{"id":"https://openalex.org/W2043175314","doi":"https://doi.org/10.1093/bioinformatics/btn356","title":"Enriched random forests","display_name":"Enriched random forests","publication_year":2008,"publication_date":"2008-07-22","ids":{"openalex":"https://openalex.org/W2043175314","doi":"https://doi.org/10.1093/bioinformatics/btn356","mag":"2043175314","pmid":"https://pubmed.ncbi.nlm.nih.gov/18650208"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn356","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn356","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/18/2010/49051677/bioinformatics_24_18_2010.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/18/2010/49051677/bioinformatics_24_18_2010.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045560880","display_name":"Dhammika Amaratunga","orcid":"https://orcid.org/0000-0001-8293-5042"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I1330063522","display_name":"Johnson & Johnson (United States)","ror":"https://ror.org/03qd7mz70","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522"]},{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Dhammika Amaratunga","raw_affiliation_strings":["1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea","institution_ids":["https://openalex.org/I1330063522","https://openalex.org/I102322142","https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432250","display_name":"Javier Cabrera","orcid":"https://orcid.org/0009-0000-9771-0786"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I1330063522","display_name":"Johnson & Johnson (United States)","ror":"https://ror.org/03qd7mz70","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522"]},{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Javier Cabrera","raw_affiliation_strings":["1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea","institution_ids":["https://openalex.org/I1330063522","https://openalex.org/I102322142","https://openalex.org/I205490536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020680387","display_name":"Yung-Seop Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1330063522","display_name":"Johnson & Johnson (United States)","ror":"https://ror.org/03qd7mz70","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522"]},{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Yung-Seop Lee","raw_affiliation_strings":["1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"1 Department of Nonclinical Biostatistics, Johnson & Johnson PRD LLC, Raritan, NJ 08869, 2Department of Statistics, Rutgers University, 110 Frelinghuysen Ave, Piscataway, NJ 08854, USA and 3Department of Statistics, Dongguk University, Seoul, South Korea","institution_ids":["https://openalex.org/I1330063522","https://openalex.org/I102322142","https://openalex.org/I205490536"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045560880"],"corresponding_institution_ids":["https://openalex.org/I102322142","https://openalex.org/I1330063522","https://openalex.org/I205490536"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.0297,"has_fulltext":false,"cited_by_count":228,"citation_normalized_percentile":{"value":0.91509596,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"24","issue":"18","first_page":"2010","last_page":"2014"},"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":0.995199978351593,"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/T10057","display_name":"Face and Expression Recognition","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8704804182052612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254539728164673},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.6974732875823975},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5980412364006042},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5214375853538513},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49932098388671875},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.48933666944503784},{"id":"https://openalex.org/keywords/systematic-sampling","display_name":"Systematic sampling","score":0.4413539171218872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3819437623023987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37691470980644226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33030474185943604},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3210393190383911},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21405425667762756}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8704804182052612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254539728164673},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.6974732875823975},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5980412364006042},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5214375853538513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49932098388671875},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48933666944503784},{"id":"https://openalex.org/C192489979","wikidata":"https://www.wikidata.org/wiki/Q1502997","display_name":"Systematic sampling","level":2,"score":0.4413539171218872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3819437623023987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37691470980644226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33030474185943604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3210393190383911},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21405425667762756},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":"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":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"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":"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/btn356","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn356","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/18/2010/49051677/bioinformatics_24_18_2010.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18650208","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18650208","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:alma.01RUT_INST:11675307420004646","is_oa":false,"landing_page_url":"https://scholarship.libraries.rutgers.edu/esploro/outputs/journalArticle/Enriched-random-forests/991031714587004646","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn356","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn356","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/18/2010/49051677/bioinformatics_24_18_2010.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.7599999904632568,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332194","display_name":"Johnson and Johnson","ror":"https://ror.org/03qd7mz70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2043175314.pdf","grobid_xml":"https://content.openalex.org/works/W2043175314.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1480754351","https://openalex.org/W1513110684","https://openalex.org/W1520812622","https://openalex.org/W1875061881","https://openalex.org/W1964895626","https://openalex.org/W1966701961","https://openalex.org/W1994401189","https://openalex.org/W2024884447","https://openalex.org/W2050088498","https://openalex.org/W2081098333","https://openalex.org/W2092419054","https://openalex.org/W2092868756","https://openalex.org/W2095594899","https://openalex.org/W2112059892","https://openalex.org/W2123106337","https://openalex.org/W2144692687","https://openalex.org/W2148825532","https://openalex.org/W2168611920","https://openalex.org/W2413553870","https://openalex.org/W2416227286","https://openalex.org/W2495373072","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W4212883601"],"related_works":["https://openalex.org/W4238714840","https://openalex.org/W2381368487","https://openalex.org/W4253670017","https://openalex.org/W2350399852","https://openalex.org/W3047864323","https://openalex.org/W2994963386","https://openalex.org/W1036777753","https://openalex.org/W2383809451","https://openalex.org/W4379210352","https://openalex.org/W2370014976"],"abstract_inverted_index":{"Although":[0],"the":[1,14,21,44,51,85,101,107,119],"random":[2,93,98,115],"forest":[3],"classification":[4],"procedure":[5,45,124],"works":[6],"well":[7],"in":[8,104,112,125],"datasets":[9],"with":[10,31,100],"many":[11],"features,":[12],"when":[13],"number":[15],"of":[16,23,53,96,106,122],"features":[17,26],"is":[18,27],"huge":[19],"and":[20],"percentage":[22],"truly":[24],"informative":[25,108],"small,":[28],"such":[29,42],"as":[30],"DNA":[32],"microarray":[33,128],"data,":[34],"its":[35],"performance":[36,121],"tends":[37],"to":[38],"decline":[39],"significantly.":[40],"In":[41],"instances,":[43],"can":[46,66],"be":[47,67],"improved":[48],"by":[49,59,69,91],"reducing":[50],"contribution":[52],"trees":[54],"whose":[55],"nodes":[56],"are":[57],"populated":[58],"non-informative":[60],"features.":[61,109],"To":[62],"some":[63],"extent,":[64],"this":[65,123],"achieved":[68],"prefiltering,":[70],"but":[71],"we":[72],"propose":[73],"a":[74],"novel,":[75],"yet":[76],"simple,":[77],"adjustment":[78],"that":[79],"has":[80],"demonstrably":[81],"superior":[82,120],"performance:":[83],"choose":[84],"eligible":[86],"subsets":[87],"at":[88],"each":[89],"node":[90],"weighted":[92],"sampling":[94],"instead":[95],"simple":[97],"sampling,":[99],"weights":[102],"tilted":[103],"favor":[105],"This":[110],"results":[111],"an":[113],"'enriched":[114],"forest'.":[116],"We":[117],"illustrate":[118],"several":[126],"actual":[127],"datasets.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
