{"id":"https://openalex.org/W2024587346","doi":"https://doi.org/10.1021/ci049933v","title":"Evaluation of Mutual Information and Genetic Programming for Feature Selection in QSAR","display_name":"Evaluation of Mutual Information and Genetic Programming for Feature Selection in QSAR","publication_year":2004,"publication_date":"2004-08-11","ids":{"openalex":"https://openalex.org/W2024587346","doi":"https://doi.org/10.1021/ci049933v","mag":"2024587346","pmid":"https://pubmed.ncbi.nlm.nih.gov/15446827"},"language":"en","primary_location":{"id":"doi:10.1021/ci049933v","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci049933v","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","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/A5091560329","display_name":"Vishwesh Venkatraman","orcid":"https://orcid.org/0000-0001-7609-2245"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vishwesh Venkatraman","raw_affiliation_strings":["School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010512127","display_name":"Andrew Dalby","orcid":"https://orcid.org/0000-0002-3598-8595"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Rowland Dalby","raw_affiliation_strings":["School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101837304","display_name":"Zheng Rong Yang","orcid":"https://orcid.org/0000-0002-6733-7893"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zheng Rong Yang","raw_affiliation_strings":["School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Sciences, University of Exeter, Exeter EX4 4QF, Great Britain and School of Engineering and Computer Science, University of Exeter, Exeter EX4 4QF, Great Britain","institution_ids":["https://openalex.org/I23923803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101837304"],"corresponding_institution_ids":["https://openalex.org/I23923803"],"apc_list":null,"apc_paid":null,"fwci":3.1153,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.91130032,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"44","issue":"5","first_page":"1686","last_page":"1692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T11882","display_name":"Plant biochemistry and biosynthesis","score":0.9397000074386597,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9351000189781189,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8743534088134766},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7790678143501282},{"id":"https://openalex.org/keywords/multicollinearity","display_name":"Multicollinearity","score":0.6104851961135864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6001769304275513},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5363932847976685},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5198712348937988},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.5191937685012817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5157883167266846},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5018105506896973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4866862893104553},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4662591218948364},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4162712097167969},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.1670415997505188}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8743534088134766},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7790678143501282},{"id":"https://openalex.org/C189285262","wikidata":"https://www.wikidata.org/wiki/Q1332350","display_name":"Multicollinearity","level":3,"score":0.6104851961135864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6001769304275513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5363932847976685},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5198712348937988},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.5191937685012817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5157883167266846},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5018105506896973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4866862893104553},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4662591218948364},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4162712097167969},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.1670415997505188},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005075","descriptor_name":"Biological Evolution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005075","descriptor_name":"Biological Evolution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005075","descriptor_name":"Biological Evolution","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}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci049933v","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci049933v","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","raw_type":"journal-article"},{"id":"pmid:15446827","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15446827","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 computer sciences","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1491190782","https://openalex.org/W1495061682","https://openalex.org/W1574715085","https://openalex.org/W1589190360","https://openalex.org/W1972266664","https://openalex.org/W1996346862","https://openalex.org/W2002503643","https://openalex.org/W2016164337","https://openalex.org/W2020947919","https://openalex.org/W2042423435","https://openalex.org/W2046653925","https://openalex.org/W2060336576","https://openalex.org/W2067582939","https://openalex.org/W2069116068","https://openalex.org/W2079225934","https://openalex.org/W2099111195","https://openalex.org/W2133072013","https://openalex.org/W2136241053","https://openalex.org/W2152121191","https://openalex.org/W2165618135","https://openalex.org/W2317912355","https://openalex.org/W2337094998","https://openalex.org/W2590187634","https://openalex.org/W3004042307","https://openalex.org/W3023540311","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W1652841952","https://openalex.org/W2997083166","https://openalex.org/W2086424613","https://openalex.org/W3037363193","https://openalex.org/W2533731304","https://openalex.org/W2386078281","https://openalex.org/W3111660818","https://openalex.org/W4287553507","https://openalex.org/W2069321575","https://openalex.org/W1770458422"],"abstract_inverted_index":{"Feature":[0],"selection":[1],"is":[2,127],"a":[3,84],"key":[4],"step":[5,44],"in":[6,32],"Quantitative":[7],"Structure":[8],"Activity":[9],"Relationship":[10],"(QSAR)":[11],"analysis.":[12],"Chance":[13],"correlations":[14],"and":[15,52,110,139,147],"multicollinearity":[16],"are":[17],"two":[18],"major":[19],"problems":[20],"often":[21],"encountered":[22],"when":[23],"attempting":[24],"to":[25,70,74,129,142],"find":[26,71],"generalized":[27],"QSAR":[28,36,89],"models":[29,37],"for":[30,45,87],"use":[31],"drug":[33],"design.":[34],"Optimal":[35],"require":[38],"an":[39],"objective":[40],"variable":[41],"relevance":[42],"analysis":[43],"producing":[46],"robust":[47],"classifiers":[48],"with":[49,59,97],"low":[50],"complexity":[51],"good":[53],"predictive":[54],"accuracy.":[55],"Genetic":[56],"algorithms":[57],"coupled":[58],"information":[60,66],"theoretic":[61],"approaches":[62],"such":[63,75],"as":[64,103],"mutual":[65],"have":[67],"been":[68,123],"used":[69],"near-optimal":[72],"solutions":[73],"multicriteria":[76],"optimization":[77],"problems.":[78],"In":[79],"this":[80,119],"paper,":[81],"we":[82],"describe":[83],"novel":[85],"approach":[86],"analyzing":[88],"data":[90,134],"based":[91],"on":[92],"these":[93],"methods.":[94],"Our":[95],"experiments":[96],"the":[98,106,116,133,136,140],"Thrombin":[99],"dataset,":[100],"previously":[101],"studied":[102],"part":[104],"of":[105,118,150],"KDD":[107],"(Knowledge":[108],"Discovery":[109],"Data":[111],"Mining)":[112],"Cup":[113],"2001":[114],"demonstrate":[115],"feasibility":[117],"approach.":[120],"It":[121],"has":[122],"found":[124],"that":[125],"it":[126],"important":[128],"take":[130],"into":[131],"account":[132],"distribution,":[135],"rule":[137],"\"interestingness\",":[138],"need":[141],"look":[143],"at":[144],"more":[145],"invariant":[146],"monotonic":[148],"measures":[149],"feature":[151],"selection.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}