{"id":"https://openalex.org/W2127798779","doi":"https://doi.org/10.1109/icde.2004.1320050","title":"From sipping on a straw to drinking from a fire hose: data integration in a public genome database","display_name":"From sipping on a straw to drinking from a fire hose: data integration in a public genome database","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2127798779","doi":"https://doi.org/10.1109/icde.2004.1320050","mag":"2127798779"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1320050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062064598","display_name":"Joel E. Richardson","orcid":"https://orcid.org/0000-0003-3342-5753"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.E. Richardson","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038370465","display_name":"James A. Kadin","orcid":"https://orcid.org/0000-0002-7644-3743"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.A. Kadin","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016349593","display_name":"Judith A. Blake","orcid":"https://orcid.org/0000-0001-8522-334X"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.A. Blake","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028990206","display_name":"Carol J. Bult","orcid":"https://orcid.org/0000-0001-9433-210X"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.J. Bult","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006382524","display_name":"Janan T. Eppig","orcid":"https://orcid.org/0000-0003-1652-8072"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.T. Eppig","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070528752","display_name":"Martin Ringwald","orcid":"https://orcid.org/0000-0002-5696-5421"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Ringwald","raw_affiliation_strings":["Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mouse Genome Informatics Group, Jackson Laboratory, Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"Mouse Genome Informatics Group, The Jackson Lab., Bar Harbor, ME, USA","institution_ids":["https://openalex.org/I4210115256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210115256"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"795","last_page":"798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.988099992275238,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.988099992275238,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9819999933242798,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6154860854148865},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.610923707485199},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5644068121910095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5188435316085815},{"id":"https://openalex.org/keywords/nexus","display_name":"Nexus (standard)","score":0.47211968898773193},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46811550855636597},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.45658108592033386},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3153224289417267},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24611464142799377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18507912755012512},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1115698516368866}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6154860854148865},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.610923707485199},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5644068121910095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188435316085815},{"id":"https://openalex.org/C148609458","wikidata":"https://www.wikidata.org/wiki/Q7021281","display_name":"Nexus (standard)","level":2,"score":0.47211968898773193},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46811550855636597},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.45658108592033386},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3153224289417267},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24611464142799377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18507912755012512},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1115698516368866},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2004.1320050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1597603991","https://openalex.org/W1986234964","https://openalex.org/W2041842900","https://openalex.org/W2075495563"],"related_works":["https://openalex.org/W3126909309","https://openalex.org/W4256360871","https://openalex.org/W2747100754","https://openalex.org/W3117832639","https://openalex.org/W2885513359","https://openalex.org/W2802787844","https://openalex.org/W1578170453","https://openalex.org/W2965101536","https://openalex.org/W2891178753","https://openalex.org/W3121214617"],"abstract_inverted_index":{"Biology":[0],"is":[1,47],"a":[2,22],"vast":[3],"domain.":[4],"The":[5],"Mouse":[6],"Genome":[7],"Informatics":[8],"(MGI)":[9],"system,":[10],"which":[11],"focuses":[12],"on":[13],"the":[14,17,70,80],"biology":[15],"of":[16,32,55,69],"laboratory":[18],"mouse,":[19],"covers":[20],"only":[21],"small,":[23],"carefully":[24],"chosen":[25],"slice.":[26],"Nevertheless,":[27],"we":[28,72,76],"deal":[29],"with":[30],"data":[31,53],"immense":[33],"variety,":[34],"deep":[35],"complexity,":[36],"and":[37,58,62,74],"exponentially":[38],"growing":[39],"volume.":[40],"Our":[41],"role":[42],"as":[43],"an":[44],"integration":[45,81],"nexus":[46],"to":[48,79],"add":[49],"value":[50],"by":[51],"combining":[52],"sets":[54],"diverse":[56],"types":[57],"origins,":[59],"eliminating":[60],"redundancy":[61],"resolving":[63],"conflicts.":[64],"We":[65],"briefly":[66],"describe":[67],"some":[68],"issues":[71],"face":[73],"approaches":[75],"have":[77],"adopted":[78],"problem.":[82]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}