{"id":"https://openalex.org/W4367320374","doi":"https://doi.org/10.1186/s13321-023-00709-9","title":"Large-scale evaluation of k-fold cross-validation ensembles for uncertainty estimation","display_name":"Large-scale evaluation of k-fold cross-validation ensembles for uncertainty estimation","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367320374","doi":"https://doi.org/10.1186/s13321-023-00709-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/37118768"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00709-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00709-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00709-9","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/s13321-023-00709-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013911493","display_name":"Thomas\u2010Martin Dutschmann","orcid":"https://orcid.org/0000-0001-5880-3517"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thomas-Martin Dutschmann","raw_affiliation_strings":["Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039083147","display_name":"Lennart Kinzel","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lennart Kinzel","raw_affiliation_strings":["Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038269097","display_name":"Antonius ter Laak","orcid":"https://orcid.org/0000-0003-1820-002X"},"institutions":[{"id":"https://openalex.org/I67348948","display_name":"Bayer (Germany)","ror":"https://ror.org/04hmn8g73","country_code":"DE","type":"company","lineage":["https://openalex.org/I67348948"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Antonius ter Laak","raw_affiliation_strings":["Bayer AG, Research & Development, Pharmaceuticals, Muellerstrasse 178, 13353, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Bayer AG, Research & Development, Pharmaceuticals, Muellerstrasse 178, 13353, Berlin, Germany","institution_ids":["https://openalex.org/I67348948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027269400","display_name":"Knut Baumann","orcid":"https://orcid.org/0000-0001-9459-0045"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Knut Baumann","raw_affiliation_strings":["Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany. k.baumann@tu-braunschweig.de","Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany. k.baumann@tu-braunschweig.de","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, Beethovenstrasse 55, 38106, Brunswick, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013911493"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1704,"currency":"EUR","value_usd":1837},"fwci":12.2594,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.99004282,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"49","last_page":"49"},"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":0.991599977016449,"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":0.972000002861023,"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/estimator","display_name":"Estimator","score":0.7453591227531433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859683394432068},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5918782949447632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5699132084846497},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5193568468093872},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.49024659395217896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.489213228225708},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4747267961502075},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.4666564166545868},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46411898732185364},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.43154582381248474},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42737990617752075},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3083096146583557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19646072387695312}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7453591227531433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859683394432068},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5918782949447632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5699132084846497},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5193568468093872},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.49024659395217896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.489213228225708},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4747267961502075},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.4666564166545868},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46411898732185364},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.43154582381248474},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42737990617752075},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3083096146583557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19646072387695312},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-023-00709-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00709-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00709-9","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:37118768","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37118768","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:10142532","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10142532","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10142532/pdf/13321_2023_Article_709.pdf","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"},{"id":"pmh:oai:doaj.org/article:d214619339c64924bb226ee92fa0faac","is_oa":true,"landing_page_url":"https://doaj.org/article/d214619339c64924bb226ee92fa0faac","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 15, Iss 1, Pp 1-16 (2023)","raw_type":"article"},{"id":"pmh:oai:https://leopard.tu-braunschweig.de/:dbbs_mods_00073366","is_oa":true,"landing_page_url":"https://leopard.tu-braunschweig.de/receive/dbbs_mods_00073366","pdf_url":null,"source":{"id":"https://openalex.org/S4306402617","display_name":"Digitale Bibliothek Braunschweig (Verbundzentrale G\u00f6ttingen (VZG))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"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":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00709-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00709-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00709-9","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":[{"id":"https://openalex.org/F4320322958","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367320374.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1534477342","https://openalex.org/W1570912112","https://openalex.org/W1994946414","https://openalex.org/W2006203663","https://openalex.org/W2008505552","https://openalex.org/W2039609876","https://openalex.org/W2044834685","https://openalex.org/W2057327562","https://openalex.org/W2063731290","https://openalex.org/W2074681440","https://openalex.org/W2076498053","https://openalex.org/W2111959010","https://openalex.org/W2127019019","https://openalex.org/W2200017991","https://openalex.org/W2278332638","https://openalex.org/W2295598076","https://openalex.org/W2473238561","https://openalex.org/W2529996553","https://openalex.org/W2731161895","https://openalex.org/W2761058956","https://openalex.org/W2790808809","https://openalex.org/W2802404464","https://openalex.org/W2897131212","https://openalex.org/W2900090807","https://openalex.org/W2901476322","https://openalex.org/W2911789160","https://openalex.org/W2911964244","https://openalex.org/W2937307539","https://openalex.org/W2938282337","https://openalex.org/W2966357564","https://openalex.org/W2971442502","https://openalex.org/W2992525328","https://openalex.org/W3014339631","https://openalex.org/W3014596384","https://openalex.org/W3044724994","https://openalex.org/W3082081167","https://openalex.org/W3098269892","https://openalex.org/W3098708496","https://openalex.org/W3098762731","https://openalex.org/W3102100346","https://openalex.org/W3107587236","https://openalex.org/W3134774296","https://openalex.org/W3164731060","https://openalex.org/W3185456481","https://openalex.org/W3199470976","https://openalex.org/W3209430615","https://openalex.org/W3215550924","https://openalex.org/W3216626280","https://openalex.org/W4205941116","https://openalex.org/W4211165734","https://openalex.org/W4239510810","https://openalex.org/W4280545185","https://openalex.org/W4367320374","https://openalex.org/W6910929151"],"related_works":["https://openalex.org/W2794896638","https://openalex.org/W1807784185","https://openalex.org/W4390905871","https://openalex.org/W3202800081","https://openalex.org/W1909207154","https://openalex.org/W3124390867","https://openalex.org/W3101614107","https://openalex.org/W3204228978","https://openalex.org/W1514365828","https://openalex.org/W4390971112"],"abstract_inverted_index":{"It":[0],"is":[1,13,147,239],"insightful":[2],"to":[3,18,104,113,119,127,140,149,181,190],"report":[4],"an":[5,51],"estimator":[6,203],"that":[7],"describes":[8],"how":[9],"certain":[10],"a":[11,15,28,40,43,160],"model":[12],"in":[14,154],"prediction,":[16],"additionally":[17],"the":[19,31,61,64,69,83,93,102,106,141,144,155,193,199,224,244],"prediction":[20],"alone.":[21],"For":[22,184],"regression":[23,109],"tasks,":[24],"most":[25],"approaches":[26],"implement":[27],"variation":[29],"of":[30,39,45,95,108,157,171,209,229,240],"ensemble":[32,145,186],"method,":[33],"apart":[34],"from":[35,90,178],"few":[36],"exceptions.":[37],"Instead":[38],"single":[41],"estimator,":[42],"group":[44],"estimators":[46],"yields":[47],"several":[48],"predictions":[49],"for":[50,66,168,206,221,243],"input.":[52],"The":[53],"uncertainty":[54,107,202,237],"can":[55,116],"then":[56],"be":[57,117],"quantified":[58],"by":[59,68,86],"measuring":[60],"disagreement":[62],"between":[63],"predictions,":[65],"example":[67],"standard":[70],"deviation.":[71],"In":[72,159],"theory,":[73],"ensembles":[74,115,165],"should":[75],"not":[76],"only":[77],"provide":[78],"uncertainties,":[79],"they":[80,98,124],"also":[81],"boost":[82],"predictive":[84,194,234],"performance":[85,195,235],"reducing":[87],"errors":[88],"arising":[89],"variance.":[91],"Despite":[92],"development":[94],"novel":[96],"methods,":[97],"are":[99,125,166,204],"still":[100],"considered":[101],"\"golden-standard\"":[103],"quantify":[105],"models.":[110],"Subsampling-based":[111],"methods":[112],"obtain":[114],"applied":[118],"all":[120,151,207],"models,":[121],"regardless":[122],"whether":[123,143,233],"related":[126],"deep":[128],"learning":[129],"or":[130,236],"traditional":[131],"machine":[132],"learning.":[133],"However,":[134],"little":[135],"attention":[136],"has":[137],"been":[138],"given":[139],"question":[142],"method":[146],"applicable":[148],"virtually":[150],"scenarios":[152],"occurring":[153],"field":[156],"cheminformatics.":[158],"widespread":[161],"and":[162,174,213,226],"diversified":[163],"attempt,":[164],"evaluated":[167],"32":[169],"datasets":[170],"different":[172],"sizes":[173,187],"modeling":[175,211],"difficulty,":[176],"ranging":[177],"physicochemical":[179],"properties":[180],"biological":[182],"activities.":[183],"increasing":[185],"with":[188],"up":[189],"200":[191],"members,":[192],"as":[196,198,201],"well":[197],"applicability":[200],"shown":[205],"combinations":[208],"five":[210],"techniques":[212],"four":[214],"molecular":[215],"featurizations.":[216],"Useful":[217],"recommendations":[218],"were":[219],"derived":[220],"practitioners":[222],"regarding":[223],"success":[225],"minimum":[227],"size":[228],"ensembles,":[230],"depending":[231],"on":[232],"quantification":[238],"more":[241],"importance":[242],"task":[245],"at":[246],"hand.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}