{"id":"https://openalex.org/W4410536779","doi":"https://doi.org/10.1109/tcbbio.2025.3565188","title":"Scalable and Maintainable Distributed Sequence Alignment Using Spark","display_name":"Scalable and Maintainable Distributed Sequence Alignment Using Spark","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410536779","doi":"https://doi.org/10.1109/tcbbio.2025.3565188","pmid":"https://pubmed.ncbi.nlm.nih.gov/40811315"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2025.3565188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3565188","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vtechworks.lib.vt.edu/bitstreams/905a078b-821a-4cd7-8dec-c8273ec665a8/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103003875","display_name":"Karim Youssef","orcid":"https://orcid.org/0000-0003-4544-9613"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karim Youssef","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer ScienceVirginia Tech"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer ScienceVirginia Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116872323","display_name":"Yusuf Elnady","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuf Elnady","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer ScienceVirginia Tech"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer ScienceVirginia Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013168771","display_name":"Eli Tilevich","orcid":"https://orcid.org/0000-0003-2415-6926"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eli Tilevich","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer ScienceVirginia Tech"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer ScienceVirginia Tech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer ScienceVirginia Tech"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer ScienceVirginia Tech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103003875"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05152089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"1388","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9965999722480774,"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":0.9965999722480774,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7725579738616943},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7267656326293945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260547280311584},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6882337331771851},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5000467300415039},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40925148129463196},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3749196529388428},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22380951046943665},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05547893047332764}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7725579738616943},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7267656326293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260547280311584},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6882337331771851},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5000467300415039},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40925148129463196},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3749196529388428},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22380951046943665},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05547893047332764},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcbbio.2025.3565188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3565188","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40811315","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40811315","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on computational biology and bioinformatics","raw_type":null},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/142233","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/142233","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/905a078b-821a-4cd7-8dec-c8273ec665a8/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/142233","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/142233","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/905a078b-821a-4cd7-8dec-c8273ec665a8/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410536779.pdf","grobid_xml":"https://content.openalex.org/works/W4410536779.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1505071416","https://openalex.org/W1596936080","https://openalex.org/W1991662581","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2099763971","https://openalex.org/W2107903949","https://openalex.org/W2109982223","https://openalex.org/W2115036455","https://openalex.org/W2123179625","https://openalex.org/W2131229759","https://openalex.org/W2142678478","https://openalex.org/W2155957132","https://openalex.org/W2156137607","https://openalex.org/W2158714788","https://openalex.org/W2162993740","https://openalex.org/W2163932369","https://openalex.org/W2396849069","https://openalex.org/W2422616509","https://openalex.org/W2547597780","https://openalex.org/W2731251882","https://openalex.org/W2744027658","https://openalex.org/W2942821924","https://openalex.org/W2951635356","https://openalex.org/W2966238514","https://openalex.org/W2995564009","https://openalex.org/W3009109635","https://openalex.org/W3015731845","https://openalex.org/W3031764734","https://openalex.org/W3043722005","https://openalex.org/W4230784961","https://openalex.org/W4234578858","https://openalex.org/W4292169167","https://openalex.org/W4311999292","https://openalex.org/W4360979106","https://openalex.org/W6606052223","https://openalex.org/W6679815717","https://openalex.org/W6753935290"],"related_works":["https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W2905242764","https://openalex.org/W4391094140","https://openalex.org/W3109411864","https://openalex.org/W3017846737","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W4401278057"],"abstract_inverted_index":{"The":[0],"exponential":[1],"growth":[2],"of":[3,26,29,179],"genomic":[4,156,181],"data":[5,140],"presents":[6],"a":[7,14,55,86,106,129],"challenge":[8,56],"to":[9,40,57,79,142,169],"bioinformatics":[10],"research.":[11],"NCBI":[12,51,63,77],"BLAST,":[13],"popular":[15],"pairwise":[16],"sequence":[17],"alignment":[18],"tool,":[19],"does":[20],"not":[21],"scale":[22,100],"with":[23,48,60,102,148],"the":[24,61,91,135,190],"hundreds":[25],"gigabytes":[27],"(GB)":[28],"sequenced":[30],"data.":[31],"Therefore,":[32],"mpiBLAST":[33,44,59],"was":[34],"widely":[35],"adopted":[36],"and":[37,119,138,146,151],"scaled":[38],"up":[39,168,189],"65,536":[41],"processors.":[42],"However,":[43,83],"is":[45],"tightly":[46],"coupled":[47],"an":[49],"obsolete":[50],"BLAST":[52,64,68,78,113,131,191],"version,":[53],"creating":[54],"upgrading":[58],"ever-changing":[62],"code.":[65],"Recent":[66],"parallel":[67,87,112,130],"implementations,":[69],"like":[70],"SparkBLAST,":[71],"use":[72],"parallelism":[73],"wrappers":[74],"separate":[75],"from":[76],"overcome":[80],"this":[81,124],"issue.":[82],"query":[84],"partitioning,":[85],"method":[88],"that":[89,133],"duplicates":[90],"genome":[92],"database":[93],"on":[94],"each":[95],"compute":[96,198],"node,":[97],"makes":[98],"SparkBLAST":[99],"poorly":[101],"databases":[103],"larger":[104],"than":[105,172],"single":[107],"node's":[108],"memory.":[109],"Thus,":[110],"no":[111],"utility":[114],"simultaneously":[115],"addresses":[116],"performance,":[117],"scalability,":[118],"software":[120],"maintainability.":[121,152],"To":[122],"fill":[123],"gap,":[125],"we":[126],"introduce":[127],"SparkLeBLAST,":[128],"tool":[132],"uses":[134],"Spark":[136],"framework":[137],"efficient":[139],"partitioning":[141],"combine":[143],"mpiBLAST's":[144],"performance":[145],"scalability":[147],"SparkBLAST's":[149],"simplicity":[150],"SparkLeBLAST":[153,166,174],"democratizes":[154],"scalable":[155],"analysis":[157,183],"for":[158],"domain":[159],"scientists":[160],"without":[161],"extensive":[162],"distributed":[163],"computing":[164],"experience.":[165],"runs":[167],"6.68\u00d7":[170],"faster":[171],"SparkBLAST.":[173],"also":[175],"accelerates":[176],"taxonomic":[177],"assignment":[178],"COVID-19":[180],"diversity":[182],"by":[184,194],"20.9\u00d7":[185],"as":[186],"it":[187],"speeds":[188],"search":[192],"component":[193],"88.6\u00d7":[195],"using":[196],"128":[197],"nodes.":[199]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}