{"id":"https://openalex.org/W2794514292","doi":"https://doi.org/10.1186/s40537-018-0114-y","title":"StreamAligner: a streaming based sequence aligner on Apache Spark","display_name":"StreamAligner: a streaming based sequence aligner on Apache Spark","publication_year":2018,"publication_date":"2018-02-27","ids":{"openalex":"https://openalex.org/W2794514292","doi":"https://doi.org/10.1186/s40537-018-0114-y","mag":"2794514292"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-018-0114-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-018-0114-y","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-018-0114-y","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-018-0114-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090525461","display_name":"Sanjay Rathee","orcid":"https://orcid.org/0000-0002-2853-0842"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sanjay Rathee","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT Mandi, Kamand Campus, Mandi, India"],"raw_orcid":"https://orcid.org/0000-0002-2853-0842","affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi, Kamand Campus, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021325865","display_name":"Arti Kashyap","orcid":"https://orcid.org/0000-0003-0243-5019"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arti Kashyap","raw_affiliation_strings":["School of Basic Sciences, IIT Mandi, Kamand Campus, Mandi, 175005, India","School of Computing and Electrical Engineering, IIT Mandi, Kamand Campus, Mandi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Basic Sciences, IIT Mandi, Kamand Campus, Mandi, 175005, India","institution_ids":["https://openalex.org/I9579091"]},{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi, Kamand Campus, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090525461"],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.5567,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65263315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"5","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9861999750137329,"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/T11478","display_name":"Caching and Content Delivery","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8660626411437988},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7473589181900024},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5660895109176636},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5191482901573181},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4832221269607544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4473320245742798},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.43652281165122986},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.3227875530719757},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21032720804214478},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12517571449279785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660626411437988},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7473589181900024},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5660895109176636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5191482901573181},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4832221269607544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4473320245742798},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.43652281165122986},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3227875530719757},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21032720804214478},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12517571449279785},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-018-0114-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-018-0114-y","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-018-0114-y","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:214554fe0b4a4ce7930543f4f9b44f0e","is_oa":true,"landing_page_url":"https://doaj.org/article/214554fe0b4a4ce7930543f4f9b44f0e","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":"Journal of Big Data, Vol 5, Iss 1, Pp 1-18 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-018-0114-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-018-0114-y","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-018-0114-y","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794514292.pdf","grobid_xml":"https://content.openalex.org/works/W2794514292.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W334811598","https://openalex.org/W1904861952","https://openalex.org/W1990073900","https://openalex.org/W2004758768","https://openalex.org/W2017663296","https://openalex.org/W2017928178","https://openalex.org/W2037113830","https://openalex.org/W2037748100","https://openalex.org/W2096760403","https://openalex.org/W2097862362","https://openalex.org/W2101286050","https://openalex.org/W2103441770","https://openalex.org/W2106808791","https://openalex.org/W2111858824","https://openalex.org/W2112113834","https://openalex.org/W2121762798","https://openalex.org/W2123179625","https://openalex.org/W2124985265","https://openalex.org/W2128793361","https://openalex.org/W2139760555","https://openalex.org/W2141978878","https://openalex.org/W2143124024","https://openalex.org/W2158322625","https://openalex.org/W2159670728","https://openalex.org/W2161488606","https://openalex.org/W2189465200","https://openalex.org/W2398924165","https://openalex.org/W2568237575","https://openalex.org/W2581225544","https://openalex.org/W2592230399","https://openalex.org/W2713810026","https://openalex.org/W2949811559","https://openalex.org/W4230062012","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W3015859229","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W1975949872","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W3017846737","https://openalex.org/W3003280185","https://openalex.org/W4379407450","https://openalex.org/W2107233609"],"abstract_inverted_index":{"Next-Generation":[0],"Sequencing":[1],"technologies":[2],"are":[3,23,54,77,89,97],"generating":[4],"a":[5,147],"huge":[6,52,125],"amount":[7],"of":[8,31,45,66,99,102,120,164,275,292],"genetic":[9],"data":[10,127,136],"that":[11,223],"need":[12,133],"to":[13,48,134,140,177,200,213,262],"be":[14,175,231],"mapped":[15],"and":[16,50,75,92,180,229,272,283,290,298],"analyzed.":[17],"Single":[18],"machine":[19],"sequence":[20,68,87,95,149,242],"alignment":[21,69,142,150,181,190],"tools":[22,70],"becoming":[24],"incapable":[25],"or":[26,107,249,264],"inefficient":[27],"in":[28,82,113,137,169,226],"keeping":[29],"track":[30],"the":[32,57,117,287],"same.":[33],"Therefore,":[34,144,172],"distributed":[35,195,201],"computing":[36],"platforms":[37],"based":[38],"on":[39,110,156,166,279],"MapReduce":[40],"paradigm,":[41],"which":[42,153,191],"uses":[43,184],"thousands":[44],"commodity":[46],"machines":[47],"process":[49],"analyze":[51,135],"datasets,":[53],"emerging":[55],"as":[56,105],"best":[58],"solution":[59],"for":[60,188,233,255,267,281,295],"growing":[61,122],"genomics":[62],"data.":[63],"A":[64,270],"lot":[65],"MapReduce-based":[67,148],"like":[71],"CloudBurst,":[72],"CloudAligner,":[73],"Halvade,":[74],"SparkBWA":[76],"proposed":[78],"by":[79],"various":[80,296],"researchers":[81],"recent":[83],"few":[84,114],"years.":[85],"These":[86,94],"aligners":[88,96],"very":[90,209],"fast":[91,128],"efficient.":[93],"capable":[98],"aligning":[100],"billions":[101],"reads":[103,165],"(stored":[104],"fasta":[106],"fastq":[108],"files)":[109],"reference":[111,167],"genome":[112,126,168],"minutes.":[115],"In":[116],"current":[118,240],"era":[119],"fastly":[121],"technology,":[123],"analyzing":[124],"is":[129,154,192,208,220,277],"not":[130],"enough.":[131],"We":[132,285],"real":[138,170],"time":[139,207,261],"automate":[141,178],"process.":[143,182],"we":[145],"propose":[146],"tool":[151],"StreamAligner":[152,160,219,259],"implemented":[155],"Spark":[157,227],"streaming":[158],"engine.":[159],"can":[161,174,230],"align":[162],"stream":[163],"time.":[171],"it":[173],"used":[176,232],"sequencing":[179],"It":[183,211],"suffix":[185],"array":[186],"index":[187,196,202,205,215,224,247,252,254,266],"read":[189],"generated":[193],"using":[194],"generation":[197,203,206],"algorithm.":[198],"Due":[199],"algorithm,":[204],"less.":[210],"needs":[212],"upload":[214],"only":[216],"once":[217],"when":[218],"launched.":[221],"After":[222],"stays":[225],"memory":[228],"an":[234],"unlimited":[235],"times":[236],"without":[237],"reloading.":[238],"Whereas,":[239],"state-of-the-art":[241],"aligner":[243,294],"either":[244],"generate":[245,263],"(hash":[246],"based)":[248,253],"load":[250,265],"(sorted":[251],"every":[256,268],"task.":[257,269],"Hence,":[258],"reduces":[260],"working":[271],"tested":[273,286],"implementation":[274],"streamAligner":[276],"available":[278],"GitHub":[280],"download":[282],"use.":[284],"effectiveness,":[288],"efficiency,":[289],"scalability":[291],"our":[293],"standard":[297],"real-life":[299],"datasets.":[300]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}