{"id":"https://openalex.org/W4206680474","doi":"https://doi.org/10.1109/bigdata52589.2021.9671534","title":"A Lakehouse Architecture for the Management and Analysis of Heterogeneous Data for Biomedical Research and Mega-biobanks","display_name":"A Lakehouse Architecture for the Management and Analysis of Heterogeneous Data for Biomedical Research and Mega-biobanks","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206680474","doi":"https://doi.org/10.1109/bigdata52589.2021.9671534"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671534","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1865733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014317244","display_name":"Edmon Begoli","orcid":"https://orcid.org/0000-0002-2173-3663"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Edmon Begoli","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025338155","display_name":"Ian Goethert","orcid":"https://orcid.org/0000-0002-6978-1939"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Goethert","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019939326","display_name":"Kathryn Knight","orcid":"https://orcid.org/0000-0003-2976-0049"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathryn Knight","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014317244"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":5.2188,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96370107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4643","last_page":"4651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727336049079895},{"id":"https://openalex.org/keywords/biobank","display_name":"Biobank","score":0.7186846733093262},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6554872393608093},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.6040771007537842},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5554172992706299},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5317959189414978},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.489300936460495},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48010802268981934},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2440834939479828},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.238235741853714},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.12174651026725769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727336049079895},{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.7186846733093262},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6554872393608093},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.6040771007537842},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5554172992706299},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5317959189414978},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.489300936460495},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48010802268981934},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2440834939479828},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.238235741853714},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.12174651026725769},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1109/bigdata52589.2021.9671534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671534","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1865733","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1865733","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1865733","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1865733","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W379212275","https://openalex.org/W1575769521","https://openalex.org/W1767470961","https://openalex.org/W1911952697","https://openalex.org/W2026479502","https://openalex.org/W2041069220","https://openalex.org/W2135497544","https://openalex.org/W2149992227","https://openalex.org/W2155014757","https://openalex.org/W2155423458","https://openalex.org/W2277720319","https://openalex.org/W2302501749","https://openalex.org/W2542459869","https://openalex.org/W2548444698","https://openalex.org/W2883476975","https://openalex.org/W3085477028","https://openalex.org/W3146147323","https://openalex.org/W4237212714","https://openalex.org/W4242661747","https://openalex.org/W6634343509","https://openalex.org/W6695340201"],"related_works":["https://openalex.org/W4285087457","https://openalex.org/W2105971613","https://openalex.org/W3113746618","https://openalex.org/W4226051228","https://openalex.org/W4226156868","https://openalex.org/W4244742767","https://openalex.org/W2024651825","https://openalex.org/W4248738672","https://openalex.org/W2323349009","https://openalex.org/W2470939431"],"abstract_inverted_index":{"Data":[0],"Lakehouse":[1],"is":[2,56],"a":[3,25,50,59,88],"new":[4,51],"paradigm":[5],"in":[6,87,114],"data":[7,23,26,30,44,54,84,93],"architectures":[8],"that":[9,64],"embodies":[10],"and":[11,39,72,91,96,104,119,122],"integrates":[12],"already":[13],"established":[14],"concepts":[15],"for":[16,28,36,110,124],"the":[17,43,53,66,83,99,125],"systematic":[18,40],"management":[19],"of":[20,33,42,82,101,116],"disparate,":[21],"large-scale":[22],"\u2013":[24],"lake":[27],"heterogeneous":[29],"management,":[31],"use":[32,65],"open":[34],"standards":[35],"high-performance":[37],"querying,":[38],"maintenance":[41],"\"freshness\".":[45],"In":[46,75],"addition":[47],"to":[48],"being":[49],"concept,":[52],"lakehouse":[55,67,85],"also":[57],"still":[58],"conceptual":[60],"construct.":[61],"Many":[62],"projects":[63],"require":[68],"maturing,":[69],"empirical":[70],"studies,":[71],"specific":[73],"implementations.":[74],"this":[76],"paper,":[77],"we":[78,97],"present":[79],"our":[80],"implementation":[81,100],"concept":[86],"biomedical":[89],"research":[90],"health":[92],"analytics":[94],"domain,":[95],"discuss":[98],"some":[102],"unique":[103],"novel":[105],"features":[106],"such":[107],"as":[108],"support":[109,115,123],"specialized":[111],"access":[112],"controls":[113],"HIPAA":[117],"regulation":[118],"IRB":[120],"protocols,":[121],"FAIR":[126],"standard.":[127],"<sup":[128],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}
