{"id":"https://openalex.org/W1971647276","doi":"https://doi.org/10.1145/2811163.2811175","title":"Evaluation of a Machine Learning Duplicate Detection Method for Bioinformatics Databases","display_name":"Evaluation of a Machine Learning Duplicate Detection Method for Bioinformatics Databases","publication_year":2015,"publication_date":"2015-10-22","ids":{"openalex":"https://openalex.org/W1971647276","doi":"https://doi.org/10.1145/2811163.2811175","mag":"1971647276"},"language":"en","primary_location":{"id":"doi:10.1145/2811163.2811175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2811163.2811175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics","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/A5042874172","display_name":"Qingyu Chen","orcid":"https://orcid.org/0000-0002-6036-1516"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qingyu Chen","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia","University of Melbourne, Melbourne, Australia,"],"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia,","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia","University of Melbourne, Melbourne, Australia,"],"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia,","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia","University of Melbourne, Melbourne, Australia,"],"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia,","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042874172"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":4.62744814,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95537946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9896000027656555,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9294999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7240522503852844},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5924621224403381},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5555583834648132},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5115455389022827},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49762967228889465},{"id":"https://openalex.org/keywords/biological-database","display_name":"Biological database","score":0.4948365092277527},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.48526737093925476},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45769956707954407},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36915141344070435},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.30751925706863403},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10507291555404663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07851165533065796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240522503852844},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5924621224403381},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5555583834648132},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5115455389022827},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49762967228889465},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.4948365092277527},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.48526737093925476},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45769956707954407},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36915141344070435},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.30751925706863403},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10507291555404663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07851165533065796},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2811163.2811175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2811163.2811175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1965664689","https://openalex.org/W1975914194","https://openalex.org/W1976369037","https://openalex.org/W1982806687","https://openalex.org/W2002180966","https://openalex.org/W2019096410","https://openalex.org/W2024231807","https://openalex.org/W2032838501","https://openalex.org/W2056646105","https://openalex.org/W2062296203","https://openalex.org/W2065199439","https://openalex.org/W2072603644","https://openalex.org/W2075715210","https://openalex.org/W2076048958","https://openalex.org/W2084258053","https://openalex.org/W2093794723","https://openalex.org/W2106302492","https://openalex.org/W2108991785","https://openalex.org/W2116699248","https://openalex.org/W2118597789","https://openalex.org/W2120158278","https://openalex.org/W2121973229","https://openalex.org/W2133610185","https://openalex.org/W2156125289","https://openalex.org/W2161062388","https://openalex.org/W2170902582","https://openalex.org/W2399636967","https://openalex.org/W2732123266","https://openalex.org/W2786418370","https://openalex.org/W4376524361","https://openalex.org/W6747823444","https://openalex.org/W6807695228"],"related_works":["https://openalex.org/W4312158493","https://openalex.org/W2033835987","https://openalex.org/W4248750016","https://openalex.org/W4205092877","https://openalex.org/W1824784554","https://openalex.org/W3141940143","https://openalex.org/W1561860948","https://openalex.org/W1979295894","https://openalex.org/W2267080198","https://openalex.org/W2123887743"],"abstract_inverted_index":{"The":[0],"impact":[1],"of":[2,20,23,27,60,93],"duplicate":[3,94],"or":[4,36],"inconsistent":[5],"records":[6,39],"in":[7],"databases":[8,15],"can":[9],"be":[10],"severe,":[11],"and":[12,87],"for":[13,25,51,62,70],"general":[14,120],"has":[16,48,80],"led":[17],"to":[18,85,100,118,122],"development":[19],"a":[21,45,57],"range":[22],"techniques":[24,61,69],"identification":[26],"such":[28],"records.":[29],"In":[30],"bioinformatics,":[31],"duplication":[32],"arises":[33],"when":[34],"two":[35],"more":[37],"database":[38],"represent":[40],"the":[41,91],"same":[42],"biological":[43],"entity,":[44],"problem":[46],"that":[47],"been":[49],"known":[50],"over":[52,81],"20":[53],"years.":[54],"However,":[55],"only":[56],"limited":[58],"number":[59],"detecting":[63],"bioinformatics":[64],"duplicates":[65],"have":[66],"emerged.":[67],"Special":[68],"handling":[71],"large":[72],"data":[73,78,89],"sets":[74],"(a":[75],"common":[76],"5000-record":[77],"set":[79],"10":[82],"million":[83],"pairs":[84,95],"compare)":[86],"imbalanced":[88],"(where":[90],"prevalence":[92],"is":[96,115],"minute":[97],"as":[98],"compared":[99],"non-duplicate":[101],"pairs).":[102],"Biological":[103],"domain":[104],"interpretation":[105],"(records":[106],"with":[107],"very":[108],"similar":[109],"sequences":[110],"are":[111],"not":[112],"necessarily":[113],"duplicates)":[114],"also":[116],"important":[117],"adapt":[119],"methods":[121],"this":[123],"context.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
