{"id":"https://openalex.org/W2151697120","doi":"https://doi.org/10.1186/s13321-015-0069-3","title":"Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?","display_name":"Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?","publication_year":2015,"publication_date":"2015-05-19","ids":{"openalex":"https://openalex.org/W2151697120","doi":"https://doi.org/10.1186/s13321-015-0069-3","mag":"2151697120","pmid":"https://pubmed.ncbi.nlm.nih.gov/26052348"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-015-0069-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0069-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0069-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0069-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026174702","display_name":"D\u00e1vid Bajusz","orcid":"https://orcid.org/0000-0003-4277-9481"},"institutions":[{"id":"https://openalex.org/I80251312","display_name":"HUN-REN Research Centre for Natural Sciences","ror":"https://ror.org/03zwxja46","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4387152226","https://openalex.org/I80251312"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"D\u00e1vid Bajusz","raw_affiliation_strings":["Medicinal Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary","Medicinal Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medicinal Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary","institution_ids":[]},{"raw_affiliation_string":"Medicinal Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary","institution_ids":["https://openalex.org/I80251312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036366502","display_name":"Anita R\u00e1cz","orcid":"https://orcid.org/0000-0001-8271-9841"},"institutions":[{"id":"https://openalex.org/I80251312","display_name":"HUN-REN Research Centre for Natural Sciences","ror":"https://ror.org/03zwxja46","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4387152226","https://openalex.org/I80251312"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Anita R\u00e1cz","raw_affiliation_strings":["Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary ; Department of Applied Chemistry, Faculty of Food Science, Corvinus University of Budapest, Vill\u00e1nyi \u00fat 29-43, H-1118 Budapest XI, Hungary","Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary ; Department of Applied Chemistry, Faculty of Food Science, Corvinus University of Budapest, Vill\u00e1nyi \u00fat 29-43, H-1118 Budapest XI, Hungary","institution_ids":[]},{"raw_affiliation_string":"Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary","institution_ids":["https://openalex.org/I80251312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043829139","display_name":"K\u00e1roly H\u00e9berger","orcid":"https://orcid.org/0000-0003-0965-939X"},"institutions":[{"id":"https://openalex.org/I80251312","display_name":"HUN-REN Research Centre for Natural Sciences","ror":"https://ror.org/03zwxja46","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4387152226","https://openalex.org/I80251312"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"K\u00e1roly H\u00e9berger","raw_affiliation_strings":["Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary","Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117 Budapest XI, Hungary","institution_ids":[]},{"raw_affiliation_string":"Plasma Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tud\u00f3sok k\u00f6r\u00fatja 2, H-1117, Budapest XI, Hungary","institution_ids":["https://openalex.org/I80251312"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026174702"],"corresponding_institution_ids":["https://openalex.org/I80251312"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":56.3294,"has_fulltext":true,"cited_by_count":1612,"citation_normalized_percentile":{"value":0.99915201,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9847000241279602,"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":0.9847000241279602,"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/T12748","display_name":"Molecular spectroscopy and chirality","score":0.006099999882280827,"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":0.0013000000035390258,"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":0.7990023493766785},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6656631827354431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6384098529815674},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5693067312240601},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5612852573394775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5354782342910767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5203670859336853},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4919733703136444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4341386556625366},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.43296295404434204}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7990023493766785},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6656631827354431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384098529815674},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5693067312240601},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5612852573394775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5354782342910767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5203670859336853},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4919733703136444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341386556625366},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.43296295404434204},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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":3,"locations":[{"id":"doi:10.1186/s13321-015-0069-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0069-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0069-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:26052348","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26052348","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4456712","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4456712","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-015-0069-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-015-0069-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-015-0069-3","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2151697120.pdf","grobid_xml":"https://content.openalex.org/works/W2151697120.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W195064984","https://openalex.org/W1480376833","https://openalex.org/W1522930108","https://openalex.org/W1554944419","https://openalex.org/W1571527653","https://openalex.org/W1576360991","https://openalex.org/W1963917497","https://openalex.org/W1965528589","https://openalex.org/W1968816006","https://openalex.org/W1973897992","https://openalex.org/W1983478747","https://openalex.org/W1988037271","https://openalex.org/W1988909822","https://openalex.org/W1990451437","https://openalex.org/W2006575776","https://openalex.org/W2017784810","https://openalex.org/W2019538911","https://openalex.org/W2026143249","https://openalex.org/W2028046413","https://openalex.org/W2042007894","https://openalex.org/W2042338355","https://openalex.org/W2059856562","https://openalex.org/W2060097376","https://openalex.org/W2062556965","https://openalex.org/W2064576005","https://openalex.org/W2069506489","https://openalex.org/W2089656772","https://openalex.org/W2091515885","https://openalex.org/W2093737637","https://openalex.org/W2094493457","https://openalex.org/W2096729078","https://openalex.org/W2102913801","https://openalex.org/W2106198479","https://openalex.org/W2114116884","https://openalex.org/W2160114756","https://openalex.org/W2320034101","https://openalex.org/W2412446857","https://openalex.org/W2522646202","https://openalex.org/W4239346200"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W2171353393","https://openalex.org/W2280638972","https://openalex.org/W3145898297"],"abstract_inverted_index":{"BACKGROUND:":[0],"Cheminformaticians":[1],"are":[2,24,45,80,293,319],"equipped":[3],"with":[4,54,188,351],"a":[5,48,123,220,238],"very":[6],"rich":[7],"toolbox":[8],"when":[9],"carrying":[10],"out":[11],"molecular":[12,19,36,52,66,115,206],"similarity":[13,34,97,120,207,265,285,306,349],"calculations.":[14,208],"A":[15,84,102],"large":[16,49,103],"number":[17,104],"of":[18,35,51,56,65,77,93,105,109,144,154,161,165,177,190,280,325,337,345,348,353],"representations":[20],"exist,":[21],"and":[22,28,60,70,119,128,171,201,249,290,302,330],"there":[23],"several":[25],"methods":[26,69,73],"(similarity":[27],"distance":[29,251],"metrics)":[30],"to":[31,199,217,254,275],"quantify":[32],"the":[33,75,78,91,96,129,145,159,162,175,224,256,272,276,281,323,334,338,346],"representations.":[37],"In":[38],"this":[39,100],"work,":[40],"eight":[41,282],"well-known":[42],"similarity/distance":[43],"metrics":[44,137,204,263,269,286,307,350],"compared":[46,139],"on":[47,74,141,169,223,296,333],"dataset":[50],"fingerprints":[53,116],"sum":[55,153,352],"ranking":[57,143,155,279,335,354],"differences":[58,156,355],"(SRD)":[59],"ANOVA":[61],"analysis.":[62],"The":[63,242,284],"effects":[64,176,324],"size,":[67,183,327],"selection":[68,184,328],"data":[71,316,331],"pretreatment":[72,332],"outcome":[76],"comparison":[79,347],"also":[81,320],"assessed.":[82],"RESULTS:":[83],"supplier":[85],"database":[86],"(https://mcule.com/)":[87],"was":[88,215],"used":[89],"as":[90,227,229],"source":[92],"compounds":[94,146,225],"for":[95,133,205,264,315],"calculations":[98],"in":[99,259,311],"study.":[101],"datasets,":[106],"each":[107,134],"consisting":[108],"one":[110,148,236],"hundred":[111],"compounds,":[112],"were":[113,117,131,138,167,186,252],"compiled,":[114],"generated":[118],"values":[121],"between":[122],"randomly":[124],"chosen":[125],"reference":[126],"compound":[127],"rest":[130],"calculated":[132],"dataset.":[135],"Similarity":[136],"based":[140],"their":[142,297,300],"within":[147],"experiment":[149],"(one":[150],"dataset)":[151],"using":[152],"(SRD),":[157],"while":[158],"results":[160],"entire":[163],"set":[164],"experiments":[166],"summarized":[168],"box":[170],"whisker":[172],"plots.":[173],"Finally,":[174],"various":[178,203],"factors":[179],"(data":[180],"pretreatment,":[181],"molecule":[182,326],"method)":[185],"evaluated":[187],"analysis":[189],"variance":[191],"(ANOVA).":[192],"CONCLUSIONS:":[193],"This":[194],"study":[195],"complements":[196],"previous":[197],"efforts":[198],"examine":[200],"rank":[202],"Here,":[209],"however,":[210],"an":[211],"entirely":[212],"general":[213],"approach":[214],"taken":[216],"neglect":[218],"any":[219,230],"priori":[221],"knowledge":[222],"involved,":[226],"well":[228],"bias":[231],"introduced":[232],"by":[233],"examining":[234],"only":[235],"or":[237],"few":[239],"specific":[240],"scenarios.":[241],"Tanimoto":[243],"index,":[244,246],"Dice":[245],"Cosine":[247],"coefficient":[248],"Soergel":[250],"identified":[253],"be":[255,309],"best":[257],"(and":[258],"some":[260],"sense":[261],"equivalent)":[262],"calculations,":[266],"i.e.":[267],"these":[268],"could":[270],"produce":[271],"rankings":[273],"closest":[274],"composite":[277],"(average)":[278],"metrics.":[283,340],"derived":[287],"from":[288,304],"Euclidean":[289],"Manhattan":[291],"distances":[292],"not":[294],"recommended":[295],"own,":[298],"although":[299],"variability":[301],"diversity":[303],"other":[305],"might":[308],"advantageous":[310],"certain":[312],"cases":[313],"(e.g.":[314],"fusion).":[317],"Conclusions":[318],"drawn":[321],"regarding":[322],"method":[329],"behavior":[336],"studied":[339],"Graphical":[341],"AbstractA":[342],"visual":[343],"summary":[344],"(SRD).":[356]},"counts_by_year":[{"year":2026,"cited_by_count":103},{"year":2025,"cited_by_count":298},{"year":2024,"cited_by_count":271},{"year":2023,"cited_by_count":208},{"year":2022,"cited_by_count":190},{"year":2021,"cited_by_count":184},{"year":2020,"cited_by_count":123},{"year":2019,"cited_by_count":80},{"year":2018,"cited_by_count":59},{"year":2017,"cited_by_count":57},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":5}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}