{"id":"https://openalex.org/W2107208924","doi":"https://doi.org/10.1093/bioinformatics/btg038","title":"Bagging to improve the accuracy of a clustering procedure","display_name":"Bagging to improve the accuracy of a clustering procedure","publication_year":2003,"publication_date":"2003-06-11","ids":{"openalex":"https://openalex.org/W2107208924","doi":"https://doi.org/10.1093/bioinformatics/btg038","mag":"2107208924","pmid":"https://pubmed.ncbi.nlm.nih.gov/12801869"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg038","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg038","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5018207168","display_name":"Sandrine Dudoit","orcid":"https://orcid.org/0000-0002-6069-8629"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sandrine Dudoit","raw_affiliation_strings":["Division of Biostatistics, School of Public Health, University of California, Berkeley, 140 Earl Warren Hall, 7360, Berkeley, CA 94720-7360, USA. sandrine@stat.berkeley.edu","Division of Biostatistics, School of Public Health, University of California, Berkeley, 140 Earl Warren Hall, 7360, Berkeley, CA 94720-7360, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biostatistics, School of Public Health, University of California, Berkeley, 140 Earl Warren Hall, 7360, Berkeley, CA 94720-7360, USA. sandrine@stat.berkeley.edu","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Division of Biostatistics, School of Public Health, University of California, Berkeley, 140 Earl Warren Hall, 7360, Berkeley, CA 94720-7360, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080124702","display_name":"Jane Fridlyand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane Fridlyand","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018207168"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":8.878,"has_fulltext":false,"cited_by_count":526,"citation_normalized_percentile":{"value":0.98701068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"19","issue":"9","first_page":"1090","last_page":"1099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9998999834060669,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9998999834060669,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9811999797821045,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8504059314727783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301671504974365},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6631491184234619},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5713700652122498},{"id":"https://openalex.org/keywords/bioconductor","display_name":"Bioconductor","score":0.4910028278827667},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.489881694316864},{"id":"https://openalex.org/keywords/bootstrap-aggregating","display_name":"Bootstrap aggregating","score":0.41274696588516235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3946415185928345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39442554116249084}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8504059314727783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301671504974365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6631491184234619},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5713700652122498},{"id":"https://openalex.org/C2779694297","wikidata":"https://www.wikidata.org/wiki/Q2888953","display_name":"Bioconductor","level":3,"score":0.4910028278827667},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.489881694316864},{"id":"https://openalex.org/C162040801","wikidata":"https://www.wikidata.org/wiki/Q799897","display_name":"Bootstrap aggregating","level":2,"score":0.41274696588516235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946415185928345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39442554116249084},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008545","descriptor_name":"Melanoma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008545","descriptor_name":"Melanoma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008545","descriptor_name":"Melanoma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btg038","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg038","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:12801869","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12801869","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.3409","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.3409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/19/9/1090.full.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1651215666","https://openalex.org/W1886306325","https://openalex.org/W1966701961","https://openalex.org/W1988790447","https://openalex.org/W1989076816","https://openalex.org/W2087684630","https://openalex.org/W2109363337","https://openalex.org/W2147246240","https://openalex.org/W2155612034","https://openalex.org/W2156643308","https://openalex.org/W2912934387","https://openalex.org/W2999729612","https://openalex.org/W3203165331"],"related_works":["https://openalex.org/W2139161003","https://openalex.org/W2138743260","https://openalex.org/W2068765483","https://openalex.org/W2068365353","https://openalex.org/W1842073544","https://openalex.org/W2285673905","https://openalex.org/W2022891205","https://openalex.org/W1991849007","https://openalex.org/W1796883164","https://openalex.org/W4388110378"],"abstract_inverted_index":{"For":[0],"supplementary":[1],"information":[2],"on":[3],"datasets,":[4],"analyses,":[5],"and":[6,10],"software,":[7],"consult":[8],"http://www.stat.berkeley.edu/~sandrine":[9],"http://www.bioconductor.org.":[11]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":29}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
