{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T06:03:59Z","timestamp":1648793039756},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,10,21]],"date-time":"2016-10-21T00:00:00Z","timestamp":1477008000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s40537-016-0055-2","type":"journal-article","created":{"date-parts":[[2016,10,20]],"date-time":"2016-10-20T23:17:21Z","timestamp":1477005441000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Data-aware optimization of bioinformatics workflows in hybrid clouds"],"prefix":"10.1186","volume":"3","author":[{"given":"Athanassios M.","family":"Kintsakis","sequence":"first","affiliation":[]},{"given":"Fotis E.","family":"Psomopoulos","sequence":"additional","affiliation":[]},{"given":"Pericles A.","family":"Mitkas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,21]]},"reference":[{"issue":"Suppl 12","key":"55_CR1","doi-asserted-by":"crossref","first-page":"S4","DOI":"10.1186\/1471-2105-11-S12-S4","volume":"11","author":"E Afgan","year":"2010","unstructured":"Afgan E, Baker D, Coraor N, Chapman B, Nekrutenko A, Taylor J. Galaxy cloudman: delivering cloud compute clusters. BMC Bioinform. 2010;11(Suppl 12):S4.","journal-title":"BMC Bioinform"},{"issue":"3","key":"55_CR2","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. Basic local alignment search tool. J Mol Biol. 1990;215(3):403\u201310.","journal-title":"J Mol Biol"},{"issue":"1","key":"55_CR3","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1186\/1471-2105-12-356","volume":"12","author":"SV Angiuoli","year":"2011","unstructured":"Angiuoli SV, Matalka M, Gussman A, Galens K, Vangala M, Riley DR, Arze C, White JR, White O, Fricke WF. Clovr: a virtual machine for automated and portable sequence analysis from the desktop using cloud computing. BMC Bioinform. 2011;12(1):356.","journal-title":"BMC Bioinform"},{"key":"55_CR4","volume-title":"Principles of sequencing and scheduling","author":"KR Baker","year":"2013","unstructured":"Baker KR, Trietsch D. Principles of sequencing and scheduling. Hoboken: Wiley; 2013."},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, K\u00f6tter T, Meinl T, Ohl P, Sieb C, Thiel K, Wiswedel B. Knime: the konstanz information miner. In: Data analysis, machine learning and applications. Berlin: Springer; 2008. p. 319\u201326","DOI":"10.1007\/978-3-540-78246-9_38"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Bocchi E, Mellia M, Sarni S. Cloud storage service benchmarking: methodologies and experimentations. In: Cloud networking (CloudNet), 2014 IEEE 3rd international conference on, IEEE; 2014. p. 395\u2013400","DOI":"10.1109\/CloudNet.2014.6969027"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Brandes U, Eiglsperger M, Herman I, Himsolt M, Marshall MS. Graphml progress report structural layer proposal. In: Graph drawing. Berlin: Springer; 2001. p. 501\u201312","DOI":"10.1007\/3-540-45848-4_59"},{"key":"55_CR8","unstructured":"Bux M, Leser U. Parallelization in scientific workflow management systems. 2013. arXiv preprint arXiv:1303.7195"},{"issue":"21","key":"55_CR9","doi-asserted-by":"crossref","first-page":"2732","DOI":"10.1093\/bioinformatics\/bts482","volume":"28","author":"Z Chong","year":"2012","unstructured":"Chong Z, Ruan J, Wu CI. Rainbow: an integrated tool for efficient clustering and assembling rad-seq reads. Bioinformatics. 2012;28(21):2732\u20137.","journal-title":"Bioinformatics"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Consortium U, et al. The universal protein resource (uniprot). Nucleic Acids Res. 2008;36(suppl 1):D190\u20135.","DOI":"10.1093\/nar\/gkm895"},{"issue":"7","key":"55_CR11","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1016\/j.future.2012.12.019","volume":"29","author":"D Oliveira De","year":"2013","unstructured":"De Oliveira D, Oca\u00f1a KA, Ogasawara E, Dias J, Gon\u00e7alves J, Bai\u00e3o F, Mattoso M. Performance evaluation of parallel strategies in public clouds: a study with phylogenomic workflows. Future Gener Comput Syst. 2013;29(7):1816\u201325.","journal-title":"Future Gener Comput Syst"},{"issue":"1","key":"55_CR12","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: simplified data processing on large clusters. Commun ACM. 2008;51(1):107\u201313.","journal-title":"Commun ACM"},{"issue":"3","key":"55_CR13","first-page":"219","volume":"13","author":"E Deelman","year":"2005","unstructured":"Deelman E, Singh G, Su MH, Blythe J, Gil Y, Kesselman C, Mehta G, Vahi K, Berriman GB, Good J, et al. Pegasus: a framework for mapping complex scientific workflows onto distributed systems. Sci Progr. 2005;13(3):219\u201337.","journal-title":"Sci Progr"},{"key":"55_CR14","doi-asserted-by":"crossref","unstructured":"Duarte AM, Psomopoulos FE, Blanchet C, Bonvin AM, Corpas M, Franc A, Jimenez RC, de\u00a0Lucas JM, Nyr\u00f6nen T, Sipos G, et\u00a0al. Future opportunities and trends for e-infrastructures and life sciences: going beyond the grid to enable life science data analysis. Front Genet. 2015:6.","DOI":"10.3389\/fgene.2015.00197"},{"issue":"3","key":"55_CR15","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s10723-013-9260-9","volume":"11","author":"VC Emeakaroha","year":"2013","unstructured":"Emeakaroha VC, Maurer M, Stern P, \u0141abaj PP, Brandic I, Kreil DP. Managing and optimizing bioinformatics workflows for data analysis in clouds. J Grid Comput. 2013;11(3):407\u201328.","journal-title":"J Grid Comput"},{"issue":"10","key":"55_CR16","doi-asserted-by":"crossref","first-page":"R80","DOI":"10.1186\/gb-2004-5-10-r80","volume":"5","author":"RC Gentleman","year":"2004","unstructured":"Gentleman RC, Carey VJ, Bates DM, Bolstad B, Dettling M, Dudoit S, Ellis B, Gautier L, Ge Y, Gentry J, et al. Bioconductor: open software development for computational biology and bioinformatics. Genome Biol. 2004;5(10):R80.","journal-title":"Genome Biol"},{"issue":"8","key":"55_CR17","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, et al. Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences. Genome Biol. 2010;11(8):R86.","journal-title":"Genome Biol"},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Gurtowski J, Schatz MC, Langmead B. Genotyping in the cloud with crossbow. Curr Prot Bioinform. 2012:15\u20133.","DOI":"10.1002\/0471250953.bi1503s39"},{"key":"55_CR19","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MC.2008.209","volume":"7","author":"MD Hill","year":"2008","unstructured":"Hill MD, Marty MR. Amdahl\u2019s law in the multicore era. Computer. 2008;7:33\u20138.","journal-title":"Computer"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Iosup A, Sonmez O, Anoep S, Epema D. The performance of bags-of-tasks in large-scale distributed systems. In: Proceedings of the 17th international symposium on high performance distributed computing. New York: ACM; 2008. p. 97\u2013108","DOI":"10.1145\/1383422.1383435"},{"key":"55_CR21","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/MIC.2013.43","volume":"3","author":"V Koukis","year":"2013","unstructured":"Koukis V, Venetsanopoulos C, Koziris N. $${\\sim }$$ \u223c Okeanos: Building a cloud, cluster by cluster. IEEE Internet Comput. 2013;3:67\u201371.","journal-title":"IEEE Internet Comput"},{"issue":"1","key":"55_CR22","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/1471-2105-13-42","volume":"13","author":"K Krampis","year":"2012","unstructured":"Krampis K, Booth T, Chapman B, Tiwari B, Bicak M, Field D, Nelson KE. Cloud biolinux: pre-configured and on-demand bioinformatics computing for the genomics community. BMC Bioinform. 2012;13(1):42.","journal-title":"BMC Bioinform"},{"key":"55_CR23","doi-asserted-by":"crossref","unstructured":"Litzkow MJ, Livny M, Mutka MW. Condor-a hunter of idle workstations. In: Distributed computing systems, 8th international conference on, IEEE; 1988. p. 104\u201311.","DOI":"10.1109\/DCS.1988.12507"},{"key":"55_CR24","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.jbi.2014.01.005","volume":"49","author":"B Liu","year":"2014","unstructured":"Liu B, Madduri RK, Sotomayor B, Chard K, Lacinski L, Dave UJ, Li J, Liu C, Foster IT. Cloud-based bioinformatics workflow platform for large-scale next-generation sequencing analyses. J Biomed Inform. 2014;49:119\u201333.","journal-title":"J Biomed Inform"},{"issue":"1","key":"55_CR25","first-page":"215","volume":"1","author":"I Lobo","year":"2008","unstructured":"Lobo I. Basic local alignment search tool (blast). Nature Educ. 2008;1(1):215.","journal-title":"Nature Educ"},{"issue":"10","key":"55_CR26","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1002\/cpe.994","volume":"18","author":"B Lud\u00e4scher","year":"2006","unstructured":"Lud\u00e4scher B, Altintas I, Berkley C, Higgins D, Jaeger E, Jones MB, Lee EA, Tao J, Zhao Y. Scientific workflow management and the kepler system. Concurr Comput Pract Exp. 2006;18(10):1039\u201365.","journal-title":"Concurr Comput Pract Exp"},{"key":"55_CR27","doi-asserted-by":"crossref","unstructured":"Maheshwari K, Rodriguez A, Kelly D, Madduri R, Wozniak J, Wilde M, Foster I. Enabling multi-task computation on galaxy-based gateways using swift. In: Cluster computing (CLUSTER), 2013 IEEE international conference on, IEEE; 2013. p. 1\u20133.","DOI":"10.1109\/CLUSTER.2013.6702701"},{"issue":"239","key":"55_CR28","first-page":"2","volume":"2014","author":"D Merkel","year":"2014","unstructured":"Merkel D. Docker: lightweight linux containers for consistent development and deployment. Linux J. 2014;2014(239):2.","journal-title":"Linux J"},{"issue":"4","key":"55_CR29","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1534\/genetics.112.144204","volume":"192","author":"G Minevich","year":"2012","unstructured":"Minevich G, Park DS, Blankenberg D, Poole RJ, Hobert O. Cloudmap: a cloud-based pipeline for analysis of mutant genome sequences. Genetics. 2012;192(4):1249\u201369.","journal-title":"Genetics"},{"key":"55_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jss.2014.11.014","volume":"101","author":"IA Moschakis","year":"2015","unstructured":"Moschakis IA, Karatza HD. Multi-criteria scheduling of bag-of-tasks applications on heterogeneous interlinked clouds with simulated annealing. J Syst Soft. 2015;101:1\u201314.","journal-title":"J Syst Soft"},{"issue":"7","key":"55_CR31","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1101\/gr.171934.113","volume":"24","author":"SN Naccache","year":"2014","unstructured":"Naccache SN, Federman S, Veeraraghavan N, Zaharia M, Lee D, Samayoa E, Bouquet J, Greninger AL, Luk KC, Enge B, et al. A cloud-compatible bioinformatics pipeline for ultrarapid pathogen identification from next-generation sequencing of clinical samples. Genome Res. 2014;24(7):1180\u201392.","journal-title":"Genome Res"},{"key":"55_CR32","doi-asserted-by":"crossref","unstructured":"Nagasaki H, Mochizuki T, Kodama Y, Saruhashi S, Morizaki S, Sugawara H, Ohyanagi H, Kurata N, Okubo K, Takagi T, et\u00a0al. Ddbj read annotation pipeline: a cloud computing-based pipeline for high-throughput analysis of next-generation sequencing data. DNA Res. 2013;dst017.","DOI":"10.1093\/dnares\/dst017"},{"issue":"8","key":"55_CR33","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1016\/j.future.2013.04.005","volume":"29","author":"KA Oca\u00f1a","year":"2013","unstructured":"Oca\u00f1a KA, De Oliveira D, Dias J, Ogasawara E, Mattoso M. Designing a parallel cloud based comparative genomics workflow to improve phylogenetic analyses. Future Gener Comput Syst. 2013;29(8):2205\u201319.","journal-title":"Future Gener Comput Syst"},{"issue":"17","key":"55_CR34","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1093\/bioinformatics\/bth361","volume":"20","author":"T Oinn","year":"2004","unstructured":"Oinn T, Addis M, Ferris J, Marvin D, Senger M, Greenwood M, Carver T, Glover K, Pocock MR, Wipat A, et al. Taverna: a tool for the composition and enactment of bioinformatics workflows. Bioinformatics. 2004;20(17):3045\u201354.","journal-title":"Bioinformatics"},{"issue":"8","key":"55_CR35","doi-asserted-by":"crossref","first-page":"4285","DOI":"10.1073\/pnas.96.8.4285","volume":"96","author":"M Pellegrini","year":"1999","unstructured":"Pellegrini M, Marcotte EM, Thompson MJ, Eisenberg D, Yeates TO. Assigning protein functions by comparative genome analysis: protein phylogenetic profiles. Proc Natl Acad Sci. 1999;96(8):4285\u20138.","journal-title":"Proc Natl Acad Sci"},{"issue":"12","key":"55_CR36","doi-asserted-by":"crossref","first-page":"3718","DOI":"10.1105\/tpc.109.071506","volume":"21","author":"S Proost","year":"2009","unstructured":"Proost S, Van Bel M, Sterck L, Billiau K, Van Parys T, Van de Peer Y, Vandepoele K. Plaza: a comparative genomics resource to study gene and genome evolution in plants. Plant Cell. 2009;21(12):3718\u201331.","journal-title":"Plant Cell"},{"issue":"1","key":"55_CR37","doi-asserted-by":"crossref","first-page":"e52854","DOI":"10.1371\/journal.pone.0052854","volume":"8","author":"FE Psomopoulos","year":"2013","unstructured":"Psomopoulos FE, Mitkas PA, Ouzounis CA, Promponas VJ, et al. Detection of genomic idiosyncrasies using fuzzy phylogenetic profiles. PLoS One. 2013;8(1):e52854.","journal-title":"PLoS One"},{"issue":"1","key":"55_CR38","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/1471-2105-15-30","volume":"15","author":"JG Reid","year":"2014","unstructured":"Reid JG, Carroll A, Veeraraghavan N, Dahdouli M, Sundquist A, English A, Bainbridge M, White S, Salerno W, Buhay C, et al. Launching genomics into the cloud: deployment of mercury, a next generation sequence analysis pipeline. BMC Bioinform. 2014;15(1):30.","journal-title":"BMC Bioinform"},{"issue":"6","key":"55_CR39","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/S0168-9525(00)02024-2","volume":"16","author":"P Rice","year":"2000","unstructured":"Rice P, Longden I, Bleasby A, et al. Emboss: the European molecular biology open software suite. Trends Genet. 2000;16(6):276\u20137.","journal-title":"Trends Genet"},{"issue":"11","key":"55_CR40","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1093\/bioinformatics\/btp236","volume":"25","author":"MC Schatz","year":"2009","unstructured":"Schatz MC. Cloudburst: highly sensitive read mapping with mapreduce. Bioinformatics. 2009;25(11):1363\u20139.","journal-title":"Bioinformatics"},{"key":"55_CR41","unstructured":"Smith B, Grehan R, Yager T, Niemi D. Byte-unixbench: a unix benchmark suite. 2011."},{"key":"55_CR42","doi-asserted-by":"crossref","unstructured":"Sreedharan VT, Schultheiss SJ, Jean G, Kahles A, Bohnert R, Drewe P, Mudrakarta P, G\u00f6rnitz N, Zeller G, R\u00e4tsch G. Oqtans: the rna-seq workbench in the cloud for complete and reproducible quantitative transcriptome analysis. Bioinformatics. 2014:btt731.","DOI":"10.1093\/bioinformatics\/btt731"},{"issue":"10","key":"55_CR43","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1101\/gr.361602","volume":"12","author":"JE Stajich","year":"2002","unstructured":"Stajich JE, Block D, Boulez K, Brenner SE, Chervitz SA, Dagdigian C, Fuellen G, Gilbert JG, Korf I, Lapp H, et al. The bioperl toolkit: Perl modules for the life sciences. Genome Res. 2002;12(10):1611\u20138.","journal-title":"Genome Res"},{"key":"55_CR44","doi-asserted-by":"crossref","unstructured":"Tang W, Wilkening J, Desai N, Gerlach W, Wilke A, Meyer F. A scalable data analysis platform for metagenomics. In: Big data, 2013 IEEE international conference on, IEEE; 2013. p. 21\u20136.","DOI":"10.1109\/BigData.2013.6691723"},{"issue":"1","key":"55_CR45","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1186\/1471-2105-11-259","volume":"11","author":"DP Wall","year":"2010","unstructured":"Wall DP, Kudtarkar P, Fusaro VA, Pivovarov R, Patil P, Tonellato PJ. Cloud computing for comparative genomics. BMC Bioinform. 2010;11(1):259.","journal-title":"BMC Bioinform"},{"issue":"2","key":"55_CR46","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.future.2003.10.004","volume":"21","author":"C Weng","year":"2005","unstructured":"Weng C, Lu X. Heuristic scheduling for bag-of-tasks applications in combination with qos in the computational grid. Future Gener Comput Syst. 2005;21(2):271\u201380.","journal-title":"Future Gener Comput Syst"},{"issue":"9","key":"55_CR47","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1016\/j.parco.2011.05.005","volume":"37","author":"M Wilde","year":"2011","unstructured":"Wilde M, Hategan M, Wozniak JM, Clifford B, Katz DS, Foster I. Swift: a language for distributed parallel scripting. Parallel Comput. 2011;37(9):633\u201352.","journal-title":"Parallel Comput"},{"key":"55_CR48","doi-asserted-by":"crossref","unstructured":"Wolstencroft K, Haines R, Fellows D, Williams A, Withers D, Owen S, Soiland-Reyes S, Dunlop I, Nenadic A, Fisher P, et\u00a0al. The taverna workflow suite: designing and executing workflows of web services on the desktop, web or in the cloud. Nucleic Acids Res. 2013:gkt328.","DOI":"10.1093\/nar\/gkt328"},{"key":"55_CR49","doi-asserted-by":"crossref","unstructured":"Zhao Y, Hategan M, Clifford B, Foster I, Von\u00a0Laszewski G, Nefedova V, Raicu I, Stef-Praun T, Wilde M. Swift: fast, reliable, loosely coupled parallel computation. In: Services, 2007 IEEE Congress on, IEEE; 2007. p. 199\u2013206.","DOI":"10.1109\/SERVICES.2007.63"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-016-0055-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-016-0055-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-016-0055-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T17:46:47Z","timestamp":1568483207000},"score":1,"resource":{"primary":{"URL":"http:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-016-0055-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,21]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["55"],"URL":"https:\/\/doi.org\/10.1186\/s40537-016-0055-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,21]]},"article-number":"20"}}