{"id":"https://openalex.org/W2205415869","doi":"https://doi.org/10.1021/ci600563w","title":"Ensemble Feature Selection:\u2009 Consistent Descriptor Subsets for Multiple QSAR Models","display_name":"Ensemble Feature Selection:\u2009 Consistent Descriptor Subsets for Multiple QSAR Models","publication_year":2007,"publication_date":"2007-04-04","ids":{"openalex":"https://openalex.org/W2205415869","doi":"https://doi.org/10.1021/ci600563w","mag":"2205415869","pmid":"https://pubmed.ncbi.nlm.nih.gov/17407280"},"language":"en","primary_location":{"id":"doi:10.1021/ci600563w","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600563w","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/A5113845539","display_name":"Debojyoti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debojyoti Dutta","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069062997","display_name":"Rajarshi Guha","orcid":"https://orcid.org/0000-0001-7403-8819"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajarshi Guha","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002092202","display_name":"David Wild","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Wild","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, Indiana 47406, and Department of Computational Biology, University of Southern California Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069062997"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":5.3383,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96503163,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"47","issue":"3","first_page":"989","last_page":"997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9905999898910522,"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"}},"topics":[{"id":"https://openalex.org/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9905999898910522,"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/T10057","display_name":"Face and Expression Recognition","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7294087409973145},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.6702941060066223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5563362836837769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496019124984741},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5405295491218567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45275190472602844},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39018332958221436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38386255502700806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36279261112213135},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2130623161792755}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7294087409973145},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.6702941060066223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5563362836837769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496019124984741},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5405295491218567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45275190472602844},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39018332958221436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38386255502700806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36279261112213135},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2130623161792755},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010982","descriptor_name":"Platelet-Derived Growth Factor","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D010982","descriptor_name":"Platelet-Derived Growth Factor","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D010982","descriptor_name":"Platelet-Derived Growth Factor","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","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":"D051546","descriptor_name":"Cyclooxygenase 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D051546","descriptor_name":"Cyclooxygenase 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D051546","descriptor_name":"Cyclooxygenase 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D052246","descriptor_name":"Cyclooxygenase 2 Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D065427","descriptor_name":"Factor Xa Inhibitors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D065427","descriptor_name":"Factor Xa Inhibitors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D065427","descriptor_name":"Factor Xa Inhibitors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci600563w","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600563w","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:17407280","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17407280","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4446475917","display_name":null,"funder_award_id":"P20 HG003894-01","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W421463624","https://openalex.org/W604621907","https://openalex.org/W1531520279","https://openalex.org/W1535113282","https://openalex.org/W1594730842","https://openalex.org/W1974187953","https://openalex.org/W1977405994","https://openalex.org/W1979934682","https://openalex.org/W1980019773","https://openalex.org/W1999846848","https://openalex.org/W2007066266","https://openalex.org/W2017337590","https://openalex.org/W2032389990","https://openalex.org/W2045886429","https://openalex.org/W2056593372","https://openalex.org/W2059889666","https://openalex.org/W2065382687","https://openalex.org/W2066273100","https://openalex.org/W2073993379","https://openalex.org/W2079179972","https://openalex.org/W2159667057","https://openalex.org/W3142152711","https://openalex.org/W4206803374","https://openalex.org/W4300819821"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1967793880","https://openalex.org/W2792066564","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Selecting":[0],"a":[1,7,12,52,62,70,113,137,181],"small":[2],"subset":[3,30,54,140],"of":[4,61,76,82,104,106,116,136,141,165,175,195],"descriptors":[5,117,142,176],"from":[6,101],"large":[8],"pool":[9],"to":[10,35,50,57,111,133,151,170,180],"build":[11],"predictive":[13,185],"quantitative":[14],"structure-activity":[15,208],"relationship":[16],"(QSAR)":[17],"model":[18,60,95,124,145,168],"is":[19,32,99],"an":[20,58,131],"important":[21],"step":[22],"in":[23,89,184],"the":[24,74,102,134,163,172,188,196],"QSAR":[25,109],"modeling":[26,78],"process.":[27],"In":[28,126,192],"general,":[29],"selection":[31,135],"very":[33],"hard":[34],"solve,":[36],"even":[37],"approximately,":[38],"with":[39],"guaranteed":[40],"performance":[41],"bounds.":[42],"Traditional":[43],"approaches":[44],"employ":[45],"deterministic":[46],"or":[47,69],"stochastic":[48],"methods":[49],"obtain":[51],"descriptor":[53,91],"that":[55,118,162,204],"leads":[56],"optimal":[59],"single":[63,114],"type":[64],"(such":[65],"as":[66],"linear":[67],"regression":[68,157],"neural":[71],"network).":[72],"With":[73],"development":[75],"ensemble":[77],"approaches,":[79],"multiple":[80,144],"models":[81,190,198],"differing":[83],"types":[84,169],"are":[85],"individually":[86],"developed":[87,199],"resulting":[88],"different":[90,123,167],"subsets":[92],"for":[93,122,143,187],"each":[94],"type.":[96],"However,":[97],"it":[98],"advantageous,":[100],"point":[103],"view":[105],"developing":[107],"interpretable":[108],"models,":[110],"have":[112],"set":[115,174],"can":[119],"be":[120],"used":[121],"types.":[125,146],"this":[127,149,201],"paper,":[128],"we":[129],"describe":[130],"approach":[132,150,202],"single,":[138],"optimal,":[139],"We":[147],"apply":[148],"three":[152],"data":[153],"sets,":[154],"covering":[155],"both":[156],"and":[158,160],"classification,":[159],"show":[161],"constraint":[164],"forcing":[166],"use":[171],"same":[173],"does":[177],"not":[178],"lead":[179],"significant":[182],"loss":[183],"ability":[186],"individual":[189,197],"considered.":[191],"addition,":[193],"interpretations":[194],"using":[200],"indicate":[203],"they":[205],"encode":[206],"similar":[207],"trends.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}