{"id":"https://openalex.org/W1984994707","doi":"https://doi.org/10.1021/ci9803381","title":"Unsupervised Data Base Clustering Based on Daylight's Fingerprint and Tanimoto Similarity: A Fast and Automated Way To Cluster Small and Large Data Sets","display_name":"Unsupervised Data Base Clustering Based on Daylight's Fingerprint and Tanimoto Similarity: A Fast and Automated Way To Cluster Small and Large Data Sets","publication_year":1999,"publication_date":"1999-06-29","ids":{"openalex":"https://openalex.org/W1984994707","doi":"https://doi.org/10.1021/ci9803381","mag":"1984994707"},"language":"en","primary_location":{"id":"doi:10.1021/ci9803381","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci9803381","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","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/A5110355540","display_name":"Darko Butina","orcid":null},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Darko Butina","raw_affiliation_strings":["Science Development Group - Biomet, Glaxo Wellcome Research and Development, Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Development Group - Biomet, Glaxo Wellcome Research and Development, Medicines Research Centre, Gunnels Wood Road, Stevenage, Hertfordshire SG1 2NY, U.K","institution_ids":["https://openalex.org/I141584323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110355540"],"corresponding_institution_ids":["https://openalex.org/I141584323"],"apc_list":null,"apc_paid":null,"fwci":1.2605,"has_fulltext":false,"cited_by_count":626,"citation_normalized_percentile":{"value":0.74321466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"39","issue":"4","first_page":"747","last_page":"750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9907000064849854,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12748","display_name":"Molecular spectroscopy and chirality","score":0.9496999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8506050109863281},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7427159547805786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6286416053771973},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.571342945098877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.569091796875},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5299336314201355},{"id":"https://openalex.org/keywords/rand-index","display_name":"Rand index","score":0.4821333587169647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4779260754585266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47420576214790344},{"id":"https://openalex.org/keywords/daylight","display_name":"Daylight","score":0.4621458947658539},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10376322269439697},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09429872035980225}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8506050109863281},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7427159547805786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286416053771973},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.571342945098877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.569091796875},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5299336314201355},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.4821333587169647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4779260754585266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47420576214790344},{"id":"https://openalex.org/C149277555","wikidata":"https://www.wikidata.org/wiki/Q16491","display_name":"Daylight","level":2,"score":0.4621458947658539},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10376322269439697},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09429872035980225},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1021/ci9803381","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci9803381","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1973826313","https://openalex.org/W2023059455","https://openalex.org/W2059975159","https://openalex.org/W2066345214","https://openalex.org/W2069530087","https://openalex.org/W2089923519","https://openalex.org/W3147295069","https://openalex.org/W4298236029"],"related_works":["https://openalex.org/W2419012894","https://openalex.org/W2381926679","https://openalex.org/W2061034917","https://openalex.org/W3048570979","https://openalex.org/W3172567524","https://openalex.org/W2153388278","https://openalex.org/W2020075988","https://openalex.org/W653992766","https://openalex.org/W4311784074","https://openalex.org/W2548744215"],"abstract_inverted_index":{"One":[0],"of":[1,27,44,51,88],"the":[2,9,36,56,86,89,142,147,153,162,171,187,200],"most":[3],"commonly":[4],"used":[5,145,182],"clustering":[6,58],"algorithms":[7],"within":[8,138,170],"worldwide":[10],"pharmaceutical":[11],"industry":[12],"is":[13],"Jarvis\u2212Patrick's":[14],"(J\u2212P)":[15],"(Jarvis,":[16],"R.":[17],"A.":[18],"IEEE":[19],"Trans.":[20],"Comput.":[21],"1973,":[22],"C-22,":[23],"1025\u22121034).":[24],"The":[25,79,179],"implementation":[26],"J\u2212P":[28,57,95,120],"under":[29],"Daylight":[30],"software,":[31],"using":[32],"Daylight's":[33,197],"fingerprints":[34,198],"and":[35,76,110,176,199],"Tanimoto":[37,143,164,201],"similarity":[38,137,180,189,202],"index,":[39],"can":[40],"deal":[41],"with":[42],"sets":[43,72],"100":[45],"k":[46],"molecules":[47],"in":[48,73,173],"a":[49,52,74,174],"matter":[50],"few":[53],"hours.":[54],"However,":[55],"algorithm":[59,130],"has":[60],"several":[61],"associated":[62],"problems":[63],"which":[64,105,131],"make":[65],"it":[66],"difficult":[67],"to":[68,93,102,166],"cluster":[69,140,154,172],"large":[70,109],"data":[71],"consistent":[75,175],"timely":[77],"manner.":[78,178],"clusters":[80,104,135],"produced":[81],"are":[82,106],"greatly":[83],"dependent":[84],"on":[85],"choice":[87],"two":[90,191],"parameters":[91],"needed":[92],"run":[94],"clustering,":[96,148],"such":[97],"that":[98],"this":[99,184],"method":[100],"tends":[101],"produce":[103],"either":[107],"very":[108],"heterogeneous":[111],"or":[112],"homogeneous":[113],"but":[114],"too":[115],"small.":[116],"In":[117],"any":[118],"case,":[119],"always":[121],"requires":[122],"time-consuming":[123],"manual":[124],"tuning.":[125],"This":[126],"paper":[127,185],"describes":[128],"an":[129],"will":[132,156],"identify":[133],"dense":[134],"where":[136,152],"each":[139],"reflects":[141,186],"value":[144],"for":[146],"and,":[149],"more":[150],"importantly,":[151],"centroid":[155],"be":[157],"at":[158,161],"least":[159],"similar,":[160],"given":[163,192],"value,":[165],"every":[167],"other":[168],"molecule":[169],"automated":[177],"term":[181],"throughout":[183],"overall":[188],"between":[190],"molecules,":[193],"as":[194],"defined":[195],"by":[196],"index.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":43},{"year":2025,"cited_by_count":78},{"year":2024,"cited_by_count":97},{"year":2023,"cited_by_count":65},{"year":2022,"cited_by_count":46},{"year":2021,"cited_by_count":65},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}