{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:46:43Z","timestamp":1783043203899,"version":"3.54.6"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T00:00:00Z","timestamp":1566432000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T00:00:00Z","timestamp":1566432000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["(CCF-15-18897)"],"award-info":[{"award-number":["(CCF-15-18897)"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["(CNS-15-13263)"],"award-info":[{"award-number":["(CNS-15-13263)"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009227","name":"Iowa State University","doi-asserted-by":"publisher","award":["(Presidential Initiative)"],"award-info":[{"award-number":["(Presidential Initiative)"]}],"id":[{"id":"10.13039\/100009227","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s12859-019-2967-2","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T07:03:51Z","timestamp":1566457431000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Shared data science infrastructure for genomics data"],"prefix":"10.1186","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1540-7797","authenticated-orcid":false,"given":"Hamid","family":"Bagheri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Usha","family":"Muppirala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rick E.","family":"Masonbrink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew J.","family":"Severin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hridesh","family":"Rajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,8,22]]},"reference":[{"key":"2967_CR1","doi-asserted-by":"crossref","unstructured":"Schmidt B, Hildebrandt A. Next-generation sequencing: big data meets high performance computing. Drug Discov Today. 2017.","DOI":"10.1016\/j.drudis.2017.01.014"},{"key":"2967_CR2","unstructured":"Terrizzano, I.G., Schwarz, P.M., Roth, M., Colino, J.E.: Data wrangling: The challenging yourney from the wild to the lake. In: CIDR (2015)."},{"issue":"4","key":"2967_CR3","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1145\/1118890.1118892","volume":"37","author":"M Mernik","year":"2005","unstructured":"Mernik M, Heering J, Sloane AM. When and how to develop domain-specific languages. ACM computing surveys (CSUR). 2005;37(4):316\u201344.","journal-title":"ACM computing surveys (CSUR)"},{"issue":"1","key":"2967_CR4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/2803171","volume":"25","author":"R Dyer","year":"2015","unstructured":"Dyer R, Nguyen HA, Rajan H, Nguyen TN. Boa: Ultra-large-scale software repository and source-code mining. ACM Transactions on Software Engineering and Methodology (TOSEM). 2015;25(1):7.","journal-title":"ACM Transactions on Software Engineering and Methodology (TOSEM)"},{"issue":"1","key":"2967_CR5","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1186\/1471-2105-12-285","volume":"12","author":"HF Deus","year":"2011","unstructured":"Deus HF, Correa MC, Stanislaus R, Miragaia M, Maass W, De Lencastre H, Fox R, Almeida JS. S3ql: A distributed domain specific language for controlled semantic integration of life sciences data. BMC bioinformatics. 2011;12(1):285.","journal-title":"BMC bioinformatics"},{"issue":"20","key":"2967_CR6","doi-asserted-by":"publisher","first-page":"2693","DOI":"10.1093\/bioinformatics\/bts494","volume":"28","author":"A Prlic\u00b4","year":"2012","unstructured":"Prlic\u00b4 A, Yates A, Bliven SE, Rose PW, Jacobsen J, Troshin PV, Chapman M, Gao J, Koh CH, Foisy S, et al. Biojava: an open-source framework for bioinformatics in 2012. Bioinformatics. 2012;28(20):2693\u20135.","journal-title":"Bioinformatics"},{"issue":"10","key":"2967_CR7","doi-asserted-by":"publisher","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"},{"issue":"11","key":"2967_CR8","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1093\/bioinformatics\/btp163","volume":"25","author":"PJ Cock","year":"2009","unstructured":"Cock PJ, Antao T, Chang JT, Chapman BA, Cox CJ, Dalke A, Friedberg I, Hamelryck T, Kauff F, Wilczynski B, et al. Biopython: freely available python tools for computational molecular biology and bioinformatics. Bioinformatics. 2009;25(11):1422\u20133.","journal-title":"Bioinformatics"},{"issue":"1","key":"2967_CR9","doi-asserted-by":"publisher","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"},{"key":"2967_CR10","unstructured":"Hadoop and MongoDB. https:\/\/www.mongodb.com\/hadoop-and-mongodb"},{"key":"2967_CR11","unstructured":"Genomics England. https:\/\/www.genomicsengland.co.uk\/"},{"key":"2967_CR12","doi-asserted-by":"crossref","unstructured":"Turnbull C, Scott RH, Thomas E, Jones L, Murugaesu N, Pretty FB, Halai D, Baple E, Craig C, Hamblin A, et al. The 100000 genomes project: Bringing whole genome sequencing to the nhs. BMJ: British Medical Journal (Online). 2018;361.","DOI":"10.1136\/bmj.k1687"},{"issue":"Suppl 12","key":"2967_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-11-S12-S1","volume":"11","author":"RC Taylor","year":"2010","unstructured":"Taylor RC. An overview of the Hadoop\/MapReduce\/HBase framework and its current applications in bioinformatics. BMC Bioinformatics. 2010;11(Suppl 12):1.","journal-title":"BMC Bioinformatics"},{"key":"2967_CR14","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1145\/2925426.2926283","volume-title":"Proceedings of the 2016 International Conference on Supercomputing. ICS \u201816","author":"K Mahadik","year":"2016","unstructured":"Mahadik K, Wright C, Zhang J, Kulkarni M, Bagchi S, Chaterji S. Sarvavid: A domain specific language for developing scalable computational genomics applications. In: Proceedings of the 2016 International Conference on Supercomputing. ICS \u201816. New York, NY, USA: ACM; 2016. p. 34\u201313412. https:\/\/doi.org\/10.1145\/2925426.2926283 ."},{"issue":"3","key":"2967_CR15","doi-asserted-by":"publisher","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"},{"key":"2967_CR16","doi-asserted-by":"crossref","unstructured":"Leo S, Santoni F, Zanetti G. Biodoop: bioinformatics on hadoop. In: Parallel Processing Workshops, 2009. ICPPW\u201909. International Conference On: IEEE; 2009. p. 415\u201322.","DOI":"10.1109\/ICPPW.2009.37"},{"issue":"6","key":"2967_CR17","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1093\/bioinformatics\/bts054","volume":"28","author":"M Niemenmaa","year":"2012","unstructured":"Niemenmaa M, Kallio A, Schumacher A, Klemel\u00e4 P, Korpelainen E, Heljanko K. Hadoop-bam: directly manipulating next generation sequencing data in the cloud. Bioinformatics. 2012;28(6):876\u20137. https:\/\/doi.org\/10.1093\/bioinformatics\/bts054 .","journal-title":"Bioinformatics"},{"key":"2967_CR18","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1145\/1779599.1779601","volume-title":"Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud. MDAC \u201810","author":"GS Sadasivam","year":"2010","unstructured":"Sadasivam GS, Baktavatchalam G. A novel approach to multiple sequence alignment using hadoop data grids. In: Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud. MDAC \u201810. New York, NY, USA: ACM; 2010. p. 2\u2013127. https:\/\/doi.org\/10.1145\/1779599.1779601 ."},{"issue":"8","key":"2967_CR19","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/gb-2010-11-8-r83","volume":"11","author":"B Langmead","year":"2010","unstructured":"Langmead B, Hansen KD, Leek JT. Cloud-scale RNA-sequencing differential expression analysis with Myrna. Genome Biol. 2010;11(8):83.","journal-title":"Genome Biol"},{"key":"2967_CR20","doi-asserted-by":"crossref","unstructured":"Alnasir J, Shanahan H. The application of hadoop in structural bioinformatics. BioRxiv. 2018;376467.","DOI":"10.1101\/376467"},{"issue":"1","key":"2967_CR21","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s42421-019-00006-8","volume":"1","author":"Md Johirul Islam","year":"2019","unstructured":"Islam MJ, Sharma A, Rajan H. A cyberinfrastructure for big data transportation engineering. Journal of Big Data Analytics in Transportation. 2019. https:\/\/doi.org\/10.1007\/s42421-019-00006-8 .","journal-title":"Journal of Big Data Analytics in Transportation"},{"issue":"1","key":"2967_CR22","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/1471-2164-10-22","volume":"10","author":"D Smedley","year":"2009","unstructured":"Smedley D, Haider S, Ballester B, Holland R, London D, Thorisson G, Kasprzyk A. Biomart\u2013biological queries made easy. BMC Genomics. 2009;10(1):22.","journal-title":"BMC Genomics"},{"issue":"8","key":"2967_CR23","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1093\/bioinformatics\/btw821","volume":"33","author":"H-G Drost","year":"2017","unstructured":"Drost H-G, Paszkowski J. Biomartr: genomic data retrieval with r. Bioinformatics. 2017;33(8):1216\u20137.","journal-title":"Bioinformatics"},{"issue":"21","key":"2967_CR24","doi-asserted-by":"publisher","first-page":"6688","DOI":"10.1093\/nar\/gkn668","volume":"36","author":"EV Koonin","year":"2008","unstructured":"Koonin EV, Wolf YI. Genomics of bacteria and archaea: the emerging dynamic view of the prokaryotic world. Nucleic Acids Res. 2008;36(21):6688\u2013719.","journal-title":"Nucleic Acids Res"},{"key":"2967_CR25","doi-asserted-by":"crossref","unstructured":"Dede E, Govindaraju M, Gunter D, Canon RS, Ramakrishnan L. In: Proceedings of the 4th ACM Workshop on Scientific Cloud Computing, editor. Performance evaluation of a mongodb and hadoop platform for scientific data analysis: ACM; 2013. p. 13\u201320.","DOI":"10.1145\/2465848.2465849"},{"key":"2967_CR26","unstructured":"Generic Feature Format Version 3. http:\/\/gmod.org\/wiki\/GFF3"},{"key":"2967_CR27","unstructured":"Chodorow K. MongoDB: the Definitive Guide: Powerful and Scalable Data Storage: O\u2019Reilly Media, Inc.\", ??? 2013."},{"issue":"suppl_1","key":"2967_CR28","first-page":"61","volume":"35","author":"KD Pruitt","year":"2006","unstructured":"Pruitt KD, Tatusova T, Maglott DR. Ncbi reference sequences (refseq): a curated non-redundant sequence database of genomes, transcripts and proteins. Nucleic Acids Res. 2006;35(suppl_1):61\u20135.","journal-title":"Nucleic Acids Res"},{"key":"2967_CR29","unstructured":"Rajan H. Bridging the digital divide in data science. In: SPLASH\/SPLASH-I\u201917: The ACM SIGPLAN Conference on Systems, Programming, Languages and Applications: Software for Humanity; 2017."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-2967-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-019-2967-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-2967-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T06:32:39Z","timestamp":1695105159000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-019-2967-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,22]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["2967"],"URL":"https:\/\/doi.org\/10.1186\/s12859-019-2967-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.2.4295\/v3","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.2.4295\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.1101\/307777","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.2.4295\/v2","asserted-by":"object"}]},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,22]]},"assertion":[{"value":"2 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"436"}}