{"id":"https://openalex.org/W2067818689","doi":"https://doi.org/10.1021/ci049850e","title":"Ensemble Methods for Classification in Cheminformatics","display_name":"Ensemble Methods for Classification in Cheminformatics","publication_year":2004,"publication_date":"2004-10-13","ids":{"openalex":"https://openalex.org/W2067818689","doi":"https://doi.org/10.1021/ci049850e","mag":"2067818689","pmid":"https://pubmed.ncbi.nlm.nih.gov/15554666"},"language":"en","primary_location":{"id":"doi:10.1021/ci049850e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci049850e","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/A5046889814","display_name":"Christian Merkwirth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH","DE"],"is_corresponding":true,"raw_author_name":"Christian Merkwirth","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068601205","display_name":"Harald Mauser","orcid":null},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["CH","DE"],"is_corresponding":false,"raw_author_name":"Harald Mauser","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059481994","display_name":"Tanja Schulz\u2010Gasch","orcid":null},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["CH","DE"],"is_corresponding":false,"raw_author_name":"Tanja Schulz-Gasch","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048937740","display_name":"Olivier Roche","orcid":"https://orcid.org/0000-0002-6751-6904"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH","DE"],"is_corresponding":false,"raw_author_name":"Olivier Roche","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074020921","display_name":"Martin St\u00e5hl","orcid":"https://orcid.org/0000-0002-6984-360X"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH","DE"],"is_corresponding":false,"raw_author_name":"Martin Stahl","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023556977","display_name":"Thomas Lengauer","orcid":"https://orcid.org/0000-0003-3801-2640"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH","DE"],"is_corresponding":false,"raw_author_name":"Thomas Lengauer","raw_affiliation_strings":["Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computational Biology & Applied Algorithmics Group, Max-Planck-Institut f\u00fcr Informatik, Stuhlsatzenhauseg 85, 66123 Saarbr\u00fccken, Germany, and Roche Pharma Research, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046889814"],"corresponding_institution_ids":["https://openalex.org/I118019719","https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":2.4117,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.88448423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"44","issue":"6","first_page":"1971","last_page":"1978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9926000237464905,"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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9926000237464905,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9914000034332275,"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":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.9641611576080322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4874603748321533},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.46018582582473755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45135390758514404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40870606899261475},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.21367907524108887},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.1305120587348938}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9641611576080322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4874603748321533},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.46018582582473755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45135390758514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40870606899261475},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21367907524108887},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.1305120587348938}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1021/ci049850e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci049850e","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:15554666","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15554666","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.730","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cbio.ensmp.fr/~jvert/svn/bibli/local/Merkwirth2004Ensemble.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:231291","is_oa":false,"landing_page_url":"http://edoc.mpg.de/231291","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Modeling, v.44, 1971-1978 (2004)","raw_type":"Article"},{"id":"pmh:oai:edoc.mpg.de:231982","is_oa":false,"landing_page_url":"http://edoc.mpg.de/231982","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Modeling, v.44, 1971-1978 (2004)","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_1329408","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-29A9-A","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1491993603","https://openalex.org/W1580948147","https://openalex.org/W1622484071","https://openalex.org/W1991537916","https://openalex.org/W1991615245","https://openalex.org/W2017670951","https://openalex.org/W2019274391","https://openalex.org/W2020530004","https://openalex.org/W2048312836","https://openalex.org/W2062338388","https://openalex.org/W2063379654","https://openalex.org/W2114196051","https://openalex.org/W2128073546","https://openalex.org/W2145073242","https://openalex.org/W2153635508","https://openalex.org/W2154183412","https://openalex.org/W2156909104","https://openalex.org/W2165618135","https://openalex.org/W2912934387","https://openalex.org/W4230674625"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"We":[0,79],"describe":[1],"the":[2,84,89,104],"application":[3],"of":[4,19,24,60,96],"ensemble":[5],"methods":[6,40],"to":[7,82,99],"binary":[8],"classification":[9,43,75],"problems":[10],"on":[11],"two":[12,53],"pharmaceutical":[13],"compound":[14],"data":[15,54,106],"sets.":[16],"Several":[17],"variants":[18],"single":[20,33],"and":[21,32,66],"ensembles":[22],"models":[23,36],"k-nearest":[25],"neighbors":[26],"classifiers,":[27],"support":[28],"vector":[29],"machines":[30],"(SVMs),":[31],"ridge":[34],"regression":[35],"are":[37,48,80],"compared.":[38],"All":[39],"exhibit":[41],"robust":[42],"even":[44],"when":[45],"more":[46],"features":[47],"given":[49],"than":[50],"observations.":[51],"On":[52],"sets":[55],"dealing":[56],"with":[57,108],"specific":[58],"properties":[59],"drug-like":[61],"substances":[62],"(cytochrome":[63],"P450":[64],"inhibition":[65],"\"Frequent":[67],"Hitters\",":[68],"i.e.,":[69],"unspecific":[70],"protein":[71],"inhibition),":[72],"we":[73],"achieve":[74],"rates":[76],"above":[77],"90%.":[78],"able":[81],"reduce":[83],"cross-validated":[85],"misclassification":[86],"rate":[87],"for":[88,103],"Frequent":[90],"Hitters":[91],"problem":[92],"by":[93],"a":[94],"factor":[95],"2":[97],"compared":[98],"previous":[100],"results":[101],"obtained":[102],"same":[105],"set":[107],"different":[109],"modeling":[110],"techniques.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
