{"id":"https://openalex.org/W1969462276","doi":"https://doi.org/10.1198/004017002317375064","title":"A Modification of the Jaccard\u2013Tanimoto Similarity Index for Diverse Selection of Chemical Compounds Using Binary Strings","display_name":"A Modification of the Jaccard\u2013Tanimoto Similarity Index for Diverse Selection of Chemical Compounds Using Binary Strings","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1969462276","doi":"https://doi.org/10.1198/004017002317375064","mag":"1969462276"},"language":"en","primary_location":{"id":"doi:10.1198/004017002317375064","is_oa":false,"landing_page_url":"https://doi.org/10.1198/004017002317375064","pdf_url":null,"source":{"id":"https://openalex.org/S985303","display_name":"Technometrics","issn_l":"0040-1706","issn":["0040-1706","1537-2723"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technometrics","raw_type":"journal-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/A5011700059","display_name":"Michael A. Fligner","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael A Fligner","raw_affiliation_strings":["Department of Statistics, The Ohio State University, Columbus, OH 43210"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, The Ohio State University, Columbus, OH 43210","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018385260","display_name":"Joseph S. Verducci","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph S Verducci","raw_affiliation_strings":["Department of Statistics, The Ohio State University, Columbus, OH 43210"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, The Ohio State University, Columbus, OH 43210","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006551243","display_name":"Paul E. Blower","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104424","display_name":"LeadScope (United States)","ror":"https://ror.org/01btem129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210104424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul E Blower","raw_affiliation_strings":["LeadScope, Inc., 1275 Kinnear Road, Columbus, OH 43212"],"affiliations":[{"raw_affiliation_string":"LeadScope, Inc., 1275 Kinnear Road, Columbus, OH 43212","institution_ids":["https://openalex.org/I4210104424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011700059"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":5.2493,"has_fulltext":false,"cited_by_count":138,"citation_normalized_percentile":{"value":0.9621362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"44","issue":"2","first_page":"110","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9836999773979187,"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/jaccard-index","display_name":"Jaccard index","score":0.9405068159103394},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.757876992225647},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6322976350784302},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5551493167877197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5206345915794373},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4664211869239807},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4548524022102356},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.4300597012042999},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41647934913635254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36161571741104126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27887049317359924},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11691209673881531}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9405068159103394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.757876992225647},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6322976350784302},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5551493167877197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5206345915794373},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4664211869239807},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4548524022102356},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4300597012042999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41647934913635254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36161571741104126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27887049317359924},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11691209673881531},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1198/004017002317375064","is_oa":false,"landing_page_url":"https://doi.org/10.1198/004017002317375064","pdf_url":null,"source":{"id":"https://openalex.org/S985303","display_name":"Technometrics","issn_l":"0040-1706","issn":["0040-1706","1537-2723"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technometrics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1963790256","https://openalex.org/W1985067238","https://openalex.org/W2006575776","https://openalex.org/W2062556965","https://openalex.org/W2096729078","https://openalex.org/W2160114756","https://openalex.org/W2167395325","https://openalex.org/W2499419648","https://openalex.org/W2522646202","https://openalex.org/W2952541077","https://openalex.org/W2964483208","https://openalex.org/W3138771162","https://openalex.org/W3147295069"],"related_works":["https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2558988915","https://openalex.org/W2972216353","https://openalex.org/W73805934"],"abstract_inverted_index":{"Determination":[0],"of":[1,33,46,90,103,129,132,139],"molecular":[2],"similarity":[3,47],"plays":[4],"an":[5,61,69],"important":[6],"role":[7],"in":[8,13,122],"analyzing":[9],"large":[10,107],"compound":[11],"databases":[12],"chemical":[14,49],"and":[15,94,127],"pharmaceutical":[16],"research.":[17],"When":[18,109],"molecules":[19],"are":[20],"described":[21],"by":[22,146],"binary":[23],"vectors":[24],"with":[25],"bits":[26],"corresponding":[27],"to":[28,57,117],"the":[29,36,41,65,91,96,110,123,136,142],"presence":[30],"or":[31,48],"absence":[32],"structural":[34],"features,":[35],"Tanimoto":[37,66,111],"association":[38,80],"coefficient":[39,67,81,93,112],"is":[40,113],"most":[42],"commonly":[43],"used":[44,56],"measure":[45],"distance":[50],"between":[51],"two":[52,97],"compounds.":[53,74],"However,":[54],"when":[55],"select":[58,118],"compounds":[59,104,144],"for":[60,99],"optimal":[62],"spread":[63],"design,":[64],"produces":[68],"intrinsic":[70],"bias":[71],"toward":[72],"smaller":[73],"We":[75],"have":[76],"developed":[77],"a":[78,106,119],"new":[79,92],"that":[82],"overcomes":[83],"this":[84],"bias.":[85],"This":[86],"article":[87],"gives":[88],"details":[89],"contrasts":[95],"coefficients":[98],"selecting":[100],"diverse":[101,120],"sets":[102],"from":[105],"collection.":[108],"modified":[114],"as":[115],"suggested":[116],"set":[121],"National":[124],"Cancer":[125],"Institute":[126],"Registry":[128],"Toxic":[130],"Effects":[131],"Chemical":[133],"Substances":[134],"databases,":[135],"average":[137],"number":[138],"features":[140],"among":[141],"selected":[143],"increases":[145],"more":[147],"than":[148],"50%.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}