{"id":"https://openalex.org/W3097920362","doi":"https://doi.org/10.1186/s13321-020-00468-x","title":"Structure\u2013activity relationship-based chemical classification of highly imbalanced Tox21 datasets","display_name":"Structure\u2013activity relationship-based chemical classification of highly imbalanced Tox21 datasets","publication_year":2020,"publication_date":"2020-10-27","ids":{"openalex":"https://openalex.org/W3097920362","doi":"https://doi.org/10.1186/s13321-020-00468-x","mag":"3097920362","pmid":"https://pubmed.ncbi.nlm.nih.gov/33372637"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-020-00468-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00468-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00468-x","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/track/pdf/10.1186/s13321-020-00468-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019222897","display_name":"Gabriel Idakwo","orcid":null},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gabriel Idakwo","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109333974","display_name":"Sundar Thangapandian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088792","display_name":"United States Army","ror":"https://ror.org/00afsp483","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I4210088792"]},{"id":"https://openalex.org/I87303767","display_name":"U.S. Army Engineer Research and Development Center","ror":"https://ror.org/027mhn368","country_code":"US","type":"facility","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1306490931","https://openalex.org/I1330347796","https://openalex.org/I87303767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sundar Thangapandian","raw_affiliation_strings":["Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA"],"affiliations":[{"raw_affiliation_string":"Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA","institution_ids":["https://openalex.org/I87303767","https://openalex.org/I4210088792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011631125","display_name":"Joseph Luttrell","orcid":"https://orcid.org/0000-0001-5832-4487"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Luttrell","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404075","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-3134-7715"},"institutions":[{"id":"https://openalex.org/I4210125162","display_name":"Bennett Aerospace (United States)","ror":"https://ror.org/038b3cg44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125162"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["Bennett Aerospace Inc, Cary, NC, 27518, USA"],"affiliations":[{"raw_affiliation_string":"Bennett Aerospace Inc, Cary, NC, 27518, USA","institution_ids":["https://openalex.org/I4210125162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332727","display_name":"Nan Wang","orcid":"https://orcid.org/0000-0002-0172-6853"},"institutions":[{"id":"https://openalex.org/I89554219","display_name":"New Jersey City University","ror":"https://ror.org/0546wew42","country_code":"US","type":"education","lineage":["https://openalex.org/I89554219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["Department of Computer Science, New Jersey City University, Jersey City, NJ, 07305, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Jersey City University, Jersey City, NJ, 07305, USA","institution_ids":["https://openalex.org/I89554219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001575594","display_name":"Zhaoxian Zhou","orcid":"https://orcid.org/0000-0001-6789-166X"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoxian Zhou","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742819","display_name":"Huixiao Hong","orcid":"https://orcid.org/0000-0001-8087-3968"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huixiao Hong","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Centre for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Centre for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, 72079, USA","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088929013","display_name":"Bei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Yang","raw_affiliation_strings":["School of Information & Engineering, Zhengzhou University, Zhengzhou, 450000, China"],"affiliations":[{"raw_affiliation_string":"School of Information & Engineering, Zhengzhou University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603443","display_name":"Chaoyang Zhang","orcid":"https://orcid.org/0000-0001-6873-1780"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaoyang Zhang","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA. chaoyang.zhang@usm.edu","School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA. chaoyang.zhang@usm.edu","institution_ids":["https://openalex.org/I44854399"]},{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021166773","display_name":"Ping Gong","orcid":"https://orcid.org/0000-0002-4782-1741"},"institutions":[{"id":"https://openalex.org/I4210088792","display_name":"United States Army","ror":"https://ror.org/00afsp483","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I4210088792"]},{"id":"https://openalex.org/I87303767","display_name":"U.S. Army Engineer Research and Development Center","ror":"https://ror.org/027mhn368","country_code":"US","type":"facility","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1306490931","https://openalex.org/I1330347796","https://openalex.org/I87303767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Gong","raw_affiliation_strings":["Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA. Ping.Gong@usace.army.mil","Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA"],"affiliations":[{"raw_affiliation_string":"Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA. Ping.Gong@usace.army.mil","institution_ids":["https://openalex.org/I87303767"]},{"raw_affiliation_string":"Environmental Laboratory, U.S. Army Engineer Research and Development Center, Vicksburg, MS, 39180, USA","institution_ids":["https://openalex.org/I87303767","https://openalex.org/I4210088792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5019222897"],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":7.9457,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.97895192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"66","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9661999940872192,"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/undersampling","display_name":"Undersampling","score":0.9630880355834961},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8505749702453613},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8051456212997437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6360030174255371},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.60340815782547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5435627698898315},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4560241401195526},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.45418301224708557},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.44642284512519836},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.44564002752304077},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4254457950592041},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4179181456565857},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24158775806427002},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.11880248785018921}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.9630880355834961},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8505749702453613},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8051456212997437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6360030174255371},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.60340815782547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5435627698898315},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4560241401195526},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.45418301224708557},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.44642284512519836},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.44564002752304077},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4254457950592041},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4179181456565857},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24158775806427002},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11880248785018921},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-020-00468-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00468-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00468-x","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:33372637","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33372637","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:aquila.usm.edu:fac_pubs-19500","is_oa":false,"landing_page_url":"https://aquila.usm.edu/fac_pubs/18186","pdf_url":null,"source":{"id":"https://openalex.org/S4306402529","display_name":"Aquila Digital Community (University of Southern Mississippi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44854399","host_organization_name":"University of Southern Mississippi","host_organization_lineage":["https://openalex.org/I44854399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:b896e5129bce4435858ec953edd5dd19","is_oa":true,"landing_page_url":"https://doaj.org/article/b896e5129bce4435858ec953edd5dd19","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 12, Iss 1, Pp 1-19 (2020)","raw_type":"article"},{"id":"pmh:oai:osti.gov:1690302","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1690302","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7592558","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7592558","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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/s13321-020-00468-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00468-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00468-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332382","display_name":"Oak Ridge Institute for Science and Education","ror":"https://ror.org/0526p1y61"},{"id":"https://openalex.org/F4320337538","display_name":"U.S. Army Corps of Engineers","ror":"https://ror.org/05w4e8v21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097920362.pdf","grobid_xml":"https://content.openalex.org/works/W3097920362.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W89348055","https://openalex.org/W108703714","https://openalex.org/W571200655","https://openalex.org/W1524761913","https://openalex.org/W1533664488","https://openalex.org/W1563938718","https://openalex.org/W1594358814","https://openalex.org/W1766594731","https://openalex.org/W1964874140","https://openalex.org/W1965427641","https://openalex.org/W1966716734","https://openalex.org/W1976526581","https://openalex.org/W1977640460","https://openalex.org/W1988037271","https://openalex.org/W1993220166","https://openalex.org/W1999552083","https://openalex.org/W2010524461","https://openalex.org/W2021070595","https://openalex.org/W2027482274","https://openalex.org/W2039618891","https://openalex.org/W2068258779","https://openalex.org/W2074681440","https://openalex.org/W2090135786","https://openalex.org/W2096945460","https://openalex.org/W2099454382","https://openalex.org/W2101234009","https://openalex.org/W2107686700","https://openalex.org/W2112415299","https://openalex.org/W2115629999","https://openalex.org/W2116825089","https://openalex.org/W2118978333","https://openalex.org/W2119498311","https://openalex.org/W2140190241","https://openalex.org/W2148143831","https://openalex.org/W2165466912","https://openalex.org/W2170413589","https://openalex.org/W2185853310","https://openalex.org/W2189911347","https://openalex.org/W2194079679","https://openalex.org/W2226725405","https://openalex.org/W2258357609","https://openalex.org/W2264925244","https://openalex.org/W2266978829","https://openalex.org/W2276859037","https://openalex.org/W2279004469","https://openalex.org/W2315136930","https://openalex.org/W2320075934","https://openalex.org/W2338318698","https://openalex.org/W2345751939","https://openalex.org/W2515889482","https://openalex.org/W2521200999","https://openalex.org/W2568027568","https://openalex.org/W2594788739","https://openalex.org/W2616891418","https://openalex.org/W2620760558","https://openalex.org/W2758914739","https://openalex.org/W2761600385","https://openalex.org/W2767034401","https://openalex.org/W2889276168","https://openalex.org/W2909055772","https://openalex.org/W2911964244","https://openalex.org/W2912485311","https://openalex.org/W2950238754","https://openalex.org/W2964331234","https://openalex.org/W2966115457","https://openalex.org/W2968395974","https://openalex.org/W2970175280","https://openalex.org/W2975373043","https://openalex.org/W2979765270","https://openalex.org/W3095491482","https://openalex.org/W4230683138","https://openalex.org/W4232935748","https://openalex.org/W4233712753","https://openalex.org/W4243990219","https://openalex.org/W6839808826"],"related_works":["https://openalex.org/W4308469503","https://openalex.org/W32988189","https://openalex.org/W2904737874","https://openalex.org/W80466363","https://openalex.org/W4389233021","https://openalex.org/W2399571531","https://openalex.org/W2947132063","https://openalex.org/W4288337828","https://openalex.org/W4287816717","https://openalex.org/W4390415670"],"abstract_inverted_index":{"The":[0,202,238,306],"specificity":[1],"of":[2,12,102,110,146,204,230,283,290,318,322,334,347],"toxicant-target":[3],"biomolecule":[4],"interactions":[5],"lends":[6],"to":[7,68,83,97,122,308],"the":[8,44,62,77,99,124,134,139,167,173,205,231,235,244,255,269,273,281,288,310,315,332,345],"very":[9],"imbalanced":[10,103,141,336],"nature":[11],"many":[13],"toxicity":[14,338],"datasets,":[15],"causing":[16],"poor":[17],"performance":[18,203,233,333],"in":[19,53,61,95,148,325],"Structure-Activity":[20],"Relationship":[21],"(SAR)-based":[22],"chemical":[23,40,337],"classification.":[24],"Undersampling":[25,191],"and":[26,86,116,170,197,222,243,272],"oversampling":[27],"are":[28],"representative":[29],"techniques":[30],"for":[31,151],"handling":[32,186],"such":[33],"an":[34,48],"imbalance":[35,185,274],"challenge.":[36],"However,":[37],"removing":[38],"inactive":[39,284,319],"compound":[41],"instances":[42,60,72],"from":[43,314],"majority":[45,78],"class":[46,64,79,84,126],"using":[47,211],"undersampling":[49],"technique":[50],"can":[51,340],"result":[52],"information":[54],"loss,":[55],"whereas":[56],"increasing":[57],"active":[58,291,312],"toxicant":[59],"minority":[63,71,125],"by":[65,127,132,287],"interpolation":[66],"tends":[67],"introduce":[69],"artificial":[70],"that":[73,155,251,262,331],"often":[74],"cross":[75],"into":[76],"space,":[80],"giving":[81],"rise":[82],"overlapping":[85],"a":[87,108,226,263,300],"higher":[88],"false":[89],"prediction":[90,100,270],"rate.":[91],"In":[92],"this":[93],"study,":[94],"order":[96],"improve":[98],"accuracy":[101,271],"learning,":[104],"we":[105,176],"employed":[106],"SMOTEENN,":[107],"combination":[109],"Synthetic":[111],"Minority":[112],"Over-sampling":[113],"Technique":[114],"(SMOTE)":[115],"Edited":[117],"Nearest":[118],"Neighbor":[119],"(ENN)":[120],"algorithms,":[121],"oversample":[123],"creating":[128],"synthetic":[129],"samples,":[130],"followed":[131],"cleaning":[133],"mislabeled":[135],"instances.":[136],"We":[137,259],"chose":[138],"highly":[140],"Tox21":[142],"dataset,":[143],"which":[144,216,277],"consisted":[145],"12":[147,236],"vitro":[149],"bioassays":[150],">":[152,304],"10,000":[153],"chemicals":[154],"were":[156],"distributed":[157],"unevenly":[158],"between":[159,268],"binary":[160],"classes.":[161],"With":[162],"Random":[163,190],"Forest":[164],"(RF)":[165],"as":[166,172,280],"base":[168],"classifier":[169],"bagging":[171],"ensemble":[174],"strategy,":[175],"applied":[177],"four":[178,206],"hybrid":[179],"learning":[180,207],"methods,":[181],"i.e.,":[182],"RF":[183,188,193,198],"without":[184],"(RF),":[187],"with":[189,194,199],"(RUS),":[192],"SMOTE":[195],"(SMO),":[196],"SMOTEENN":[200],"(SMN).":[201],"methods":[208],"was":[209],"compared":[210],"nine":[212],"evaluation":[213],"metrics,":[214],"among":[215],"F<sub>1</sub>":[217],"score,":[218],"Matthews":[219],"correlation":[220,266],"coefficient":[221],"Brier":[223],"score":[224],"provided":[225],"more":[227],"consistent":[228],"assessment":[229],"overall":[232],"across":[234],"datasets.":[237],"Friedman's":[239],"aligned":[240],"ranks":[241],"test":[242,249],"subsequent":[245],"Bergmann-Hommel":[246],"post":[247],"hoc":[248],"showed":[250],"SMN":[252,293],"significantly":[253,342],"outperformed":[254],"other":[256],"three":[257],"methods.":[258],"also":[260],"found":[261],"strong":[264],"negative":[265],"existed":[267],"ratio":[275],"(IR),":[276],"is":[278,321],"defined":[279],"number":[282,289],"compounds":[285,313],"divided":[286],"compounds.":[292],"became":[294],"less":[295],"effective":[296],"when":[297],"IR":[298],"exceeded":[299],"certain":[301],"threshold":[302],"(e.g.,":[303],"28).":[305],"ability":[307],"separate":[309],"few":[311],"vast":[316],"amounts":[317],"ones":[320],"great":[323],"importance":[324],"computational":[326],"toxicology.":[327],"This":[328],"work":[329],"demonstrates":[330],"SAR-based,":[335],"classification":[339],"be":[341],"improved":[343],"through":[344],"use":[346],"data":[348],"rebalancing.":[349]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":17}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}