{"id":"https://openalex.org/W2918239264","doi":"https://doi.org/10.1021/acs.jcim.8b00712","title":"In Need of Bias Control: Evaluating Chemical Data for Machine Learning in Structure-Based Virtual Screening","display_name":"In Need of Bias Control: Evaluating Chemical Data for Machine Learning in Structure-Based Virtual Screening","publication_year":2019,"publication_date":"2019-03-05","ids":{"openalex":"https://openalex.org/W2918239264","doi":"https://doi.org/10.1021/acs.jcim.8b00712","mag":"2918239264","pmid":"https://pubmed.ncbi.nlm.nih.gov/30835112"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00712","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00712","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/A5055412887","display_name":"Jochen Sieg","orcid":"https://orcid.org/0000-0001-5343-7255"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jochen Sieg","raw_affiliation_strings":["Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5343-7255","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048360660","display_name":"Florian Flachsenberg","orcid":"https://orcid.org/0000-0001-7051-8719"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Flachsenberg","raw_affiliation_strings":["Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7051-8719","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083205378","display_name":"Matthias Rarey","orcid":"https://orcid.org/0000-0002-9553-6531"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Rarey","raw_affiliation_strings":["Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9553-6531","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, ZBH - Center for Bioinformatics, Research Group for Computational Molecular Design, Bundesstra\u00dfe 43, 20146 Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083205378"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":36.7816,"has_fulltext":false,"cited_by_count":329,"citation_normalized_percentile":{"value":0.99881517,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"59","issue":"3","first_page":"947","last_page":"961"},"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":0.9998000264167786,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9830999970436096,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8725696802139282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742348313331604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6519802808761597},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6047955751419067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5936775803565979},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5654969811439514},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5345840454101562},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49918508529663086},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.46693745255470276},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.431761771440506},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40325725078582764}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8725696802139282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742348313331604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6519802808761597},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6047955751419067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936775803565979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5654969811439514},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5345840454101562},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49918508529663086},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.46693745255470276},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.431761771440506},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40325725078582764},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"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":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.8b00712","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00712","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:30835112","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30835112","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":54,"referenced_works":["https://openalex.org/W1964513093","https://openalex.org/W1966950894","https://openalex.org/W1968319881","https://openalex.org/W1984480244","https://openalex.org/W1988195734","https://openalex.org/W1988744515","https://openalex.org/W1998791246","https://openalex.org/W2004386051","https://openalex.org/W2017132056","https://openalex.org/W2017254234","https://openalex.org/W2034553680","https://openalex.org/W2040496005","https://openalex.org/W2040990879","https://openalex.org/W2045873232","https://openalex.org/W2058820833","https://openalex.org/W2058835307","https://openalex.org/W2060531713","https://openalex.org/W2073021822","https://openalex.org/W2076779488","https://openalex.org/W2079331631","https://openalex.org/W2088388996","https://openalex.org/W2093814531","https://openalex.org/W2096541451","https://openalex.org/W2101234009","https://openalex.org/W2114704115","https://openalex.org/W2119512897","https://openalex.org/W2127760066","https://openalex.org/W2145722722","https://openalex.org/W2148512505","https://openalex.org/W2158698691","https://openalex.org/W2176516200","https://openalex.org/W2208175234","https://openalex.org/W2271840356","https://openalex.org/W2294213638","https://openalex.org/W2346710580","https://openalex.org/W2526925775","https://openalex.org/W2583907533","https://openalex.org/W2587598315","https://openalex.org/W2594183968","https://openalex.org/W2608559058","https://openalex.org/W2760085125","https://openalex.org/W2774738748","https://openalex.org/W2784213390","https://openalex.org/W2793989982","https://openalex.org/W2800448650","https://openalex.org/W2803094965","https://openalex.org/W2900743800","https://openalex.org/W2911964244","https://openalex.org/W3100704554","https://openalex.org/W3104508774","https://openalex.org/W3104705366","https://openalex.org/W4239678514","https://openalex.org/W4241587358","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3114272811","https://openalex.org/W3185156046","https://openalex.org/W2922305141","https://openalex.org/W2786391746","https://openalex.org/W3132346564","https://openalex.org/W2991483587","https://openalex.org/W2914559142","https://openalex.org/W4226059458","https://openalex.org/W4381430104","https://openalex.org/W2995102745"],"abstract_inverted_index":{"Reports":[0],"of":[1,4,90,128],"successful":[2],"applications":[3],"machine":[5],"learning":[6],"(ML)":[7],"methods":[8,17,30,92],"in":[9,36,62,87,153],"structure-based":[10],"virtual":[11],"screening":[12],"(SBVS)":[13],"are":[14,43,50,65,72],"increasing.":[15],"ML":[16,41,91,148],"such":[18,31],"as":[19,32,46],"convolutional":[20],"neural":[21],"networks":[22],"show":[23],"promising":[24],"results":[25],"and":[26,49,67,93,120,142,165],"often":[27,44],"outperform":[28],"traditional":[29],"empirical":[33],"scoring":[34],"functions":[35],"retrospective":[37],"validation.":[38],"However,":[39],"trained":[40],"models":[42],"treated":[45],"black":[47],"boxes":[48],"not":[51,99],"straightforwardly":[52],"interpretable.":[53],"In":[54],"most":[55],"cases,":[56],"it":[57],"is":[58,104,117,135],"unknown":[59],"which":[60],"features":[61],"the":[63,75,88,96,126],"data":[64,85,102,144,172],"decisive":[66],"whether":[68],"a":[69,136,167],"model's":[70],"predictions":[71],"right":[73,76],"for":[74,138,149,160],"reason.":[77],"Hence,":[78],"we":[79,107,131,157],"re-evaluated":[80],"three":[81],"widely":[82],"used":[83],"benchmark":[84,101,143],"sets":[86,145,173],"context":[89],"came":[94],"to":[95,147],"conclusion":[97],"that":[98,115,133],"every":[100],"set":[103],"suitable.":[105],"Moreover,":[106],"demonstrate":[108],"on":[109,169],"two":[110],"examples":[111],"from":[112,122],"current":[113],"literature":[114],"bias":[116],"learned":[118],"implicitly":[119],"unnoticed":[121],"standard":[123],"benchmarks.":[124],"On":[125],"basis":[127],"these":[129],"results,":[130],"conclude":[132],"there":[134],"need":[137],"eligible":[139],"validation":[140,152,163],"experiments":[141,164],"suited":[146],"more":[150],"bias-controlled":[151],"ML-based":[154],"SBVS.":[155],"Therefore,":[156],"provide":[158],"guidelines":[159],"setting":[161],"up":[162],"give":[166],"perspective":[168],"how":[170],"new":[171],"could":[174],"be":[175],"generated.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":46},{"year":2021,"cited_by_count":69},{"year":2020,"cited_by_count":50},{"year":2019,"cited_by_count":17}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}