{"id":"https://openalex.org/W2217498234","doi":"https://doi.org/10.1109/bibm.2015.7359781","title":"A highly parallel next-generation DNA sequencing data analysis pipeline in Hadoop","display_name":"A highly parallel next-generation DNA sequencing data analysis pipeline in Hadoop","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2217498234","doi":"https://doi.org/10.1109/bibm.2015.7359781","mag":"2217498234"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2015.7359781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050284653","display_name":"Kareem S. Aggour","orcid":"https://orcid.org/0000-0002-7467-3836"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kareem S. Aggour","raw_affiliation_strings":["Knowledge Discovery Lab"],"affiliations":[{"raw_affiliation_string":"Knowledge Discovery Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673411","display_name":"Virendra Kumar","orcid":"https://orcid.org/0000-0003-2234-1546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay S. Kumar","raw_affiliation_strings":["Knowledge Discovery Lab"],"affiliations":[{"raw_affiliation_string":"Knowledge Discovery Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079607594","display_name":"Dipen P. Sangurdekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dipen P. Sangurdekar","raw_affiliation_strings":["Computational Biology and Biostatistics Lab GE Global Research"],"affiliations":[{"raw_affiliation_string":"Computational Biology and Biostatistics Lab GE Global Research","institution_ids":["https://openalex.org/I4210134512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057953740","display_name":"Lee A. Newberg","orcid":"https://orcid.org/0000-0003-4644-8874"},"institutions":[{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee A. Newberg","raw_affiliation_strings":["Computational Biology and Biostatistics Lab GE Global Research"],"affiliations":[{"raw_affiliation_string":"Computational Biology and Biostatistics Lab GE Global Research","institution_ids":["https://openalex.org/I4210134512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066179673","display_name":"Chinnappa D. Kodira","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinnappa D. Kodira","raw_affiliation_strings":["Computational Biology and Biostatistics Lab GE Global Research"],"affiliations":[{"raw_affiliation_string":"Computational Biology and Biostatistics Lab GE Global Research","institution_ids":["https://openalex.org/I4210134512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050284653"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4544,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64081941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"756","last_page":"763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9970999956130981,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/pipeline","display_name":"Pipeline (software)","score":0.7969084978103638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587721943855286},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6996108889579773},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.6508058309555054},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6210328936576843},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5452426671981812},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5227656364440918},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5050342679023743},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43297138810157776},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4221581816673279},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3702036142349243},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32551154494285583},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23356449604034424},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22557085752487183},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.20858687162399292},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11786571145057678},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10648685693740845},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0918419361114502}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7969084978103638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587721943855286},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6996108889579773},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.6508058309555054},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6210328936576843},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5452426671981812},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5227656364440918},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5050342679023743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43297138810157776},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4221581816673279},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3702036142349243},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32551154494285583},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23356449604034424},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22557085752487183},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.20858687162399292},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11786571145057678},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10648685693740845},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0918419361114502},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2015.7359781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W1978251004","https://openalex.org/W2034798008","https://openalex.org/W2042935997","https://openalex.org/W2053582911","https://openalex.org/W2054905474","https://openalex.org/W2096791516","https://openalex.org/W2103441770","https://openalex.org/W2104846587","https://openalex.org/W2108234281","https://openalex.org/W2109701112","https://openalex.org/W2122732537","https://openalex.org/W2130626344","https://openalex.org/W2140723686","https://openalex.org/W2148294372","https://openalex.org/W2159670728","https://openalex.org/W2159715390","https://openalex.org/W2170551349","https://openalex.org/W2408045830","https://openalex.org/W3101182326","https://openalex.org/W6713636576","https://openalex.org/W7005645303","https://openalex.org/W7037897006"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2071821326","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397"],"abstract_inverted_index":{"The":[0],"era":[1],"of":[2,106,113,130,138,140],"precision":[3],"medicine":[4],"is":[5,78],"best":[6],"exemplified":[7],"by":[8,205],"the":[9,104,128,136,160,198],"growing":[10],"reliance":[11],"on":[12,145],"next-generation":[13,65],"sequencing":[14,67,201],"(NGS)":[15],"technologies":[16],"to":[17,39,189],"provide":[18],"improved":[19],"disease":[20],"diagnosis":[21],"and":[22,41,45,134,163,194,208],"targeted":[23],"therapeutic":[24],"selection.":[25],"Well-established":[26],"NGS":[27],"data":[28,68],"analysis":[29,57,69],"software":[30],"tools,":[31],"in":[32,48,71,154,159,167,171,176,192],"their":[33],"unmodified":[34],"form,":[35],"can":[36,195],"take":[37],"days":[38],"identify":[40],"interpret":[42],"single":[43,52,96],"nucleotide":[44],"structural":[46],"variations":[47],"DNA":[49,66,200],"for":[50],"a":[51,61,91,95,114,156,164,173],"patient.":[53],"To":[54],"improve":[55],"sample":[56],"throughput,":[58],"we":[59,101],"developed":[60],"highly":[62],"parallel":[63],"end-to-end":[64],"pipeline":[70,110,123],"Hadoop.":[72],"In":[73,143],"our":[74,108,122,146],"pipeline,":[75],"each":[76,87],"step":[77],"parallelized":[79],"not":[80],"only":[81,155,172],"across":[82],"samples":[83,131,152],"but":[84],"also":[85],"within":[86],"individual":[88],"sample,":[89],"achieving":[90],"30\u00d7":[92],"speedup":[93],"over":[94],"server":[97],"workflow":[98],"execution.":[99],"Furthermore,":[100],"extensively":[102],"evaluate":[103],"viability":[105],"having":[107],"Hadoop-based":[109],"as":[111,150],"part":[112],"larger":[115],"commercial":[116],"genomic":[117],"services":[118],"offering-we":[119],"demonstrate":[120],"how":[121],"scales":[124],"sub-linearly":[125],"both":[126,206],"with":[127,135],"number":[129],"being":[132],"analyzed":[133,191],"depth":[137,169],"coverage":[139,168],"those":[141],"samples.":[142],"particular,":[144],"commodity":[147],"cluster,":[148],"10\u00d7":[149],"many":[151],"resulted":[153,170],"2.24\u00d7":[157],"increase":[158,166],"execution":[161,177],"time,":[162],"4\u00d7":[165],"2.53\u00d7":[174],"growth":[175],"time.":[178],"We":[179],"anticipate":[180],"that":[181],"such":[182],"improvements":[183],"will":[184],"allow":[185],"large":[186],"cohort":[187],"populations":[188],"be":[190],"parallel,":[193],"fundamentally":[196],"change":[197],"way":[199],"analyses":[202],"are":[203],"used":[204],"researchers":[207],"clinicians.":[209]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}