{"id":"https://openalex.org/W2024391534","doi":"https://doi.org/10.1021/ci900080f","title":"A Model-Based Ensembling Approach for Developing QSARs","display_name":"A Model-Based Ensembling Approach for Developing QSARs","publication_year":2009,"publication_date":"2009-07-13","ids":{"openalex":"https://openalex.org/W2024391534","doi":"https://doi.org/10.1021/ci900080f","mag":"2024391534","pmid":"https://pubmed.ncbi.nlm.nih.gov/19807194"},"language":"en","primary_location":{"id":"doi:10.1021/ci900080f","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci900080f","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":"https://www.ncbi.nlm.nih.gov/pmc/articles/2760036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024493594","display_name":"Qianyi Zhang","orcid":"https://orcid.org/0000-0003-0973-0037"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]},{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"Qianyi Zhang","raw_affiliation_strings":["Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I137902535","https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075245616","display_name":"Jacqueline M. Hughes\u2010Oliver","orcid":"https://orcid.org/0000-0002-6464-9955"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]},{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Jacqueline M. Hughes-Oliver","raw_affiliation_strings":["Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I137902535","https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113567130","display_name":"Raymond T. Ng","orcid":"https://orcid.org/0000-0003-3692-8524"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]},{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Raymond T. Ng","raw_affiliation_strings":["Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, and Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I137902535","https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024493594"],"corresponding_institution_ids":["https://openalex.org/I137902535","https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":2.8364,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9007065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"49","issue":"8","first_page":"1857","last_page":"1865"},"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14249","display_name":"Water Quality Monitoring and Analysis","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.7313550710678101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112146615982056},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5960244536399841},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5809191465377808},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5755835771560669},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5752590298652649},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5641617774963379},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.546390950679779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5255141258239746},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.4503275156021118},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32809603214263916},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.07462534308433533}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.7313550710678101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112146615982056},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5960244536399841},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5809191465377808},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5755835771560669},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5752590298652649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5641617774963379},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.546390950679779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5255141258239746},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.4503275156021118},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32809603214263916},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.07462534308433533},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","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":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci900080f","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci900080f","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:19807194","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19807194","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:pubmedcentral.nih.gov:2760036","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2760036","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2760036","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2760036","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310013","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W85259421","https://openalex.org/W1534477342","https://openalex.org/W1595468493","https://openalex.org/W1680392829","https://openalex.org/W1978163942","https://openalex.org/W1987202142","https://openalex.org/W1988195734","https://openalex.org/W1994126845","https://openalex.org/W1997355076","https://openalex.org/W2032245355","https://openalex.org/W2082698910","https://openalex.org/W2199634952","https://openalex.org/W2482589566","https://openalex.org/W2911964244","https://openalex.org/W4236647746"],"related_works":["https://openalex.org/W2082054933","https://openalex.org/W2794896638","https://openalex.org/W1807784185","https://openalex.org/W4390905871","https://openalex.org/W3202800081","https://openalex.org/W1909207154","https://openalex.org/W3124390867","https://openalex.org/W3101614107","https://openalex.org/W3204228978","https://openalex.org/W1514365828"],"abstract_inverted_index":{"Ensemble":[0],"methods":[1,39],"have":[2,11],"become":[3],"popular":[4],"for":[5],"QSAR":[6],"modeling,":[7],"but":[8],"most":[9],"studies":[10],"assumed":[12],"balanced":[13],"data,":[14],"consisting":[15],"of":[16,20,37,43,45],"approximately":[17],"equal":[18],"numbers":[19],"active":[21],"and":[22,48,77],"inactive":[23],"compounds.":[24],"Cheminformatics":[25],"data":[26,84],"are":[27],"often":[28],"far":[29],"from":[30,82],"being":[31],"balanced.":[32],"We":[33],"extend":[34],"the":[35,57,69,79,88],"application":[36],"ensemble":[38,62,90],"to":[40,49,73],"include":[41],"cases":[42],"imbalance":[44],"class":[46],"membership":[47],"more":[50],"adequately":[51],"assess":[52],"model":[53],"output.":[54],"Based":[55],"on":[56,94],"extension,":[58],"we":[59],"propose":[60],"an":[61],"method":[63],"called":[64],"MBEnsemble":[65],"that":[66,87],"automatically":[67],"determines":[68],"appropriate":[70],"tuning":[71],"parameters":[72],"provide":[74],"reliable":[75],"predictions":[76],"maximize":[78],"F-measure.":[80],"Results":[81],"multiple":[83],"sets":[85],"demonstrate":[86],"proposed":[89],"technique":[91],"works":[92],"well":[93],"imbalanced":[95],"data.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
