{"id":"https://openalex.org/W2912564562","doi":"https://doi.org/10.1021/acs.jcim.8b00663","title":"Evaluation of Cross-Validation Strategies in Sequence-Based Binding Prediction Using Deep Learning","display_name":"Evaluation of Cross-Validation Strategies in Sequence-Based Binding Prediction Using Deep Learning","publication_year":2019,"publication_date":"2019-02-07","ids":{"openalex":"https://openalex.org/W2912564562","doi":"https://doi.org/10.1021/acs.jcim.8b00663","mag":"2912564562","pmid":"https://pubmed.ncbi.nlm.nih.gov/30730731"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00663","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00663","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":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/168430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053502564","display_name":"Angela Lopez-del Rio","orcid":"https://orcid.org/0000-0002-5486-7465"},"institutions":[{"id":"https://openalex.org/I1307323311","display_name":"Hospital Sant Joan de D\u00e9u Barcelona","ror":"https://ror.org/001jx2139","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I1307323311"]},{"id":"https://openalex.org/I4210105141","display_name":"Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine","ror":"https://ror.org/01gm5f004","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210105141"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Angela Lopez-del Rio","raw_affiliation_strings":["B2SLab, Departament d\u2019Enginyeria de Sistemes, Autom\u00e0tica i Inform\u00e0tica Industrial, Universitat Polit\u00e8cnica de Catalunya, 08028 Barcelona, Spain","Department of Biomedical Engineering, Institut de Recerca Pedi\u00e0trica Hospital Sant Joan de D\u00e9u, Esplugues de Llobregat, 08950 Barcelona, Spain","Mind the Byte S.L., 08007 Barcelona, Spain","Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN) 28029 Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5486-7465","affiliations":[{"raw_affiliation_string":"B2SLab, Departament d\u2019Enginyeria de Sistemes, Autom\u00e0tica i Inform\u00e0tica Industrial, Universitat Polit\u00e8cnica de Catalunya, 08028 Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Institut de Recerca Pedi\u00e0trica Hospital Sant Joan de D\u00e9u, Esplugues de Llobregat, 08950 Barcelona, Spain","institution_ids":["https://openalex.org/I1307323311"]},{"raw_affiliation_string":"Mind the Byte S.L., 08007 Barcelona, Spain","institution_ids":[]},{"raw_affiliation_string":"Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN) 28029 Madrid, Spain","institution_ids":["https://openalex.org/I4210105141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051270084","display_name":"Alfons Nonell\u2010Canals","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfons Nonell-Canals","raw_affiliation_strings":["Mind the Byte S.L., 08007 Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mind the Byte S.L., 08007 Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029522345","display_name":"David Vidal","orcid":"https://orcid.org/0000-0002-2658-5313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Vidal","raw_affiliation_strings":["Mind the Byte S.L., 08007 Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mind the Byte S.L., 08007 Barcelona, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041616492","display_name":"Alexandre Perera-Lluna","orcid":"https://orcid.org/0000-0001-6427-851X"},"institutions":[{"id":"https://openalex.org/I1307323311","display_name":"Hospital Sant Joan de D\u00e9u Barcelona","ror":"https://ror.org/001jx2139","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I1307323311"]},{"id":"https://openalex.org/I4210105141","display_name":"Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine","ror":"https://ror.org/01gm5f004","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210105141"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alexandre Perera-Lluna","raw_affiliation_strings":["B2SLab, Departament d\u2019Enginyeria de Sistemes, Autom\u00e0tica i Inform\u00e0tica Industrial, Universitat Polit\u00e8cnica de Catalunya, 08028 Barcelona, Spain","Department of Biomedical Engineering, Institut de Recerca Pedi\u00e0trica Hospital Sant Joan de D\u00e9u, Esplugues de Llobregat, 08950 Barcelona, Spain","Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN) 28029 Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"B2SLab, Departament d\u2019Enginyeria de Sistemes, Autom\u00e0tica i Inform\u00e0tica Industrial, Universitat Polit\u00e8cnica de Catalunya, 08028 Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Institut de Recerca Pedi\u00e0trica Hospital Sant Joan de D\u00e9u, Esplugues de Llobregat, 08950 Barcelona, Spain","institution_ids":["https://openalex.org/I1307323311"]},{"raw_affiliation_string":"Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN) 28029 Madrid, Spain","institution_ids":["https://openalex.org/I4210105141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053502564"],"corresponding_institution_ids":["https://openalex.org/I1307323311","https://openalex.org/I4210105141","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":4.447,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94891079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"59","issue":"4","first_page":"1645","last_page":"1657"},"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":0.9952999949455261,"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.7303724884986877},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6622446179389954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6603559255599976},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.653410792350769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6026785373687744},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.563403308391571},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5473664999008179},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49404457211494446},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4688825309276581},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.43458759784698486},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.42541688680648804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11784723401069641},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09208786487579346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303724884986877},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6622446179389954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603559255599976},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.653410792350769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6026785373687744},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.563403308391571},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5473664999008179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49404457211494446},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4688825309276581},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.43458759784698486},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.42541688680648804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11784723401069641},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09208786487579346},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jcim.8b00663","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00663","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:30730731","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30730731","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},{"id":"pmh:oai:recercat.cat:2072/361635","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/168430","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},{"id":"pmh:oai:dnet:upcommonspor::818bffb2ee1448748cf31fc6ec2986bb","is_oa":true,"landing_page_url":"https://chemrxiv.org/articles/Evaluation_of_Cross-Validation_Strategies_in_Sequence-Based_Binding_Prediction_Using_Deep_Learning/7133885/1","pdf_url":"http://hdl.handle.net/2117/168430","source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"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":"info:eu-repo/semantics/submittedVersion"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/361635","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/168430","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5218991717","display_name":null,"funder_award_id":"TEC2014-60337-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G5920264666","display_name":null,"funder_award_id":"TEC2017 DPI2017-89827-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G7751642955","display_name":null,"funder_award_id":"DI 2016-080","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334923","display_name":"Instituto de Salud Carlos III","ror":"https://ror.org/00ca2c886"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W109016873","https://openalex.org/W1545231783","https://openalex.org/W1598796236","https://openalex.org/W1655274992","https://openalex.org/W1738019091","https://openalex.org/W1964513093","https://openalex.org/W1968319881","https://openalex.org/W1975147762","https://openalex.org/W1975875968","https://openalex.org/W1982131304","https://openalex.org/W1988037271","https://openalex.org/W1995341919","https://openalex.org/W1995495408","https://openalex.org/W1999798000","https://openalex.org/W2008381136","https://openalex.org/W2016979469","https://openalex.org/W2019678805","https://openalex.org/W2021574925","https://openalex.org/W2027482274","https://openalex.org/W2042110087","https://openalex.org/W2053154970","https://openalex.org/W2060531713","https://openalex.org/W2083339697","https://openalex.org/W2095705004","https://openalex.org/W2107845562","https://openalex.org/W2108101947","https://openalex.org/W2110065044","https://openalex.org/W2119512897","https://openalex.org/W2127760066","https://openalex.org/W2134299061","https://openalex.org/W2156226201","https://openalex.org/W2158461363","https://openalex.org/W2159229889","https://openalex.org/W2189911347","https://openalex.org/W2194775991","https://openalex.org/W2213443318","https://openalex.org/W2214665483","https://openalex.org/W2268071782","https://openalex.org/W2325343629","https://openalex.org/W2471196942","https://openalex.org/W2475330876","https://openalex.org/W2502949459","https://openalex.org/W2565684601","https://openalex.org/W2567534979","https://openalex.org/W2611386757","https://openalex.org/W2740946158","https://openalex.org/W2749122933","https://openalex.org/W2786785157","https://openalex.org/W2803094965","https://openalex.org/W2806547269","https://openalex.org/W2897885572","https://openalex.org/W2919115771","https://openalex.org/W2964121744","https://openalex.org/W3104508774","https://openalex.org/W4285719527","https://openalex.org/W4292916026","https://openalex.org/W4299737965"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4375867731","https://openalex.org/W2371138613","https://openalex.org/W816105089","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W1800458610","https://openalex.org/W2384527366"],"abstract_inverted_index":{"Binding":[0],"prediction":[1,60],"between":[2],"targets":[3],"and":[4,78,86,94,109,137,179,195],"drug-like":[5],"compounds":[6],"through":[7],"deep":[8,105,147],"neural":[9],"networks":[10],"has":[11],"generated":[12],"promising":[13],"results":[14,160,199],"in":[15,91,95,128,175],"recent":[16],"years,":[17],"outperforming":[18],"traditional":[19],"machine":[20],"learning-based":[21,148],"methods.":[22],"However,":[23],"the":[24,56,92,96,129,154,157,163],"generalization":[25,166],"capability":[26],"of":[27,58,76,125,145,156,165,167],"these":[28,168],"classification":[29,143],"models":[30,169],"is":[31,151,170],"still":[32],"an":[33],"issue":[34],"to":[35,48,55,103,110,116,153,172,190],"be":[36,117],"addressed.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"explored":[42],"how":[43],"different":[44,51,123],"cross-validation":[45,183],"strategies":[46,64],"applied":[47,102],"data":[49],"from":[50],"molecular":[52,177],"databases":[53,178],"affect":[54],"performance":[57,144,203],"binding":[59],"proteochemometrics":[61,107,149],"models.":[62],"These":[63,99],"are":[65,101,131],"(1)":[66,133],"random":[67],"splitting,":[68],"(2)":[69,138],"splitting":[70,81,88],"based":[71,82,89,185],"on":[72,83,186],"K-means":[73],"clustering":[74,93,188],"(both":[75],"actives":[77],"inactives),":[79],"(3)":[80],"source":[84,97],"database,":[85],"(4)":[87],"both":[90],"database.":[98],"schemas":[100],"a":[104,111,173,181],"learning":[106],"model":[108,115,130,150],"simple":[112],"logistic":[113],"regression":[114],"used":[118],"as":[119],"baseline.":[120],"Additionally,":[121],"two":[122],"ways":[124],"describing":[126],"molecules":[127,206],"tested:":[132],"by":[134,139,207],"their":[135,208],"SMILES":[136],"three":[140],"fingerprints.":[141,209],"The":[142],"our":[146],"comparable":[152],"state":[155],"art.":[158],"Our":[159,198],"show":[161,201],"that":[162,180],"lack":[164],"due":[171],"bias":[174],"public":[176],"restrictive":[182],"schema":[184],"compound":[187],"leads":[189],"worse":[191],"but":[192],"more":[193],"robust":[194],"credible":[196],"results.":[197],"also":[200],"better":[202],"when":[204],"representing":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}