{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T04:09:47Z","timestamp":1759205387025,"version":"3.41.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:00:00Z","timestamp":1519689600000},"content-version":"tdm","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":[[2018,12]]},"DOI":"10.1186\/s40537-018-0114-y","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:48:43Z","timestamp":1519692523000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["StreamAligner: a streaming based sequence aligner on Apache Spark"],"prefix":"10.1186","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2853-0842","authenticated-orcid":false,"given":"Sanjay","family":"Rathee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arti","family":"Kashyap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,27]]},"reference":[{"key":"114_CR1","unstructured":"Sabatini R. Ted Talk. (2017). https:\/\/www.ted.com\/talks\/riccardo_sabatini_how_to_read_the_genome_and_build_a_human_being"},{"issue":"11","key":"114_CR2","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1101\/gr.078212.108","volume":"18","author":"H Li","year":"2008","unstructured":"Li H, Ruan J, Durbin R. Mapping short dna sequencing reads and calling variants using mapping quality scores. Genome Res. 2008;18(11):1851\u20138. https:\/\/doi.org\/10.1101\/gr.078212.108 .","journal-title":"Genome Res"},{"key":"114_CR3","unstructured":"Cox A. ELAND: Efficient local slignment of nucleotide data (unpublished)."},{"issue":"20","key":"114_CR4","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1093\/bioinformatics\/btn429","volume":"24","author":"H Jiang","year":"2008","unstructured":"Jiang H, Wong WH. Seqmap: mapping massive amount of oligonucleotides to the genome. Bioinformatics. 2008;24(20):2395. https:\/\/doi.org\/10.1093\/bioinformatics\/btn429 .","journal-title":"Bioinformatics"},{"issue":"21","key":"114_CR5","doi-asserted-by":"publisher","first-page":"2431","DOI":"10.1093\/bioinformatics\/btn416","volume":"24","author":"H Lin","year":"2008","unstructured":"Lin H, Zhang Z, Zhang MQ, Ma B, Li M. ZOOM! Zillions of oligos mapped. Bioinformatics. 2008;24(21):2431\u20137. https:\/\/doi.org\/10.1093\/bioinformatics\/btn416 .","journal-title":"Bioinformatics"},{"issue":"21","key":"114_CR6","doi-asserted-by":"publisher","first-page":"2841","DOI":"10.1093\/bioinformatics\/btp533","volume":"25","author":"AD Smith","year":"2009","unstructured":"Smith AD, Chung WY, Hodges E, Kendall J, Hannon G, Hicks J, Xuan Z, Zhang MQ. Updates to the rmap short-read mapping software. Bioinformatics. 2009;25(21):2841. https:\/\/doi.org\/10.1093\/bioinformatics\/btp533 .","journal-title":"Bioinformatics"},{"key":"114_CR7","unstructured":"Novocraft Technologies Sdn Bhd: NovoAlign. Novocraft Technologies Sdn Bhd. 2008. http:\/\/www.novocraft.com."},{"issue":"5","key":"114_CR8","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1093\/bioinformatics\/btn025","volume":"24","author":"R Li","year":"2008","unstructured":"Li R, Li Y, Kristiansen K, Wang J. Soap: short oligonucleotide alignment program. Bioinformatics. 2008;24(5):713\u20134. https:\/\/doi.org\/10.1093\/bioinformatics\/btn025 .","journal-title":"Bioinformatics"},{"issue":"7","key":"114_CR9","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1093\/bioinformatics\/btp087","volume":"25","author":"D Campagna","year":"2009","unstructured":"Campagna D, Albiero A, Bilardi A, Caniato E, Forcato C, Manavski S, Vitulo N, Valle G. PASS: a program to align short sequences. Bioinformatics. 2009;25(7):967\u20138. https:\/\/doi.org\/10.1093\/bioinformatics\/btp087 .","journal-title":"Bioinformatics"},{"issue":"7","key":"114_CR10","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1093\/bioinformatics\/btp092","volume":"25","author":"HL Eaves","year":"2009","unstructured":"Eaves HL, Gao Y. Mom: maximum oligonucleotide mapping. Bioinformatics. 2009;25(7):969\u201370. https:\/\/doi.org\/10.1093\/bioinformatics\/btp092 .","journal-title":"Bioinformatics"},{"issue":"11","key":"114_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0007767","volume":"4","author":"N Homer","year":"2009","unstructured":"Homer N, Merriman B, Nelson SF. Bfast: an alignment tool for large scale genome resequencing. PLoS ONE. 2009;4(11):1\u201312. https:\/\/doi.org\/10.1371\/journal.pone.0007767 .","journal-title":"PLoS ONE"},{"issue":"11","key":"114_CR12","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1093\/bioinformatics\/btp178","volume":"25","author":"YJ Kim","year":"2009","unstructured":"Kim YJ, Teletia N, Ruotti V, Maher CA, Chinnaiyan AM, Stewart R, Thomson JA, Patel JM. Probematch: rapid alignment of oligonucleotides to genome allowing both gaps and mismatches. Bioinformatics. 2009;25(11):1424\u20135. https:\/\/doi.org\/10.1093\/bioinformatics\/btp178 .","journal-title":"Bioinformatics"},{"issue":"1","key":"114_CR13","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1093\/bioinformatics\/btn565","volume":"25","author":"N Malhis","year":"2009","unstructured":"Malhis N, Butterfield YSN, Ester M, Jones SJM. Slider\u2014maximum use of probability information for alignment of short sequence reads and snp detection. Bioinformatics. 2009;25(1):6\u201313. https:\/\/doi.org\/10.1093\/bioinformatics\/btn565 .","journal-title":"Bioinformatics"},{"key":"114_CR14","unstructured":"Burrows M, Wheeler DJ. A block-sorting lossless data compression algorithm. 1994. http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.121.6177 . Accessed 15 Mar 2016."},{"issue":"3","key":"114_CR15","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/gb-2009-10-3-r25","volume":"10","author":"B Langmead","year":"2009","unstructured":"Langmead B, Trapnell C, Pop M, Salzberg SL. Ultrafast and memory-efficient alignment of short dna sequences to the human genome. Genome Biol. 2009;10(3):25. https:\/\/doi.org\/10.1186\/gb-2009-10-3-r25 .","journal-title":"Genome Biol"},{"issue":"14","key":"114_CR16","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","volume":"25","author":"H Li","year":"2009","unstructured":"Li H, Durbin R. Fast and accurate short read alignment with Burrows\u2013Wheeler transform. Bioinformatics. 2009;25(14):1754\u201360. https:\/\/doi.org\/10.1093\/bioinformatics\/btp324 .","journal-title":"Bioinformatics"},{"issue":"5","key":"114_CR17","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1093\/bioinformatics\/btp698","volume":"26","author":"H Li","year":"2010","unstructured":"Li H, Durbiin R. Fast and accurate long-read alignment with Burrows\u2013Wheeler transform. Bioinformatics. 2010;26(5):589. https:\/\/doi.org\/10.1093\/bioinformatics\/btp698 .","journal-title":"Bioinformatics"},{"key":"114_CR18","doi-asserted-by":"crossref","unstructured":"Ferragina P, Manzini G. Opportunistic data structures with applications. In: Proceedings of the 41st annual symposium on foundations of computer science. FOCS \u201900, IEEE computer society, Washington, DC; 2000. p. 390. http:\/\/dl.acm.org\/citation.cfm?id=795666.796543","DOI":"10.1109\/SFCS.2000.892127"},{"key":"114_CR19","unstructured":"Apache Hadoop. http:\/\/hadoop.apache.org\/ ."},{"key":"114_CR20","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I. Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX conference on hot topics in cloud computing. HotCloud\u201910. USENIX Association, Berkeley; 2010. p. 10\u201310. http:\/\/dl.acm.org\/citation.cfm?id=1863103.1863113 ."},{"key":"114_CR21","unstructured":"Dean J, Ghemawat S. Mapreduce: simplified data processing on large clusters. In: Proceedings of the 6th conference on symposium on operating systems design & implementation, Vol 6. OSDI\u201904. USENIX Association, Berkeley, CA, USA; 2004. p. 10\u201310. http:\/\/dl.acm.org\/citation.cfm?id=1251254.1251264 ."},{"issue":"11","key":"114_CR22","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1093\/bioinformatics\/btp236 .","journal-title":"Bioinformatics"},{"key":"114_CR23","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1186\/1756-0500-4-171","volume":"4","author":"T Nguyen","year":"2011","unstructured":"Nguyen T, Shi W, Ruden D. Cloudaligner: a fast and full-featured mapreduce based tool for sequence mapping. BMC Res Notes. 2011;4:171. https:\/\/doi.org\/10.1186\/1756-0500-4-171 .","journal-title":"BMC Res Notes"},{"key":"114_CR24","unstructured":"Schatz MC. BlastReduce: high performance short read mapping with MapReduce."},{"issue":"24","key":"114_CR25","doi-asserted-by":"publisher","first-page":"4003","DOI":"10.1093\/bioinformatics\/btv506","volume":"31","author":"JM Abuin","year":"2015","unstructured":"Abuin JM, Pichel JC, Pena TF, Amigo J. BigBWA: approaching the Burrows-Wheeler aligner to Big Data technologies. Bioinformatics. 2015;31(24):4003\u20135. https:\/\/doi.org\/10.1093\/bioinformatics\/btv506 .","journal-title":"Bioinformatics"},{"issue":"5","key":"114_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0155461","volume":"11","author":"JM Abuin","year":"2016","unstructured":"Abuin JM, Pichel JC, Pena T, Amigo J. Sparkbwa: speeding up the alignment of high-throughput dna sequencing data. PLoS ONE. 2016;11(5):1\u201321. https:\/\/doi.org\/10.1371\/journal.pone.0155461 .","journal-title":"PLoS ONE"},{"issue":"15","key":"114_CR27","doi-asserted-by":"publisher","first-page":"2482","DOI":"10.1093\/bioinformatics\/btv179","volume":"31","author":"D Decap","year":"2015","unstructured":"Decap D, Reumers J, Herzeel C, Costanza P, Fostier J. Halvade: scalable sequence analysis with mapreduce. Bioinformatics. 2015;31(15):2482\u20138. https:\/\/doi.org\/10.1093\/bioinformatics\/btv179 .","journal-title":"Bioinformatics"},{"key":"114_CR28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.jnca.2017.01.029","volume":"83","author":"M Congosto","year":"2017","unstructured":"Congosto M, Basanta-Val P, Fern\u00e1ndez LS. T-hoarder: a framework to process twitter data streams. J Netw Comput Appl. 2017;83:28\u201339.","journal-title":"J Netw Comput Appl"},{"issue":"4","key":"114_CR29","doi-asserted-by":"publisher","first-page":"1891","DOI":"10.1109\/TII.2017.2650204","volume":"13","author":"Z Lv","year":"2017","unstructured":"Lv Z, Song H, Basanta-Val P, Steed A, Jo M. Next-generation big data analytics: state of the art, challenges, and future research topics. IEEE Trans Ind Inf. 2017;13(4):1891\u20139. https:\/\/doi.org\/10.1109\/TII.2017.2650204 .","journal-title":"IEEE Trans Ind Inf"},{"key":"114_CR30","doi-asserted-by":"publisher","unstructured":"Rathee S, Kaul M, Kashyap A. R-apriori: an efficient apriori based algorithm on spark. In: Proceedings of the 8th workshop on Ph.D. workshop in information and knowledge management. PIKM. ACM, Melbourne, Australia. 2015;15: 27\u201334. https:\/\/doi.org\/10.1145\/2809890.2809893","DOI":"10.1145\/2809890.2809893"},{"issue":"11","key":"114_CR31","doi-asserted-by":"publisher","first-page":"3243","DOI":"10.1109\/TPDS.2017.2716929","volume":"28","author":"P Basanta-Val","year":"2017","unstructured":"Basanta-Val P, Fern\u00e1ndez-Garc\u00eda N, Basanta-Val P, Fern\u00e1ndez-Garc\u00eda N, S\u00e1nchez-Fern\u00e1 ndez L, Arias-Fisteus J. Patterns for distributed real-time stream processing. IEEE Trans Parallel Distrib Syst. 2017;28(11):3243\u201357. https:\/\/doi.org\/10.1109\/TPDS.2017.2716929 .","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"C","key":"114_CR32","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.future.2015.03.023","volume":"52","author":"P Basanta-Val","year":"2015","unstructured":"Basanta-Val P, Fern\u00e1ndez-Garc\u00eda N, Wellings AJ, Audsley NC. Improving the predictability of distributed stream processors. Future Gener Comput Syst. 2015;52(C):22\u201336. https:\/\/doi.org\/10.1016\/j.future.2015.03.023 .","journal-title":"Future Gener Comput Syst"},{"issue":"15","key":"114_CR33","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.1093\/bioinformatics\/btr325","volume":"27","author":"L Pireddu","year":"2011","unstructured":"Pireddu L, Leo S, Zanetti G. Seal: a distributed short read mapping and duplicate removal tool. Bioinformatics. 2011;27(15):2159\u201360. https:\/\/doi.org\/10.1093\/bioinformatics\/btr325 .","journal-title":"Bioinformatics"},{"key":"114_CR34","unstructured":"Li Y, Zhong S. Seqmapreduce: software and web service for accelerating sequence mapping. Critical assessment of massive data analysis (CAMDA). 2009."},{"issue":"11","key":"114_CR35","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1186\/gb-2009-10-11-r134","volume":"10","author":"B Langmead","year":"2009","unstructured":"Langmead B, Schatz MC, Lin J, Pop M, Salzberg SL. Searching for snps with cloud computing. Genome Biol. 2009;10(11):134. https:\/\/doi.org\/10.1186\/gb-2009-10-11-r134 .","journal-title":"Genome Biol"},{"key":"114_CR36","unstructured":"Amazon EC2 Cloud: Amazon Web Services Genomics. Amazon EC2 Cloud. 2017. https:\/\/aws.amazon.com\/health\/genomics\/ ."},{"key":"114_CR37","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.1109\/BigData.2016.7840727","volume":"12","author":"F Versaci","year":"2016","unstructured":"Versaci F, Pireddu L, Zanetti G. Scalable genomics: from raw data to aligned reads on apache yarn. EEE Int Conf Big Data. 2016;12:1232\u201341. https:\/\/doi.org\/10.1109\/BigData.2016.7840727 .","journal-title":"EEE Int Conf Big Data"},{"issue":"1","key":"114_CR38","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1063\/1.3663477","volume":"1368","author":"D Peters","year":"2011","unstructured":"Peters D, Qiu K, Liang P. Faster short dna sequence alignment with parallel bwa. AIP Conf Proc. 2011;1368(1):131\u20134. https:\/\/doi.org\/10.1063\/1.3663477 .","journal-title":"AIP Conf Proc"},{"issue":"1","key":"114_CR39","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/1756-0500-5-27","volume":"5","author":"P Klus","year":"2012","unstructured":"Klus P, Lam S, Lyberg D, Cheung MS, Pullan G, McFarlane I, Yeo GS, Lam BY. Barracuda\u2014a fast short read sequence aligner using graphics processing units. BMC Res Notes. 2012;5(1):27. https:\/\/doi.org\/10.1186\/1756-0500-5-27 .","journal-title":"BMC Res Notes"},{"issue":"7","key":"114_CR40","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1093\/bioinformatics\/btw750","volume":"33","author":"W Zhou","year":"2017","unstructured":"Zhou W, Li R, Yuan S, Liu C, Yao S, Luo J, Niu B. Metaspark: a spark-based distributed processing tool to recruit metagenomic reads to reference genomes. Bioinformatics. 2017;33(7):1090. https:\/\/doi.org\/10.1093\/bioinformatics\/btw750 .","journal-title":"Bioinformatics"},{"key":"114_CR41","unstructured":"National Center for Biotechnology Information. Reference Genomes. National Center for Biotechnology Information. 2017. http:\/\/www.ncbi.nlm.nih.gov ."},{"key":"114_CR42","unstructured":"Agilent Inc. USA. Query Datasets. Agilent Inc. USA. 2017. https:\/\/cloud.iitmandi.ac.in\/d\/2ba909564a\/ ."},{"key":"114_CR43","unstructured":"1000genomes Project: Genome Dataset Project. 1000genomes Project. 2017. ftp:\/\/ftp-trace.ncbi.nih.gov\/1000genomes\/ftp\/ ."},{"key":"114_CR44","unstructured":"Apache: Flink. Apache. 2017. https:\/\/flink.apache.org\/ ."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-018-0114-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-018-0114-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-018-0114-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T01:15:10Z","timestamp":1751418910000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-018-0114-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,27]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["114"],"URL":"https:\/\/doi.org\/10.1186\/s40537-018-0114-y","relation":{},"ISSN":["2196-1115"],"issn-type":[{"type":"electronic","value":"2196-1115"}],"subject":[],"published":{"date-parts":[[2018,2,27]]},"assertion":[{"value":"15 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"8"}}