{"id":"https://openalex.org/W2122629583","doi":"https://doi.org/10.1186/1758-2946-5-17","title":"The influence of the inactives subset generation on the performance of machine learning methods","display_name":"The influence of the inactives subset generation on the performance of machine learning methods","publication_year":2013,"publication_date":"2013-04-05","ids":{"openalex":"https://openalex.org/W2122629583","doi":"https://doi.org/10.1186/1758-2946-5-17","mag":"2122629583","pmid":"https://pubmed.ncbi.nlm.nih.gov/23561266"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-5-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-17","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-17","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/10.1186/1758-2946-5-17","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108421908","display_name":"Sabina Smusz","orcid":null},"institutions":[{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"funder","lineage":["https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210120768","display_name":"Maj Institute of Pharmacology","ror":"https://ror.org/0288swk05","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210120768","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I4210138023","display_name":"Medicina","ror":"https://ror.org/04m219c69","country_code":"PL","type":"healthcare","lineage":["https://openalex.org/I4210138023"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Sabina Smusz","raw_affiliation_strings":["Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland. bojarski@if-pan.krakow.pl","Faculty of Chemistry, Jagiellonian University, Krak\u00f3w, Poland","Department of Medicinal Chemistry, Institute of Pharmacology Polish Academy of Sciences, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland. bojarski@if-pan.krakow.pl","institution_ids":[]},{"raw_affiliation_string":"Faculty of Chemistry, Jagiellonian University, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I126596746"]},{"raw_affiliation_string":"Department of Medicinal Chemistry, Institute of Pharmacology Polish Academy of Sciences, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I4210120768","https://openalex.org/I4210138023","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060640473","display_name":"Rafa\u0142 Kurczab","orcid":"https://orcid.org/0000-0002-9555-3905"},"institutions":[{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"funder","lineage":["https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210120768","display_name":"Maj Institute of Pharmacology","ror":"https://ror.org/0288swk05","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210120768","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 Kurczab","raw_affiliation_strings":["Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland","Department of Medicinal Chemistry Institute of Pharmacology, Polish Academy of Sciences, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland","institution_ids":["https://openalex.org/I4210120768","https://openalex.org/I99542240"]},{"raw_affiliation_string":"Department of Medicinal Chemistry Institute of Pharmacology, Polish Academy of Sciences, Krak\u00f3w, Poland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025399512","display_name":"Andrzej J. Bojarski","orcid":"https://orcid.org/0000-0003-1417-6333"},"institutions":[{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"funder","lineage":["https://openalex.org/I99542240"]},{"id":"https://openalex.org/I4210120768","display_name":"Maj Institute of Pharmacology","ror":"https://ror.org/0288swk05","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210120768","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej J Bojarski","raw_affiliation_strings":["Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland","Department of Medicinal Chemistry Institute of Pharmacology, Polish Academy of Sciences, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, Sm\u0119tna 12, Krak\u00f3w, 31-343, Poland","institution_ids":["https://openalex.org/I4210120768","https://openalex.org/I99542240"]},{"raw_affiliation_string":"Department of Medicinal Chemistry Institute of Pharmacology, Polish Academy of Sciences, Krak\u00f3w, Poland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108421908"],"corresponding_institution_ids":["https://openalex.org/I126596746","https://openalex.org/I4210120768","https://openalex.org/I4210138023","https://openalex.org/I99542240"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":5.9578,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96603941,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6696000099182129,"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":0.6696000099182129,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.14910000562667847,"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":0.030899999663233757,"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/virtual-screening","display_name":"Virtual screening","score":0.8106206655502319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973662614822388},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6653050184249878},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6083170771598816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6022621393203735},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5385725498199463},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4927408993244171},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4886325001716614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4674898684024811},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41915401816368103},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4115683436393738},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41121524572372437},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.1605783998966217},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.1177985668182373}],"concepts":[{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.8106206655502319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973662614822388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6653050184249878},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6083170771598816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6022621393203735},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5385725498199463},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4927408993244171},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4886325001716614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4674898684024811},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41915401816368103},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4115683436393738},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41121524572372437},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.1605783998966217},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.1177985668182373},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/1758-2946-5-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-17","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-17","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:23561266","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23561266","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:ruj.uj.edu.pl:item/13746","is_oa":true,"landing_page_url":"http://ruj.uj.edu.pl/xmlui/handle/item/13746","pdf_url":null,"source":{"id":"https://openalex.org/S4306400316","display_name":"Homo Politicus (Academy of Humanities and Economics in Lodz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"artyku\u0142 w czasopi\u015bmie"},{"id":"pmh:oai:europepmc.org:2626531","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3626618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3626618","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3626618","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-5-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-17","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-17","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2122629583.pdf","grobid_xml":"https://content.openalex.org/works/W2122629583.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W159840418","https://openalex.org/W1604938182","https://openalex.org/W1968506227","https://openalex.org/W1978163942","https://openalex.org/W1984518758","https://openalex.org/W1988195734","https://openalex.org/W1988534836","https://openalex.org/W2015907087","https://openalex.org/W2017640164","https://openalex.org/W2021558456","https://openalex.org/W2031216614","https://openalex.org/W2056881083","https://openalex.org/W2068538859","https://openalex.org/W2078240823","https://openalex.org/W2096560421","https://openalex.org/W2107081909","https://openalex.org/W2112912103","https://openalex.org/W2121776789","https://openalex.org/W2124110045","https://openalex.org/W2125520654","https://openalex.org/W2127760066","https://openalex.org/W2133990480","https://openalex.org/W2134473739","https://openalex.org/W2145784250","https://openalex.org/W2148676930","https://openalex.org/W2148797284","https://openalex.org/W2157914995","https://openalex.org/W2159887157","https://openalex.org/W2164641162","https://openalex.org/W2176516200","https://openalex.org/W2177026622","https://openalex.org/W2911964244","https://openalex.org/W3083116277","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2123376283","https://openalex.org/W3201070945","https://openalex.org/W2792951589","https://openalex.org/W2743606042","https://openalex.org/W2038671703","https://openalex.org/W2122629583","https://openalex.org/W3090337104","https://openalex.org/W4376629715","https://openalex.org/W3027412285","https://openalex.org/W2315136930"],"abstract_inverted_index":{"BACKGROUND:":[0],"A":[1],"growing":[2],"popularity":[3],"of":[4,42,45,49,92,137,154,161,187],"machine":[5,147],"learning":[6,76,148],"methods":[7,77,149],"application":[8],"in":[9,12,21,80,103,169,179],"virtual":[10,170],"screening,":[11],"both":[13],"classification":[14,53,127],"and":[15,58,67,96,125],"regression":[16],"tasks,":[17,172],"can":[18],"be":[19,206],"observed":[20],"the":[22,40,43,47,52,62,72,87,135,146,159,209],"past":[23],"few":[24],"years.":[25],"However,":[26],"their":[27],"effectiveness":[28],"is":[29],"strongly":[30],"dependent":[31],"on":[32,51,145],"many":[33],"different":[34,117],"factors.":[35],"RESULTS:":[36],"In":[37],"this":[38],"study,":[39],"influence":[41],"way":[44,106],"forming":[46,202],"set":[48,139,204],"inactives":[50,101],"process":[54,136],"was":[55],"examined:":[56],"random":[57],"diverse":[59,193],"selection":[60,186],"from":[61,190],"ZINC":[63],"database,":[64],"MDDR":[65],"database":[66],"libraries":[68,214],"generated":[69],"according":[70],"to":[71,164,208],"DUD":[73],"methodology.":[74],"All":[75],"were":[78,112],"tested":[79,162],"two":[81],"modes:":[82],"using":[83,97],"one":[84],"test":[85,98],"set,":[86],"same":[88],"for":[89,108,115,122,174,213],"each":[90],"method":[91],"inactive":[93,138,200],"molecules":[94,123,168,189],"generation":[95],"sets":[99],"with":[100,129,192],"prepared":[102],"an":[104],"analogous":[105],"as":[107,173],"training.":[109],"The":[110,152,195],"experiments":[111],"carried":[113],"out":[114],"5":[116],"protein":[118],"targets,":[119],"3":[120],"fingerprints":[121],"representation":[124],"7":[126],"algorithms":[128],"varying":[130],"parameters.":[131],"It":[132],"appeared":[133],"that":[134,199,215],"formation":[140],"had":[141],"a":[142],"substantial":[143],"impact":[144],"performance.":[150],"CONCLUSIONS:":[151],"level":[153],"chemical":[155],"space":[156],"limitation":[157],"determined":[158],"ability":[160],"classifiers":[163],"select":[165],"potentially":[166],"active":[167,188],"screening":[171],"example":[175],"DUDs":[176],"(widely":[177],"applied":[178],"docking":[180],"experiments)":[181],"did":[182],"not":[183],"provide":[184],"proper":[185],"databases":[191],"structures.":[194],"study":[196],"clearly":[197],"showed":[198],"compounds":[201],"training":[203],"should":[205],"representative":[207],"highest":[210],"possible":[211],"extent":[212],"undergo":[216],"screening.":[217]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}