{"id":"https://openalex.org/W1992441011","doi":"https://doi.org/10.1021/ci100264e","title":"Leave-Cluster-Out Cross-Validation Is Appropriate for Scoring Functions Derived from Diverse Protein Data Sets","display_name":"Leave-Cluster-Out Cross-Validation Is Appropriate for Scoring Functions Derived from Diverse Protein Data Sets","publication_year":2010,"publication_date":"2010-10-12","ids":{"openalex":"https://openalex.org/W1992441011","doi":"https://doi.org/10.1021/ci100264e","mag":"1992441011","pmid":"https://pubmed.ncbi.nlm.nih.gov/20936880"},"language":"en","primary_location":{"id":"doi:10.1021/ci100264e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci100264e","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/A5078834012","display_name":"Christian Kr\u00e4mer","orcid":"https://orcid.org/0000-0001-8663-5266"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Christian Kramer","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","Novartis Institutes for BioMedical Research, Novartis Pharma AG , Forum 1, Novartis Campus, CH-4056 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG , Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033071006","display_name":"Peter Gedeck","orcid":"https://orcid.org/0000-0002-4111-3162"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter Gedeck","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","Novartis Institutes for BioMedical Research, Novartis Pharma AG , Forum 1, Novartis Campus, CH-4056 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG , Forum 1, Novartis Campus, CH-4056 Basel, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078834012"],"corresponding_institution_ids":["https://openalex.org/I1283582996"],"apc_list":null,"apc_paid":null,"fwci":5.0179,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.95331733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"50","issue":"11","first_page":"1961","last_page":"1969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9934999942779541,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.6529653072357178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.600337564945221},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5946969985961914},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5024855136871338},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4892115592956543},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4686291515827179},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.438726007938385},{"id":"https://openalex.org/keywords/protein-ligand","display_name":"Protein ligand","score":0.4313448667526245},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4225572347640991},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4222294092178345},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4202064275741577},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4168768525123596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36870577931404114},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1468273401260376},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10828155279159546},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07677271962165833}],"concepts":[{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.6529653072357178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600337564945221},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5946969985961914},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5024855136871338},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4892115592956543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4686291515827179},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.438726007938385},{"id":"https://openalex.org/C109095088","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Protein ligand","level":2,"score":0.4313448667526245},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4225572347640991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4222294092178345},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4202064275741577},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4168768525123596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36870577931404114},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1468273401260376},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10828155279159546},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07677271962165833},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci100264e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci100264e","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:20936880","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20936880","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1506387682","https://openalex.org/W1512801428","https://openalex.org/W1988195734","https://openalex.org/W1993046136","https://openalex.org/W1993403967","https://openalex.org/W1999597013","https://openalex.org/W2060284524","https://openalex.org/W2067455153","https://openalex.org/W2076070421","https://openalex.org/W2092285329","https://openalex.org/W2148512505","https://openalex.org/W2154662590","https://openalex.org/W4253050621"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1967793880","https://openalex.org/W2792066564","https://openalex.org/W1186905254","https://openalex.org/W2898703579"],"abstract_inverted_index":{"With":[0,29],"the":[1,71,106,119,126,131],"emergence":[2],"of":[3,6],"large":[4,80],"collections":[5,32],"protein-ligand":[7,48],"complexes":[8],"complemented":[9],"by":[10,46],"binding":[11],"data,":[12],"as":[13],"found":[14],"in":[15,41,59,83,112,124],"PDBbind":[16,107],"or":[17,88,110],"BindingMOAD,":[18],"new":[19],"opportunities":[20],"for":[21,93],"parametrizing":[22],"and":[23,51,128],"evaluating":[24],"scoring":[25,39,97],"functions":[26,40],"have":[27],"arisen.":[28],"huge":[30],"data":[31,61],"available,":[33],"it":[34,102],"becomes":[35],"feasible":[36],"to":[37,66,69],"fit":[38],"a":[42,94,113],"QSAR":[43],"style,":[44],"i.e.,":[45],"defining":[47],"interaction":[49],"descriptors":[50],"analyzing":[52],"them":[53],"with":[54],"modern":[55],"machine-learning":[56],"methods.":[57],"As":[58],"each":[60],"modeling":[62],"ansatz,":[63],"care":[64],"has":[65],"be":[67],"taken":[68],"validate":[70],"model":[72],"carefully.":[73],"Here,":[74],"we":[75],"show":[76],"that":[77],"there":[78],"are":[79,122],"differences":[81],"measured":[82],"R":[84],"(0.77":[85],"vs":[86,91],"0.46)":[87],"R\u00b2":[89],"(0.59":[90],"0.21)":[92],"relatively":[95],"simple":[96],"function":[98],"depending":[99],"on":[100],"whether":[101],"is":[103],"validated":[104,111],"against":[105],"core":[108],"set":[109],"leave-cluster-out":[114],"cross-validation.":[115],"If":[116],"proteins":[117],"from":[118,135],"same":[120],"family":[121],"present":[123],"both":[125],"training":[127],"validation":[129,137],"set,":[130],"estimated":[132],"prediction":[133],"quality":[134],"standard":[136],"techniques":[138],"looks":[139],"too":[140],"optimistic.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}