{"id":"https://openalex.org/W1972650279","doi":"https://doi.org/10.1021/ci400099q","title":"Estimating Error Rates in Bioactivity Databases","display_name":"Estimating Error Rates in Bioactivity Databases","publication_year":2013,"publication_date":"2013-10-02","ids":{"openalex":"https://openalex.org/W1972650279","doi":"https://doi.org/10.1021/ci400099q","mag":"1972650279","pmid":"https://pubmed.ncbi.nlm.nih.gov/24160896"},"language":"en","primary_location":{"id":"doi:10.1021/ci400099q","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci400099q","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","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/A5059691139","display_name":"Pekka Tiikkainen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145033","display_name":"MerLion Pharma (Germany)","ror":"https://ror.org/04kark913","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145033"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Pekka Tiikkainen","raw_affiliation_strings":["Merz Pharmaceuticals GmbH, Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","Merz Pharmaceuticals GmbH , Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany"],"affiliations":[{"raw_affiliation_string":"Merz Pharmaceuticals GmbH, Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I4210145033"]},{"raw_affiliation_string":"Merz Pharmaceuticals GmbH , Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021944314","display_name":"Louisa J. Bellis","orcid":"https://orcid.org/0000-0001-9581-870X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louisa Bellis","raw_affiliation_strings":["EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, U.K"],"affiliations":[{"raw_affiliation_string":"EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075076722","display_name":"Yvonne Light","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yvonne Light","raw_affiliation_strings":["EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, U.K"],"affiliations":[{"raw_affiliation_string":"EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5118583932","display_name":"Lutz Franke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145033","display_name":"MerLion Pharma (Germany)","ror":"https://ror.org/04kark913","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145033"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lutz Franke","raw_affiliation_strings":["Merz Pharmaceuticals GmbH, Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","Merz Pharmaceuticals GmbH , Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany"],"affiliations":[{"raw_affiliation_string":"Merz Pharmaceuticals GmbH, Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I4210145033"]},{"raw_affiliation_string":"Merz Pharmaceuticals GmbH , Eckenheimer Landstrasse 100, 60318 Frankfurt am Main, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059691139"],"corresponding_institution_ids":["https://openalex.org/I4210145033"],"apc_list":null,"apc_paid":null,"fwci":7.8268,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.97708533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"53","issue":"10","first_page":"2499","last_page":"2505"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9388999938964844,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.9637641906738281},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6740100383758545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6454051733016968},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.630677342414856},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.566606879234314},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5130685567855835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5078368782997131},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.4106298089027405},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.22980165481567383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1529882848262787},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13511425256729126}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.9637641906738281},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6740100383758545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6454051733016968},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.630677342414856},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.566606879234314},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5130685567855835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5078368782997131},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.4106298089027405},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.22980165481567383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1529882848262787},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13511425256729126},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D015706","descriptor_name":"Bibliometrics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015706","descriptor_name":"Bibliometrics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015706","descriptor_name":"Bibliometrics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017594","descriptor_name":"Publication Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017594","descriptor_name":"Publication Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017594","descriptor_name":"Publication Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci400099q","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci400099q","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","raw_type":"journal-article"},{"id":"pmid:24160896","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24160896","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 modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1984678368","https://openalex.org/W2021235830","https://openalex.org/W2041610798","https://openalex.org/W2045717408","https://openalex.org/W2057069496","https://openalex.org/W2057260453","https://openalex.org/W2057409466","https://openalex.org/W2079223054","https://openalex.org/W2081802492","https://openalex.org/W2096541451","https://openalex.org/W2108238592","https://openalex.org/W2123179625","https://openalex.org/W2317066137","https://openalex.org/W2329862012","https://openalex.org/W2497748342"],"related_works":["https://openalex.org/W2800402488","https://openalex.org/W2155478691","https://openalex.org/W3005441379","https://openalex.org/W1552948952","https://openalex.org/W4310672789","https://openalex.org/W2096541451","https://openalex.org/W2745013929","https://openalex.org/W4362507535","https://openalex.org/W4321254242","https://openalex.org/W4385760073"],"abstract_inverted_index":{"Bioactivity":[0],"databases":[1,22,74],"are":[2,23,92,136],"routinely":[3],"used":[4],"in":[5,35,56,129,139,165],"drug":[6,59],"discovery":[7,60],"to":[8,14,53,94,151],"look-up":[9],"and,":[10],"using":[11],"prediction":[12],"tools,":[13],"predict":[15],"potential":[16],"targets":[17],"for":[18,99,143],"small":[19],"molecules.":[20],"These":[21,49],"typically":[24],"manually":[25],"curated":[26,81],"from":[27,33,71,83],"patents":[28],"and":[29,77,103,121,161],"scientific":[30],"articles.":[31],"Apart":[32],"errors":[34,44,50,164],"the":[36,39,46,57,63,84,111,147,159],"source":[37,86],"document,":[38],"human":[40],"factor":[41],"can":[42,51],"cause":[43],"during":[45],"extraction":[47],"process.":[48,61],"lead":[52,150],"wrong":[54],"decisions":[55],"early":[58],"In":[62],"current":[64],"work,":[65],"we":[66,91],"have":[67,80,110],"compared":[68],"bioactivity":[69,105,166],"data":[70,82,141],"three":[72],"large":[73],"(ChEMBL,":[75],"Liceptor,":[76],"WOMBAT)":[78],"who":[79],"same":[85],"documents.":[87],"As":[88],"a":[89,152],"result,":[90],"able":[93],"report":[95],"error":[96,114,131],"rate":[97,115,132],"estimates":[98],"individual":[100,104],"activity":[101,119,122],"parameters":[102],"databases.":[106],"Small":[107],"molecule":[108],"structures":[109],"greatest":[112],"estimated":[113],"followed":[116],"by":[117],"target,":[118],"value,":[120],"type.":[123],"This":[124],"order":[125],"is":[126],"also":[127,137],"reflected":[128],"supplier-specific":[130],"estimates.":[133],"The":[134],"results":[135,148],"useful":[138],"identifying":[140],"points":[142],"recuration.":[144],"We":[145],"hope":[146],"will":[149],"more":[153],"widespread":[154],"awareness":[155],"among":[156],"scientists":[157],"on":[158],"frequencies":[160],"types":[162],"of":[163],"data.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}