{"id":"https://openalex.org/W2472085920","doi":"https://doi.org/10.1186/s13321-016-0148-0","title":"Comparing structural fingerprints using a literature-based similarity benchmark","display_name":"Comparing structural fingerprints using a literature-based similarity benchmark","publication_year":2016,"publication_date":"2016-07-05","ids":{"openalex":"https://openalex.org/W2472085920","doi":"https://doi.org/10.1186/s13321-016-0148-0","mag":"2472085920","pmid":"https://pubmed.ncbi.nlm.nih.gov/27382417"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-016-0148-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0148-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0148-0","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/s13321-016-0148-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036721569","display_name":"Noel M. O\u2019Boyle","orcid":"https://orcid.org/0000-0003-4879-2003"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Noel M. O\u2019Boyle","raw_affiliation_strings":["NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064515321","display_name":"Roger A. Sayle","orcid":"https://orcid.org/0000-0003-0188-471X"},"institutions":[{"id":"https://openalex.org/I4210099042","display_name":"Johnson Matthey (United Kingdom)","ror":"https://ror.org/01411sx56","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210099042"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roger A. Sayle","raw_affiliation_strings":["NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY UK","NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY UK","institution_ids":["https://openalex.org/I4210099042"]},{"raw_affiliation_string":"NextMove Software, Innovation Centre, Cambridge Science Park, Milton Road, Cambridge, CB4 0EY, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036721569"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":2390,"currency":"USD","value_usd":2390},"fwci":15.2152,"has_fulltext":true,"cited_by_count":281,"citation_normalized_percentile":{"value":0.99045747,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9865000247955322,"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":0.9865000247955322,"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/T11476","display_name":"Graph theory and applications","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0010000000474974513,"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/cheminformatics","display_name":"Cheminformatics","score":0.9222885966300964},{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.8701515197753906},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6950557231903076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6713502407073975},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6657798886299133},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.610825777053833},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5750791430473328},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.5068147778511047},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5064023733139038},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.47656726837158203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4398152530193329},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.4336823523044586},{"id":"https://openalex.org/keywords/structural-similarity","display_name":"Structural similarity","score":0.42811664938926697},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2948909401893616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2851905822753906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2778826951980591},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.24818867444992065},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.2391166090965271},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.1670321524143219},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09166228771209717}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9222885966300964},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.8701515197753906},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6950557231903076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713502407073975},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6657798886299133},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.610825777053833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5750791430473328},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.5068147778511047},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5064023733139038},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.47656726837158203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4398152530193329},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.4336823523044586},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.42811664938926697},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2948909401893616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2851905822753906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2778826951980591},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.24818867444992065},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.2391166090965271},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.1670321524143219},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09166228771209717},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13321-016-0148-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0148-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0148-0","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:27382417","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27382417","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:4932683","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4932683","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/s13321-016-0148-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0148-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0148-0","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":[{"display_name":"Good health and well-being","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2472085920.pdf","grobid_xml":"https://content.openalex.org/works/W2472085920.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1496416236","https://openalex.org/W1605923270","https://openalex.org/W1964513093","https://openalex.org/W1972816772","https://openalex.org/W1974880836","https://openalex.org/W1975875968","https://openalex.org/W1981802097","https://openalex.org/W1983478747","https://openalex.org/W1988037271","https://openalex.org/W1988909822","https://openalex.org/W1993421185","https://openalex.org/W1995696364","https://openalex.org/W1999049142","https://openalex.org/W2003021806","https://openalex.org/W2005465759","https://openalex.org/W2012852630","https://openalex.org/W2016979469","https://openalex.org/W2017380317","https://openalex.org/W2017547569","https://openalex.org/W2021083597","https://openalex.org/W2021574925","https://openalex.org/W2021748110","https://openalex.org/W2028129896","https://openalex.org/W2038361288","https://openalex.org/W2039609876","https://openalex.org/W2039693046","https://openalex.org/W2042110087","https://openalex.org/W2048277731","https://openalex.org/W2057044370","https://openalex.org/W2059733118","https://openalex.org/W2064440950","https://openalex.org/W2078765032","https://openalex.org/W2083385715","https://openalex.org/W2086729168","https://openalex.org/W2093901601","https://openalex.org/W2095008151","https://openalex.org/W2112912103","https://openalex.org/W2119512897","https://openalex.org/W2121044470","https://openalex.org/W2125792789","https://openalex.org/W2127760066","https://openalex.org/W2130629641","https://openalex.org/W2155159115","https://openalex.org/W2166845081","https://openalex.org/W2173531201","https://openalex.org/W2174991771","https://openalex.org/W2345060776","https://openalex.org/W2411599209","https://openalex.org/W2412446857","https://openalex.org/W2431092165","https://openalex.org/W4240773179","https://openalex.org/W4245602869","https://openalex.org/W6773842061"],"related_works":["https://openalex.org/W2780675302","https://openalex.org/W2802492120","https://openalex.org/W2080207377","https://openalex.org/W2172072929","https://openalex.org/W2472085920","https://openalex.org/W3175241218","https://openalex.org/W3164924191","https://openalex.org/W2007560618","https://openalex.org/W1996053610","https://openalex.org/W3045647619"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,72],"concept":[2],"of":[3,8,33,39,66,74,83,87,118,126,139,200,216,226,234,241,250,281,333,354],"molecular":[4,34],"similarity":[5,35,88,140,191],"is":[6,19,78,299,343,360],"one":[7,82,170,353],"the":[9,15,37,61,67,84,97,102,116,119,130,198,239,248,255,260,265,288,300,310,315,331,334,340,355],"central":[10],"ideas":[11],"in":[12,36,90,101,107,151,163,172],"cheminformatics,":[13],"despite":[14],"fact":[16],"that":[17,79,99,192,330],"it":[18,80],"ill-defined":[20],"and":[21,44,57,229,258,267,284],"rather":[22],"difficult":[23],"to":[24,55,141,196,204,220,238,262,347,365],"assess":[25],"objectively.":[26],"Here":[27],"we":[28,95,121,183,328],"propose":[29],"a":[30,49,76,108,124,142,208,325,367],"practical":[31],"definition":[32,77],"context":[38],"drug":[40,92],"discovery:":[41],"molecules":[42,100,128,135,150],"A":[43],"B":[45],"are":[46,213,286],"similar":[47,114,127,205],"if":[48,339],"medicinal":[50,69,109,131],"chemist":[51],"would":[52],"be":[53,145,194],"likely":[54],"synthesise":[56],"test":[58],"them":[59],"around":[60],"same":[62,68,103],"time":[63],"as":[64,298],"part":[65],"chemistry":[70,110,132],"program.":[71],"attraction":[73],"such":[75],"matches":[81],"key":[85],"uses":[86],"measures":[89],"early-stage":[91],"discovery.":[93],"If":[94],"make":[96],"assumption":[98],"compound":[104],"activity":[105,153,161,179],"table":[106,154],"paper":[111],"were":[112],"considered":[113],"by":[115,147,155,159,296],"authors":[117],"paper,":[120],"can":[122,144,193],"create":[123],"dataset":[125],"from":[129,181,207,264,345,352],"literature.":[133],"Furthermore,":[134],"with":[136,178],"decreasing":[137],"levels":[138],"reference":[143],"found":[146],"either":[148],"ordering":[149],"an":[152,214],"their":[156,227],"activity,":[157],"or":[158,244,322],"considering":[160],"tables":[162],"different":[164,252],"papers":[165],"which":[166],"have":[167,184],"at":[168],"least":[169],"molecule":[171],"common.":[173],"RESULTS:":[174],"Using":[175],"this":[176],"procedure":[177],"data":[180],"ChEMBL,":[182],"created":[185],"two":[186],"benchmark":[187,256,356],"datasets":[188],"for":[189],"structural":[190],"used":[195],"guide":[197],"development":[199],"improved":[201],"measures.":[202],"Compared":[203],"results":[206,261],"virtual":[209,275,326],"screen,":[210,327],"these":[211],"benchmarks":[212],"order":[215],"magnitude":[217],"more":[218],"sensitive":[219],"differences":[221],"between":[222],"fingerprints":[223,253,280,291,336],"both":[224],"because":[225,230],"size":[228],"they":[231],"avoid":[232],"loss":[233],"statistical":[235],"power":[236],"due":[237],"use":[240],"mean":[242],"scores":[243],"ranks.":[245],"We":[246],"measure":[247],"performance":[249,332],"28":[251],"on":[254,362],"sets":[257],"compare":[259],"those":[263],"Riniker":[266],"Landrum":[268],"(J":[269],"Cheminf":[270],"5:26,":[271],"2013.":[272],"doi:10.1186/1758-2946-5-26)":[273],"ligand-based":[274],"screening":[276],"benchmark.":[277],"CONCLUSIONS:":[278],"Extended-connectivity":[279],"diameter":[282],"4":[283],"6":[285],"among":[287],"best":[289],"performing":[290],"when":[292,305],"ranking":[293,306,319],"diverse":[294,320],"structures":[295,321],"similarity,":[297],"topological":[301],"torsion":[302],"fingerprint.":[303],"However,":[304],"very":[307],"close":[308],"analogues,":[309],"atom":[311],"pair":[312],"fingerprint":[313,359],"outperforms":[314],"others":[316],"tested.":[317],"When":[318],"carrying":[323],"out":[324],"find":[329],"ECFP":[335],"significantly":[337],"improves":[338],"bit-vector":[341],"length":[342],"increased":[344],"1024":[346],"16,384.Graphical":[348],"abstractAn":[349],"example":[350],"series":[351,369],"datasets.":[357],"Each":[358],"assessed":[361],"its":[363],"ability":[364],"reproduce":[366],"specific":[368],"order.":[370]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":58},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2016-07-22T00:00:00"}