.: Impala: A modern, open-source sql engine for hadoop. In: CIDR. www.cidrdb.org (2015)","DOI":"10.1007\/978-3-658-11589-0_8"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Kovatch, P., Costa, A., Giles, Z., Fluder, E., Cho, H.M., Mazurkova, S.: Big omics data experience. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC \u201915, pp. 39:1\u201339:12. ACM, New York, NY, USA (2015)","DOI":"10.1145\/2807591.2807595"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Leinonen, R., Akhtar, R., Birney, E., Bower, L., Cerdeno-T\u00e1rraga, A., Cheng, Y., Cleland, I., Faruque, N., Goodgame, N., Gibson, R., Hoad, G., Jang, M., Pakseresht, N., Plaister, S., Radhakrishnan, R., Reddy, K., Sobhany, S., Hoopen, P.T., Vaughan, R., Zalunin, V., Cochrane, G.: The European nucleotide archive. Nucleic Acids Res. 39(SUPPL. 1) (2011)","DOI":"10.1093\/nar\/gkq967"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Leipzig, J.: A review of bioinformatic pipeline frameworks. Briefings in Bioinformatics (2016)","DOI":"10.1093\/bib\/bbw020"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: A system for large-scale graph processing. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201910, pp. 135\u2013146. ACM, New York, NY, USA (2010)","DOI":"10.1145\/1807167.1807184"},{"issue":"1\u20132","key":"13_CR25","doi-asserted-by":"crossref","first-page":"330","DOI":"10.14778\/1920841.1920886","volume":"3","author":"S Melnik","year":"2010","unstructured":"Melnik, S., Gubarev, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. Proc. VLDB Endowment 3(1\u20132), 330\u2013339 (2010)","journal-title":"Proc. VLDB Endowment"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Nothaft, F.A., Massie, M., Danford, T., Zhang, Z., Laserson, U., Yeksigian, C., Kottalam, J., Ahuja, A., Hammerbacher, J., Linderman, M., Franklin, M.J., Joseph, A.D., Patterson, D.A.: Rethinking data-intensive science using scalable analytics systems. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201915, pp. 631\u2013646. ACM, New York, NY, USA (2015)","DOI":"10.1145\/2723372.2742787"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Olston, C., Chopra, S., Srivastava, U.: Generating example data for dataflow programs. In: Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201909, pp. 245\u2013256. ACM, New York, NY, USA (2009)","DOI":"10.1145\/1559845.1559873"},{"key":"13_CR28","unstructured":"Oracle: MySQL. http:\/\/www.mysql.com . Cited 18 April 2016"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Pedersen, E., Bongo, L.A.: Large-scale biological meta-database management. In: Future Generation Computer Systems (2016)","DOI":"10.1016\/j.future.2016.02.010"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Pedersen, E., Raknes, I.A., Ernstsen, M., Bongo, L.A.: Integrating data-intensive computing systems with biological data analysis frameworks. In: Proceedings of 23rd Euromicro International Conference on Parallel, Distributed and Network-based Processing, pp. 733\u2013740. IEEE (2015)","DOI":"10.1109\/PDP.2015.106"},{"key":"13_CR31","unstructured":"Robertsen, E.M., Kahlke, T., Raknes, I.A., Pedersen, E., Semb, E.K., Ernstsen, M., Bongo, L.A., Willassen, N.P.: Meta-pipe - pipeline annotation, analysis and visualization of marine metagenomic sequence data. arXiv:1604.04103 (2016)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Schildgen, J., Jorg, T., Hoffmann, M., Dessloch, S.: Marimba: A framework for making mapreduce jobs incremental. In: 2014 IEEE International Congress on Big Data, pp. 128\u2013135. IEEE (2014)","DOI":"10.1109\/BigData.Congress.2014.27"},{"key":"13_CR33","unstructured":"Schmuck, F., Haskin, R.: Gpfs: A shared-disk file system for large computing clusters. In: Proceedings of the 1st USENIX Conference on File and Storage Technologies, FAST \u201902. USENIX Association, Berkeley, CA, USA (2002)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In: 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies 0(5), 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"issue":"10","key":"13_CR35","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1101\/gr.361602","volume":"12","author":"JE Stajich","year":"2002","unstructured":"Stajich, J.E., Block, D., Boulez, K., Brenner, S.E., Chervitz, S.A., Dagdigian, C., Fuellen, G., Gilbert, J.G.R., Korf, I., Lapp, H., Lehv\u00e4slaiho, H., Matsalla, C., Mungall, C.J., Osborne, B.I., Pocock, M.R., Schattner, P., Senger, M., Stein, L.D., Stupka, E., Wilkinson, M.D., Birney, E.: The Bioperl toolkit: Perl modules for the life sciences. Genome Res. 12(10), 1611\u20131618 (2002)","journal-title":"Genome Res."},{"key":"13_CR36","unstructured":"Twitter, and Cloudera: Parquet. http:\/\/www.parquet.io . Cited 18 April 2016"},{"key":"13_CR37","unstructured":"UniProt Consortium: UniProt release 201504. http:\/\/www.uniprot.org\/help\/2015\/04\/01\/release . Cited 18-April-2016"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Wang, D.L., Monkewitz, S.M., Lim, K.T., Becla, J.: Qserv: A distributed shared-nothing database for the lsst catalog. In: State of the Practice Reports, SC \u201911, pp. 12:1\u201312:11. ACM, New York, NY, USA (2011)","DOI":"10.1145\/2063348.2063364"},{"key":"13_CR39","unstructured":"Wetterstrand, K.: DNA Sequencing Costs: Data from the NHGRI Genome Sequencing Program (GSP). http:\/\/www.genome.gov\/sequencingcosts . Cited 18-April-2016"},{"key":"13_CR40","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster Computing with Working Sets. In: Proceedings of the 2nd USENIX conference on Hot topics in cloud computing, p.\u00a010 (2010)"}],"container-title":["Computer Communications and Networks","Resource Management for Big Data Platforms"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-44881-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T22:39:03Z","timestamp":1568500743000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-44881-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319448800","9783319448817"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-44881-7_13","relation":{},"ISSN":["1617-7975","2197-8433"],"issn-type":[{"type":"print","value":"1617-7975"},{"type":"electronic","value":"2197-8433"}],"subject":[],"published":{"date-parts":[[2016]]}}}