{"id":"https://openalex.org/W2004689820","doi":"https://doi.org/10.1021/ci9000508","title":"CAUTION: Popular \u201cBenchmark\u201d Data Sets Do Not Distinguish the Merits of 3D QSAR Methods","display_name":"CAUTION: Popular \u201cBenchmark\u201d Data Sets Do Not Distinguish the Merits of 3D QSAR Methods","publication_year":2009,"publication_date":"2009-05-13","ids":{"openalex":"https://openalex.org/W2004689820","doi":"https://doi.org/10.1021/ci9000508","mag":"2004689820","pmid":"https://pubmed.ncbi.nlm.nih.gov/19438212"},"language":"en","primary_location":{"id":"doi:10.1021/ci9000508","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci9000508","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/A5014628206","display_name":"John I. Manchester","orcid":"https://orcid.org/0000-0001-7183-8802"},"institutions":[{"id":"https://openalex.org/I4210150756","display_name":"AstraZeneca (United States)","ror":"https://ror.org/043cec594","country_code":"US","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210150756"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Manchester","raw_affiliation_strings":["AstraZeneca Pharmaceuticals LLP, 35 Gatehouse Drive, Waltham, Massachusetts 02451"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals LLP, 35 Gatehouse Drive, Waltham, Massachusetts 02451","institution_ids":["https://openalex.org/I4210150756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010796099","display_name":"Ryszard Czermi\u0144ski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150756","display_name":"AstraZeneca (United States)","ror":"https://ror.org/043cec594","country_code":"US","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210150756"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryszard Czermi\u0144ski","raw_affiliation_strings":["AstraZeneca Pharmaceuticals LLP, 35 Gatehouse Drive, Waltham, Massachusetts 02451"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals LLP, 35 Gatehouse Drive, Waltham, Massachusetts 02451","institution_ids":["https://openalex.org/I4210150756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010796099"],"corresponding_institution_ids":["https://openalex.org/I4210150756"],"apc_list":null,"apc_paid":null,"fwci":2.4818,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88346644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"49","issue":"6","first_page":"1449","last_page":"1454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9901999831199646,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9735999703407288,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8806129693984985},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.6265020370483398},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5507968664169312},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5385962128639221},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4900132715702057},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4857061803340912},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.48324427008628845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4592573046684265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44298475980758667},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43734824657440186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41145703196525574},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3710761070251465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3328324258327484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3325512409210205},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.32299917936325073},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.06492525339126587}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8806129693984985},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.6265020370483398},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5507968664169312},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5385962128639221},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4900132715702057},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4857061803340912},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.48324427008628845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4592573046684265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44298475980758667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43734824657440186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41145703196525574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3710761070251465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3328324258327484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3325512409210205},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.32299917936325073},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.06492525339126587},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008968","descriptor_name":"Molecular Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008968","descriptor_name":"Molecular Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008968","descriptor_name":"Molecular Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013256","descriptor_name":"Steroids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci9000508","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci9000508","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:19438212","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19438212","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W417995331","https://openalex.org/W1480376833","https://openalex.org/W1966350242","https://openalex.org/W1983492171","https://openalex.org/W1992787746","https://openalex.org/W1998194343","https://openalex.org/W2011785226","https://openalex.org/W2021352513","https://openalex.org/W2032245355","https://openalex.org/W2033872649","https://openalex.org/W2035833657","https://openalex.org/W2063060349","https://openalex.org/W2064095852","https://openalex.org/W2077562320","https://openalex.org/W2099475054","https://openalex.org/W2104869668","https://openalex.org/W4245355923","https://openalex.org/W4253764495"],"related_works":["https://openalex.org/W1978931025","https://openalex.org/W1518515965","https://openalex.org/W3159291941","https://openalex.org/W2063120953","https://openalex.org/W3149724803","https://openalex.org/W2753230657","https://openalex.org/W2165637039","https://openalex.org/W2026843845","https://openalex.org/W4379468083","https://openalex.org/W2155827364"],"abstract_inverted_index":{"The":[0,38,162],"quality":[1],"of":[2,22,41,46,58,123,154,215,233,244,263],"3D":[3,35,246],"QSAR":[4,36,247],"models":[5,64,75,108,164],"obtained":[6,65],"using":[7,66,111],"extremely":[8],"simple":[9],"descriptors":[10,54,112,140,248],"was":[11,91,133,158],"examined":[12,238],"for":[13,26,33,94,178,183,256],"nine":[14,235],"popular":[15],"data":[16,82,204,226,236],"sets,":[17,83],"including":[18],"the":[19,31,47,56,95,121,152,184,198,222,234,242,261],"well-known":[20],"set":[21],"31":[23],"steroids,":[24,185],"which":[25,69],"20":[27],"years":[28],"has":[29],"been":[30,71],"standard":[32],"benchmarking":[34],"methods.":[37],"atomic":[39,117,144,155,174],"numbers":[40],"atoms":[42],"coinciding":[43],"with":[44,191,197],"vertices":[45,60],"molecular":[48],"alignment":[49],"as":[50,52],"well":[51],"binary":[53],"indicating":[55],"occupancy":[57,96],"those":[59],"were":[61,109,146],"compared":[62],"to":[63,73,220],"SAMFA":[67],"descriptors,":[68,97],"have":[70],"shown":[72],"yield":[74],"statistically":[76],"indistinguishable":[77],"from":[78,113,141],"CoMFA.":[79],"For":[80],"most":[81],"only":[84],"a":[85,105,115,142,171,202,213,225],"minor":[86],"loss":[87,130],"in":[88,120,131,137,149,224],"model":[89],"performance":[90,132],"observed,":[92,134],"even":[93,135],"where":[98],"all":[99,150],"chemical":[100],"information":[101],"is":[102,176,188,212,229],"neglected.":[103],"As":[104],"further":[106,129],"simplification,":[107],"fitted":[110],"just":[114],"few":[116,172,218],"positions":[118,156,175],"occupied":[119],"majority":[122],"active":[124],"or":[125],"inactive":[126],"compounds.":[127],"No":[128],"though":[136],"one":[138],"case":[139],"single":[143],"position":[145],"used,":[147],"and":[148,194,249],"cases":[151],"number":[153],"required":[157],"fewer":[159],"than":[160],"twelve.":[161],"resulting":[163],"suggest":[165],"that":[166,208,231,250],"simply":[167],"filling":[168],"space":[169],"at":[170,189],"key":[173],"responsible":[177],"enhanced":[179],"activity.":[180],"At":[181],"least":[182],"this":[186,209,257],"finding":[187],"odds":[190],"known":[192],"SAR":[193],"binding":[195],"interactions":[196],"relevant":[199],"receptor.":[200],"Using":[201],"simulated":[203,264],"set,":[205],"we":[206],"illustrate":[207],"paradoxical":[210],"outcome":[211],"symptom":[214],"having":[216],"too":[217],"observations":[219],"describe":[221],"response":[223],"set.":[227],"It":[228],"concluded":[230],"none":[232],"sets":[237],"can":[239],"reliably":[240],"distinguish":[241],"merits":[243],"different":[245],"they":[251],"should":[252],"not":[253],"be":[254],"used":[255],"purpose.":[258],"We":[259],"advocate":[260],"use":[262],"data,":[265],"instead.":[266]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}