{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:53:54Z","timestamp":1743072834419,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319577104"},{"type":"electronic","value":"9783319577111"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-57711-1_7","type":"book-chapter","created":{"date-parts":[[2017,4,20]],"date-time":"2017-04-20T08:39:35Z","timestamp":1492677575000},"page":"77-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Spark Distributed Data Structures: A Sequence Analysis Case Study"],"prefix":"10.1007","author":[{"given":"Umberto","family":"Ferraro Petrillo","sequence":"first","affiliation":[]},{"given":"Roberto","family":"Vitali","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,4,21]]},"reference":[{"issue":"3","key":"7_CR1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.tig.2007.12.006","volume":"24","author":"M Pop","year":"2008","unstructured":"Pop, M., Salzberg, S.L.: Bioinformatics challenges of new sequencing technology. Trends Genet. 24(3), 142\u2013149 (2008)","journal-title":"Trends Genet."},{"issue":"8","key":"7_CR2","first-page":"16","volume":"200","author":"SC Schuster","year":"2007","unstructured":"Schuster, S.C.: Next-generation sequencing transforms today\u2019s biology. Nature 200(8), 16\u201318 (2007)","journal-title":"Nature"},{"issue":"12","key":"7_CR3","doi-asserted-by":"publisher","first-page":"5463","DOI":"10.1073\/pnas.74.12.5463","volume":"74","author":"F Sanger","year":"1977","unstructured":"Sanger, F., Nicklen, S., Coulson, A.R.: DNA sequencing with chain-terminating inhibitors. Proc. Natl. Acad. Sci. 74(12), 5463\u20135467 (1977)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1","key":"7_CR4","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 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"7_CR5","unstructured":"Apache: Hadoop. \n                    http:\/\/hadoop.apache.org\/"},{"issue":"1","key":"7_CR6","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s10723-012-9204-9","volume":"10","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y., Gao, Q., Gao, L., Wang, C.: iMapReduce: a distributed computing framework for iterative computation. J. Grid Comput. 10(1), 47\u201368 (2012). \n                    http:\/\/dx.doi.org\/10.1007\/s10723-012-9204-9","journal-title":"J. Grid Comput."},{"key":"7_CR7","unstructured":"Apache: Spark. \n                    http:\/\/spark.apache.org\/"},{"issue":"9","key":"7_CR8","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1101\/gr.107524.110","volume":"20","author":"A McKenna","year":"2010","unstructured":"McKenna, A., Hanna, M., Banks, E., Sivachenko, A., Cibulskis, K., Kernytsky, A., Kiran, G., Altshuler, D., Gabriel, S., Daly, M., DePristo, M.A.: The genome analysis toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20(9), 1297\u20131303 (2010). \n                    http:\/\/genome.cshlp.org\/content\/20\/9\/1297.abstract","journal-title":"Genome Res."},{"issue":"6","key":"7_CR9","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 28(6), 876\u2013877 (2012)","journal-title":"Bioinformatics"},{"key":"7_CR10","unstructured":"Massie, M., Nothaft, F., Hartl, C., Kozanitis, C., Schumacher, A., Joseph, A.D., Patterson, D.A.: ADAM: Genomics formats and processing patterns for cloud scale computing. University of California, Berkeley Technical report, No. UCB\/EECS-2013 207 (2013)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Cattaneo, G., Ferraro-Petrillo, U., Giancarlo, R., Roscigno, G.: Alignment-free sequence comparison over Hadoop for computational biology. In: Proceedings of 44th International Conference on Parallel Processing Workshops, ICPPW, pp. 184\u2013192 (2015)","DOI":"10.1109\/ICPPW.2015.28"},{"issue":"4","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1007\/s11227-016-1835-3","volume":"73","author":"G Cattaneo","year":"2017","unstructured":"Cattaneo, G., Ferraro-Petrillo, U., Giancarlo, R., Roscigno, G.: An effective extension of the applicability of alignment-free biological sequence comparison algorithms with Hadoop. J. Supercomputing. 73(4), 1467\u20131483 (2017)","journal-title":"J. Supercomputing."},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Wiewi\u00f3rka, M.S., Messina, A., Pacholewska, A., Maffioletti, S., Gawrysiak, P., Okoniewski, M.J.: SparkSeq: fast, scalable, cloud-ready tool for the interactive genomic data analysis with nucleotide precision. Bioinformatics (2014)","DOI":"10.1093\/bioinformatics\/btu343"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Bahmani, A., Sibley, A.B., Parsian, M., Owzar, K., Mueller, F.: SparkScore: leveraging apache spark for distributed genomic inference. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, pp. 435\u2013442, May 2016","DOI":"10.1109\/IPDPSW.2016.6"},{"key":"7_CR15","unstructured":"Xin R., R.J.: Project tungsten: Bringing Spark closer to bare metal. \n                    https:\/\/databricks.com\/blog\/2015\/04\/28\/project-tungsten-bringing-spark-closer-to-bare-metal.html"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Giancarlo, R., Rombo, S.E., Utro, F.: Epigenomic k-mer dictionaries: shedding light on how sequence composition influences in vivo nucleosome positioning. Bioinformatics (2015)","DOI":"10.1093\/bioinformatics\/btv295"},{"key":"7_CR17","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1093\/bioinformatics\/btv022","volume":"31","author":"S Deorowicz","year":"2015","unstructured":"Deorowicz, S., Kokot, M., Grabowski, S., Debudaj-Grabysz, A.: KMC2: fast and resource-frugal k-mer counting. Bioinformatics 31, 1569\u20131576 (2015)","journal-title":"Bioinformatics"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Ferraro Petrillo, U., Roscigno, G., Cattaneo, G., Giancarlo, R.: FASTdoop: a versatile and efficient library for the input of FASTA and FASTQ files for MapReduce Hadoop bioinformatics applications. Bioinformatics (2017). \n                    https:\/\/dx.doi.org\/10.1093\/bioinformatics\/btx010","DOI":"10.1093\/bioinformatics\/btx010"},{"key":"7_CR19","unstructured":"Wikipedia: FASTA format \u2013 Wikipedia, the free encyclopedia. \n                    https:\/\/en.wikipedia.org\/wiki\/FASTA_format"}],"container-title":["Communications in Computer and Information Science","Advances in Artificial Life, Evolutionary Computation, and Systems Chemistry"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-57711-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T23:26:18Z","timestamp":1558394778000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-57711-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319577104","9783319577111"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-57711-1_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"21 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WIVACE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italian Workshop on Artificial Life and Evolutionary Computation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fisciano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wivace2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wivace.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}