{"id":"https://openalex.org/W3178895995","doi":"https://doi.org/10.3390/data11030048","title":"Burrows Wheeler Transform on a Large Scale: Algorithms Implemented in Apache Spark","display_name":"Burrows Wheeler Transform on a Large Scale: Algorithms Implemented in Apache Spark","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W3178895995","doi":"https://doi.org/10.3390/data11030048","mag":"3178895995"},"language":"en","primary_location":{"id":"doi:10.3390/data11030048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11030048","pdf_url":"https://www.mdpi.com/2306-5729/11/3/48/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/11/3/48/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012555693","display_name":"Ylenia Galluzzo","orcid":null},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ylenia Galluzzo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078881318","display_name":"Raffaele Giancarlo","orcid":"https://orcid.org/0000-0002-6286-8871"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Giancarlo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025222989","display_name":"Mario Randazzo","orcid":null},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Randazzo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047319643","display_name":"Simona E. Rombo","orcid":"https://orcid.org/0000-0003-3833-835X"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simona E. Rombo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012555693"],"corresponding_institution_ids":["https://openalex.org/I900890020"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":31.4596,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97962308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"11","issue":"3","first_page":"48","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8592057228088379},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7455480098724365},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7358963489532471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266542911529541},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6730802059173584},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6368309855461121},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5501101016998291},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49170929193496704},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4494384229183197},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43096035718917847},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.42896467447280884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4015624523162842},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32493895292282104},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32474422454833984},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17836502194404602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17544466257095337},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13127651810646057},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07158693671226501}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8592057228088379},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7455480098724365},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7358963489532471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266542911529541},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6730802059173584},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6368309855461121},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5501101016998291},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49170929193496704},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4494384229183197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43096035718917847},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.42896467447280884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4015624523162842},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32493895292282104},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32474422454833984},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17836502194404602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17544466257095337},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13127651810646057},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07158693671226501},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/data11030048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11030048","pdf_url":"https://www.mdpi.com/2306-5729/11/3/48/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2107.03341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.03341","pdf_url":"https://arxiv.org/pdf/2107.03341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3178895995","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.03341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:aed27aa30e4e42d28378c2a2419e7904","is_oa":true,"landing_page_url":"https://doaj.org/article/aed27aa30e4e42d28378c2a2419e7904","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 11, Iss 3, p 48 (2026)","raw_type":"article"},{"id":"pmh:oai:iris.unipa.it:10447/703593","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/703593","pdf_url":null,"source":{"id":"https://openalex.org/S4377196289","display_name":"IRIS UniPA (University of Palermo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I900890020","host_organization_name":"University of Palermo","host_organization_lineage":["https://openalex.org/I900890020"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2107.03341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.03341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/data11030048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11030048","pdf_url":"https://www.mdpi.com/2306-5729/11/3/48/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5087985992","display_name":null,"funder_award_id":"B77G24000050001","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7205771190","display_name":null,"funder_award_id":"PE00000001","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8828314804","display_name":null,"funder_award_id":"E83C22004640001","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178895995.pdf","grobid_xml":"https://content.openalex.org/works/W3178895995.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1904861952","https://openalex.org/W2021724381","https://openalex.org/W2063431258","https://openalex.org/W2067974452","https://openalex.org/W2103441770","https://openalex.org/W2131975293","https://openalex.org/W2134283755","https://openalex.org/W2157355837","https://openalex.org/W2159647614","https://openalex.org/W2530385528","https://openalex.org/W2585711475","https://openalex.org/W2962678578","https://openalex.org/W2998160967","https://openalex.org/W3121516856"],"related_works":["https://openalex.org/W3042699812","https://openalex.org/W3098328330","https://openalex.org/W2945665681","https://openalex.org/W2809536481","https://openalex.org/W1514347489","https://openalex.org/W2403451390","https://openalex.org/W2514021172","https://openalex.org/W3092102627","https://openalex.org/W1483680804","https://openalex.org/W2258180570","https://openalex.org/W3197743743","https://openalex.org/W1927287081","https://openalex.org/W2149059931","https://openalex.org/W2809353976","https://openalex.org/W236870159","https://openalex.org/W2147869723","https://openalex.org/W3013531585","https://openalex.org/W2594410993","https://openalex.org/W3135467714","https://openalex.org/W2588353203"],"abstract_inverted_index":{"With":[0],"the":[1,32,46,68,72,78,86,96],"rapid":[2],"growth":[3],"of":[4,12,31,48],"Next":[5],"Generation":[6],"Sequencing":[7],"(NGS)":[8],"technologies,":[9,56],"large":[10,26],"amounts":[11],"\u201comics\u201d":[13],"data":[14],"are":[15,29],"daily":[16],"collected":[17],"and":[18,24,60,75],"need":[19],"to":[20],"be":[21],"processed.":[22],"Indexing":[23],"compressing":[25],"sequences":[27],"datasets":[28,93],"some":[30],"most":[33],"important":[34],"tasks":[35],"in":[36],"this":[37],"context.":[38],"Here,":[39],"we":[40],"propose":[41],"a":[42],"novel":[43],"approach":[44,98],"for":[45],"computation":[47,74],"Burrows":[49],"Wheeler":[50],"transform":[51],"relying":[52],"on":[53,67,91],"Big":[54],"Data":[55],"i.e.,":[57],"Apache":[58],"Spark":[59],"Hadoop.":[61],"We":[62],"implement":[63],"three":[64],"algorithms":[65],"based":[66],"MapReduce":[69],"framework,":[70],"distributing":[71],"index":[73],"not":[76],"only":[77],"input":[79],"dataset,":[80],"differently":[81],"than":[82],"previous":[83],"approaches":[84],"from":[85],"literature.":[87],"Experimental":[88],"results":[89],"performed":[90],"real":[92],"show":[94],"that":[95],"proposed":[97],"is":[99],"promising.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2021-07-19T00:00:00"}
