{"id":"https://openalex.org/W2094493457","doi":"https://doi.org/10.1021/ci034001x","title":"Analysis and Display of the Size Dependence of Chemical Similarity Coefficients","display_name":"Analysis and Display of the Size Dependence of Chemical Similarity Coefficients","publication_year":2003,"publication_date":"2003-04-09","ids":{"openalex":"https://openalex.org/W2094493457","doi":"https://doi.org/10.1021/ci034001x","mag":"2094493457","pmid":"https://pubmed.ncbi.nlm.nih.gov/12767139"},"language":"en","primary_location":{"id":"doi:10.1021/ci034001x","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034001x","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/A5034861147","display_name":"John D. Holliday","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":false,"raw_author_name":"John D. Holliday","raw_affiliation_strings":["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","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012641332","display_name":"Naomie Salim","orcid":"https://orcid.org/0000-0001-8509-3055"},"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":false,"raw_author_name":"Naomie Salim","raw_affiliation_strings":["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","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","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":false,"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"],"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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102885255","display_name":"Peter Willett","orcid":"https://orcid.org/0000-0003-4591-7173"},"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":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"],"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6441,"has_fulltext":false,"cited_by_count":140,"citation_normalized_percentile":{"value":0.97742194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"43","issue":"3","first_page":"819","last_page":"828"},"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":0.9919000267982483,"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":0.9908000230789185,"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":0.8659045696258545},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5311281681060791},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.52791428565979},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5047637224197388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45942074060440063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38048243522644043},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3628953695297241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2024592161178589},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09256544709205627}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8659045696258545},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5311281681060791},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.52791428565979},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5047637224197388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45942074060440063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38048243522644043},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3628953695297241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2024592161178589},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09256544709205627},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1021/ci034001x","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034001x","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:12767139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12767139","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},{"id":"pmh:oai:eprints.whiterose.ac.uk:9229","is_oa":false,"landing_page_url":"http://eprints.whiterose.ac.uk/9229/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320320670","display_name":"Wolfson Foundation","ror":"https://ror.org/0333xzh65"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W82186612","https://openalex.org/W1969462276","https://openalex.org/W1990696547","https://openalex.org/W2062556965","https://openalex.org/W2096729078"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2544423928","https://openalex.org/W2052122378","https://openalex.org/W2012531322","https://openalex.org/W2053286651","https://openalex.org/W2181743346","https://openalex.org/W2187401768","https://openalex.org/W2181413294","https://openalex.org/W2785900585"],"abstract_inverted_index":{"We":[0],"discuss":[1],"the":[2,13,24,35,48,55,60,78,83,99,108,119],"size-bias":[3],"inherent":[4,85],"in":[5,59,86,94],"several":[6],"chemical":[7],"similarity":[8,14,30,88],"coefficients":[9,31,89],"when":[10,105],"used":[11,38],"for":[12,118],"searching":[15],"or":[16],"diversity":[17],"selection":[18],"of":[19,27,44,47],"compound":[20],"collections.":[21],"Limits":[22],"to":[23,39,54,69,75,92,107,151],"upper":[25],"bounds":[26],"14":[28],"standard":[29],"are":[32,37,73],"investigated,":[33],"and":[34,101],"results":[36],"identify":[40],"some":[41],"exceptional":[42],"characteristics":[43],"a":[45],"few":[46],"coefficients.":[49,79,103],"An":[50],"additional":[51],"numerical":[52],"contribution":[53],"known":[56],"size":[57,128],"bias":[58,93],"Tanimoto":[61,112],"coefficient":[62,113],"is":[63,123],"identified.":[64],"Graphical":[65],"plots":[66],"with":[67,98],"respect":[68],"relative":[70],"bit":[71,140],"density":[72],"introduced":[74,110],"further":[76],"assess":[77],"Our":[80],"methods":[81,115],"reveal":[82],"asymmetries":[84],"most":[87,96],"that":[90,121],"lead":[91],"selection,":[95],"notably":[97],"Forbes":[100],"Russell-Rao":[102],"Conversely,":[104],"applied":[106],"recently":[109],"Modified":[111],"our":[114,136,146],"provide":[116],"support":[117],"view":[120],"it":[122],"less":[124],"biased":[125],"toward":[126],"molecular":[127],"than":[129],"most.":[130],"In":[131],"this":[132],"work":[133],"we":[134,143],"focus":[135],"discussion":[137],"on":[138],"fragment-based":[139],"strings,":[141],"but":[142],"demonstrate":[144],"how":[145],"approach":[147],"can":[148],"be":[149],"generalized":[150],"continuous":[152],"representations.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
