{"id":"https://openalex.org/W2949435151","doi":"https://doi.org/10.1021/ci980109e","title":"Molecular Diversity and Representativity in Chemical Databases","display_name":"Molecular Diversity and Representativity in Chemical Databases","publication_year":1998,"publication_date":"1998-12-16","ids":{"openalex":"https://openalex.org/W2949435151","doi":"https://doi.org/10.1021/ci980109e","mag":"2949435151"},"language":"en","primary_location":{"id":"doi:10.1021/ci980109e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci980109e","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/A5045319813","display_name":"Denis M. Bayada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis M. Bayada","raw_affiliation_strings":["Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054371513","display_name":"Hans Hamersma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans Hamersma","raw_affiliation_strings":["Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025695891","display_name":"V. J. van Geerestein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent J. van Geerestein","raw_affiliation_strings":["Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Design & Informatics, N.V. Organon, P.O. Box 20, 5340 BH Oss, The Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.6753,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.99524397,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"39","issue":"1","first_page":"1","last_page":"10"},"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":0.9721999764442444,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9174000024795532,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6831380128860474},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6133059859275818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5870496034622192},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.5593304634094238},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5468286871910095},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5006730556488037},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.4758308231830597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4121948480606079},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.41084909439086914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4058968722820282},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.2528179883956909}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6831380128860474},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6133059859275818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5870496034622192},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.5593304634094238},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5468286871910095},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5006730556488037},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.4758308231830597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4121948480606079},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.41084909439086914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4058968722820282},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.2528179883956909},{"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/ci980109e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci980109e","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":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1605923270","https://openalex.org/W1973175049","https://openalex.org/W1976160686","https://openalex.org/W1981214699","https://openalex.org/W2005685204","https://openalex.org/W2021083597","https://openalex.org/W2037730130","https://openalex.org/W2064751934","https://openalex.org/W2069530087","https://openalex.org/W2077583250","https://openalex.org/W2078115945","https://openalex.org/W2082698910","https://openalex.org/W2085911438","https://openalex.org/W2152629484","https://openalex.org/W2503053030","https://openalex.org/W2504627914","https://openalex.org/W2951517626"],"related_works":["https://openalex.org/W2381926679","https://openalex.org/W2007009951","https://openalex.org/W2082644203","https://openalex.org/W3165040664","https://openalex.org/W2350539780","https://openalex.org/W3122652148","https://openalex.org/W1583866266","https://openalex.org/W4242386713","https://openalex.org/W2002351209","https://openalex.org/W2996505764"],"abstract_inverted_index":{"It":[0],"is":[1,152],"now":[2],"common":[3],"practice":[4],"in":[5,129],"the":[6,16,47,64],"pharmaceutical":[7],"industry":[8],"to":[9,38,74,126],"use":[10],"molecular":[11],"diversity":[12,50,59],"selection":[13,60,128,149],"methods.":[14,169],"With":[15],"advent":[17],"of":[18,32,34,36,71,76,83,89,134,168,174],"high":[19],"throughput":[20],"screening":[21],"and":[22,51,86,92],"combinatorial":[23],"chemistry,":[24],"compounds":[25,37,72],"must":[26],"be":[27,39],"rationally":[28],"selected":[29],"from":[30,136,150],"databases":[31],"hundreds":[33],"thousands":[35],"tested":[40],"for":[41,57,104],"several":[42,67],"biological":[43,108],"activities.":[44,109],"We":[45,110],"explore":[46],"differences":[48],"between":[49],"representativity.":[52],"Validation":[53],"runs":[54],"were":[55,102],"made":[56],"different":[58],"methods":[61],"(such":[62],"as":[63],"MaxMin":[65],"function),":[66],"representativity":[68],"techniques":[69],"(selection":[70],"closest":[73],"centroids":[75],"clusters,":[77],"Kohonen":[78],"neural":[79],"networks,":[80],"nonlinear":[81],"scaling":[82],"descriptor":[84],"values),":[85],"various":[87],"types":[88,167],"descriptors":[90,100,121,172],"(topological":[91],"3D":[93],"fingerprints)":[94],"including":[95],"some":[96],"validated":[97],"whole-molecule":[98,120],"numerical":[99,171],"that":[101,112,147,159],"chosen":[103],"their":[105],"correlation":[106],"with":[107,139],"find":[111],"only":[113],"clustering":[114,148],"based":[115],"on":[116,119],"fingerprints":[117,151,175],"or":[118],"gives":[122],"results":[123,144],"consistently":[124],"superior":[125],"random":[127],"extracting":[130],"a":[131,137,157],"diverse":[132],"set":[133],"activities":[135],"file":[138],"potential":[140],"drug":[141],"molecules.":[142],"The":[143],"further":[145],"indicate":[146],"biased":[153],"toward":[154],"small":[155],"molecules,":[156],"behavior":[158],"might":[160],"partly":[161],"explain":[162],"its":[163],"success":[164],"over":[165],"other":[166],"Using":[170],"instead":[173],"removes":[176],"this":[177],"bias":[178],"without":[179],"penalising":[180],"performance":[181],"too":[182],"much.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}