{"id":"https://openalex.org/W1990696547","doi":"https://doi.org/10.1021/ci025591m","title":"Evaluation of Similarity Measures for Searching the <i>Dictionary of Natural Products</i> Database","display_name":"Evaluation of Similarity Measures for Searching the <i>Dictionary of Natural Products</i> Database","publication_year":2003,"publication_date":"2003-01-28","ids":{"openalex":"https://openalex.org/W1990696547","doi":"https://doi.org/10.1021/ci025591m","mag":"1990696547","pmid":"https://pubmed.ncbi.nlm.nih.gov/12653508"},"language":"en","primary_location":{"id":"doi:10.1021/ci025591m","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci025591m","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","pubmed"],"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/A5108785323","display_name":"Martin Whittle","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Whittle","raw_affiliation_strings":["Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom. m.whittle@sheffield.ac.uk","Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom. m.whittle@sheffield.ac.uk","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102885255","display_name":"Peter Willett","orcid":"https://orcid.org/0000-0003-4591-7173"},"institutions":[{"id":"https://openalex.org/I4210113155","display_name":"Unilever (Netherlands)","ror":"https://ror.org/02436cs38","country_code":"NL","type":"company","lineage":["https://openalex.org/I1342131907","https://openalex.org/I4210113155"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Peter Willett","raw_affiliation_strings":["Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands","institution_ids":["https://openalex.org/I4210113155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064259122","display_name":"Werner Klaffke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113155","display_name":"Unilever (Netherlands)","ror":"https://ror.org/02436cs38","country_code":"NL","type":"company","lineage":["https://openalex.org/I1342131907","https://openalex.org/I4210113155"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Werner Klaffke","raw_affiliation_strings":["Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands","institution_ids":["https://openalex.org/I4210113155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009585076","display_name":"Paula van Noort","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113155","display_name":"Unilever (Netherlands)","ror":"https://ror.org/02436cs38","country_code":"NL","type":"company","lineage":["https://openalex.org/I1342131907","https://openalex.org/I4210113155"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Paula van Noort","raw_affiliation_strings":["Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Unilever Research and Development, Unilever Health Institute, Vlaardingen, Oliver van Noortlaan 120, 3133 AT Vlaardingen, The Netherlands","institution_ids":["https://openalex.org/I4210113155"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108785323"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":4.732,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95206832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"43","issue":"2","first_page":"449","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9940999746322632,"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/T11882","display_name":"Plant biochemistry and biosynthesis","score":0.9918000102043152,"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/similarity","display_name":"Similarity (geometry)","score":0.8000580072402954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5919651389122009},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5401998162269592},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5213785767555237},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.46024081110954285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43313199281692505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.42359447479248047},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4166828393936157},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3693506121635437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34626102447509766}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8000580072402954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5919651389122009},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5401998162269592},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5213785767555237},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.46024081110954285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43313199281692505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42359447479248047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4166828393936157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693506121635437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34626102447509766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci025591m","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci025591m","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"},{"id":"pmid:12653508","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12653508","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320670","display_name":"Wolfson Foundation","ror":"https://ror.org/0333xzh65"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1493396923","https://openalex.org/W1601835124","https://openalex.org/W1969462276","https://openalex.org/W1991619291","https://openalex.org/W2000942311","https://openalex.org/W2003752196","https://openalex.org/W2003932708","https://openalex.org/W2030686695","https://openalex.org/W2035180565","https://openalex.org/W2062556965","https://openalex.org/W2071717945","https://openalex.org/W2080734107","https://openalex.org/W2093265335","https://openalex.org/W2096729078","https://openalex.org/W2110556045","https://openalex.org/W2949243165"],"related_works":["https://openalex.org/W3027599074","https://openalex.org/W2410198229","https://openalex.org/W2019538911","https://openalex.org/W2399932691","https://openalex.org/W2056162765","https://openalex.org/W2334800106","https://openalex.org/W1498782543","https://openalex.org/W420686868","https://openalex.org/W2583727515","https://openalex.org/W1990696547"],"abstract_inverted_index":{"Similarity":[0],"searches":[1],"using":[2,130,145],"combinations":[3],"of":[4,20,33,55,58,69,75,112,117],"seven":[5],"different":[6,11,42,81],"similarity":[7,59],"coefficients":[8,111],"and":[9,92,119,135,148],"six":[10],"representations":[12],"have":[13,51,96,127],"been":[14,52,97,128],"carried":[15],"out":[16],"on":[17,105],"the":[18,46,53,70,90,110,115,154],"Dictionary":[19],"Natural":[21],"Products":[22],"database.":[23],"The":[24,80],"objective":[25],"was":[26,63],"to":[27,36,99,102],"discover":[28],"if":[29],"any":[30],"special":[31],"methods":[32],"searching":[34],"apply":[35],"this":[37],"database,":[38],"which":[39,95],"is":[40],"very":[41],"in":[43,114,139,151],"nature":[44],"from":[45,73,124],"many":[47],"synthetic":[48],"databases":[49],"that":[50],"subject":[54],"previous":[56],"studies":[57],"searching.":[60],"Search":[61],"effectiveness":[62],"assessed":[64],"by":[65,144],"a":[66,103,131],"recall":[67],"analysis":[68],"search":[71],"outputs":[72],"sets":[74,83],"pharmacologically":[76],"active":[77],"target":[78,82],"structures.":[79],"produce":[84],"exceptional":[85],"but":[86],"contradictory":[87],"results":[88,126],"for":[89],"Russell-Rao":[91],"Forbes":[93],"coefficients,":[94],"shown":[98],"be":[100],"due":[101],"dependence":[104],"molecular":[106,149],"size;":[107],"these":[108,125],"are":[109],"choice":[113],"case":[116],"large":[118],"small":[120,137],"structures,":[121],"respectively.":[122],"Rankings":[123],"combined":[129],"data":[132],"fusion":[133],"scheme":[134],"some":[136],"gains":[138],"performance":[140],"were":[141],"normally":[142],"obtained":[143],"substructural":[146],"fingerprints":[147],"holograms":[150],"combination":[152],"with":[153],"Squared":[155],"Euclidean":[156],"or":[157],"Tanimoto":[158],"coefficients.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2016-06-24T00:00:00"}