{"id":"https://openalex.org/W2003998164","doi":"https://doi.org/10.1021/ci4000536","title":"Oversampling to Overcome Overfitting: Exploring the Relationship between Data Set Composition, Molecular Descriptors, and Predictive Modeling Methods","display_name":"Oversampling to Overcome Overfitting: Exploring the Relationship between Data Set Composition, Molecular Descriptors, and Predictive Modeling Methods","publication_year":2013,"publication_date":"2013-03-06","ids":{"openalex":"https://openalex.org/W2003998164","doi":"https://doi.org/10.1021/ci4000536","mag":"2003998164","pmid":"https://pubmed.ncbi.nlm.nih.gov/23464929"},"language":"en","primary_location":{"id":"doi:10.1021/ci4000536","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci4000536","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/A5102155986","display_name":"Chia\u2010Yun Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Yun Chang","raw_affiliation_strings":["School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,\rTaipei, Taiwan 100","School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road, Taipei, Taiwan 100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,\rTaipei, Taiwan 100","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road, Taipei, Taiwan 100","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055631081","display_name":"Ming-Tsung Hsu","orcid":"https://orcid.org/0000-0002-6940-1844"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Tsung Hsu","raw_affiliation_strings":["Genome\rand Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,\rTaipei, Taiwan 106","Genome#R#and Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,#R#Taipei, Taiwan 106"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome\rand Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,\rTaipei, Taiwan 106","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Genome#R#and Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,#R#Taipei, Taiwan 106","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084220892","display_name":"Emilio Xavier Esposito","orcid":"https://orcid.org/0000-0002-6193-0485"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emilio Xavier Esposito","raw_affiliation_strings":["exeResearch, LLC, 32 University Drive, East Lansing,\rMichigan 48823, United States","exeResearch, LLC, 32 University Drive, East Lansing,#R#Michigan 48823, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"exeResearch, LLC, 32 University Drive, East Lansing,\rMichigan 48823, United States","institution_ids":[]},{"raw_affiliation_string":"exeResearch, LLC, 32 University Drive, East Lansing,#R#Michigan 48823, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021255582","display_name":"Yufeng Jane Tseng","orcid":"https://orcid.org/0000-0002-8461-6181"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yufeng J. Tseng","raw_affiliation_strings":["Department of Computer Science and Information\rEngineering, National Taiwan University, No.1 Sec.4, Roosevelt Road, Taipei, Taiwan 106","Genome\rand Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,\rTaipei, Taiwan 106","Graduate Institute of Biomedical Electronics and\rBioinformatics, National Taiwan University, No.1 Sec.4, Roosevelt Road, Taipei, Taiwan 106","School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,\rTaipei, Taiwan 100","School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,#R#Taipei, Taiwan 100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information\rEngineering, National Taiwan University, No.1 Sec.4, Roosevelt Road, Taipei, Taiwan 106","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Genome\rand Systems Biology Degree Program, College of Life Science, National Taiwan University, No.1 Sec.4, Roosevelt Road,\rTaipei, Taiwan 106","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Biomedical Electronics and\rBioinformatics, National Taiwan University, No.1 Sec.4, Roosevelt Road, Taipei, Taiwan 106","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,\rTaipei, Taiwan 100","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"School of Pharmacy, College of Medicine, National Taiwan University, No.1, Sec.1, Jen-Ai Road,#R#Taipei, Taiwan 100","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021255582"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":5.5867,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96053965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"53","issue":"4","first_page":"958","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"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":0.9991999864578247,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9300000071525574,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9875731468200684},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9207351207733154},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7881664633750916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7243585586547852},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7192053198814392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7099143266677856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6448665857315063},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5806660056114197},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.528488039970398},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5085059404373169},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.4750397503376007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39687004685401917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3859366178512573},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.23218974471092224},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1268177032470703}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9875731468200684},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9207351207733154},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7881664633750916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7243585586547852},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7192053198814392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7099143266677856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448665857315063},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5806660056114197},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.528488039970398},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5085059404373169},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.4750397503376007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39687004685401917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3859366178512573},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.23218974471092224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1268177032470703},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D002470","descriptor_name":"Cell Survival","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D002470","descriptor_name":"Cell Survival","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D002470","descriptor_name":"Cell Survival","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003603","descriptor_name":"Cytotoxins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019169","descriptor_name":"Jurkat Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019169","descriptor_name":"Jurkat Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019169","descriptor_name":"Jurkat Cells","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":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000633","qualifier_name":"toxicity","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","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},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci4000536","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci4000536","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:23464929","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23464929","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:140.112.114.62:246246/260664","is_oa":false,"landing_page_url":"http://ntur.lib.ntu.edu.tw//handle/246246/260664","pdf_url":null,"source":{"id":"https://openalex.org/S4306402491","display_name":"NTUR (\u81fa\u7063\u6a5f\u69cb\u5178\u85cf)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16733864","host_organization_name":"National Taiwan University","host_organization_lineage":["https://openalex.org/I16733864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1964185884","https://openalex.org/W1968996837","https://openalex.org/W1977340881","https://openalex.org/W1985699832","https://openalex.org/W1988195734","https://openalex.org/W1990302994","https://openalex.org/W1999318832","https://openalex.org/W2005382895","https://openalex.org/W2007436490","https://openalex.org/W2010184995","https://openalex.org/W2010524461","https://openalex.org/W2016610112","https://openalex.org/W2023639956","https://openalex.org/W2031372687","https://openalex.org/W2047909810","https://openalex.org/W2049801133","https://openalex.org/W2053154970","https://openalex.org/W2059405137","https://openalex.org/W2065354989","https://openalex.org/W2068337719","https://openalex.org/W2071458812","https://openalex.org/W2074621016","https://openalex.org/W2081659180","https://openalex.org/W2085009790","https://openalex.org/W2087466582","https://openalex.org/W2095441995","https://openalex.org/W2099094031","https://openalex.org/W2099550922","https://openalex.org/W2102592852","https://openalex.org/W2108564850","https://openalex.org/W2112208320","https://openalex.org/W2123969444","https://openalex.org/W2124776405","https://openalex.org/W2138723475","https://openalex.org/W2143417663","https://openalex.org/W2147695654","https://openalex.org/W2148603752","https://openalex.org/W2149706766","https://openalex.org/W2153635508","https://openalex.org/W2164296439","https://openalex.org/W2167960921","https://openalex.org/W2334218692","https://openalex.org/W2494768458","https://openalex.org/W2911964244","https://openalex.org/W4230674625"],"related_works":["https://openalex.org/W4389965896","https://openalex.org/W4387747402","https://openalex.org/W3119578451","https://openalex.org/W2903618681","https://openalex.org/W3172259201","https://openalex.org/W3184937791","https://openalex.org/W3208882810","https://openalex.org/W2972862903","https://openalex.org/W3099765033","https://openalex.org/W4288419306"],"abstract_inverted_index":{"The":[0,48,90,170],"traditional":[1],"biological":[2,21,29,43],"assay":[3],"is":[4,23,35,95,114],"very":[5,102],"time-consuming,":[6],"and":[7,45,71,101,106,167,180,183,188,221],"thus":[8],"the":[9,28,39,56,86,107,110,129,137,146,159,191,204,206,219],"ability":[10,108],"to":[11,75,78,85,128,157,190,200],"quickly":[12],"screen":[13],"large":[14],"numbers":[15],"of":[16,31,41,58,68,109,161,164,194],"compounds":[17,80,100,144],"against":[18],"a":[19,62],"specific":[20],"target":[22],"appealing.":[24],"To":[25],"speed":[26],"up":[27],"evaluation":[30],"compounds,":[32],"high-throughput":[33],"screening":[34],"widely":[36],"used":[37,156],"in":[38,51,117,134,203],"fields":[40],"biomedical,":[42],"information,":[44],"drug":[46],"discovery.":[47],"research":[49],"presented":[50],"this":[52,135],"study":[53,136],"focuses":[54],"on":[55],"use":[57],"support":[59],"vector":[60,151],"machines,":[61],"machine":[63,152],"learning":[64],"method,":[65],"various":[66],"classes":[67,163],"molecular":[69,165],"descriptors,":[70],"different":[72,162],"sampling":[73],"techniques":[74],"overcome":[76],"overfitting":[77],"classify":[79],"for":[81,218],"cytotoxicity":[82,92],"with":[83,126],"respect":[84,127],"Jurkat":[87],"cell":[88,91],"line.":[89],"data":[93,122,212],"set":[94],"imbalanced":[96,121],"(a":[97],"few":[98],"active":[99],"many":[103],"inactive":[104,142],"compounds),":[105],"predictive":[111,192,216],"modeling":[112],"methods":[113],"adversely":[115],"affected":[116],"these":[118],"situations.":[119],"Commonly":[120],"sets":[123,213],"are":[124],"overfit":[125,140],"dominant":[130],"classified":[131],"end":[132],"point;":[133],"models":[138,154,172,208],"routinely":[139],"toward":[141],"(noncytotoxic)":[143],"when":[145],"imbalance":[147],"was":[148],"substantial.":[149],"Support":[150],"(SVM)":[153],"were":[155,173],"probe":[158],"proficiency":[160],"descriptors":[166,186],"oversampling":[168],"ratios.":[169],"SVM":[171,207],"constructed":[174],"from":[175,210],"4D-FPs,":[176],"MOE":[177],"(1D,":[178],"2D,":[179],"21/2D),":[181],"noNP+MOE,":[182],"CATS2D":[184],"trial":[185],"pools":[187],"compared":[189],"abilities":[193,217],"CATS2D-based":[195],"random":[196],"forest":[197],"models.":[198],"Compared":[199],"previous":[201],"results":[202],"literature,":[205],"built":[209],"oversampled":[211],"exhibited":[214],"better":[215],"training":[220],"external":[222],"test":[223],"sets.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":6}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}