{"id":"https://openalex.org/W3171520305","doi":"https://doi.org/10.1109/tcbb.2021.3089417","title":"Enriched Random Forest for High Dimensional Genomic Data","display_name":"Enriched Random Forest for High Dimensional Genomic Data","publication_year":2021,"publication_date":"2021-06-15","ids":{"openalex":"https://openalex.org/W3171520305","doi":"https://doi.org/10.1109/tcbb.2021.3089417","mag":"3171520305","pmid":"https://pubmed.ncbi.nlm.nih.gov/34129502"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2021.3089417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3089417","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9923687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101982963","display_name":"Debopriya Ghosh","orcid":"https://orcid.org/0000-0001-8487-7894"},"institutions":[{"id":"https://openalex.org/I4210151386","display_name":"Janssen (United States)","ror":"https://ror.org/05af73403","country_code":"US","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I4210151386"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Debopriya Ghosh","raw_affiliation_strings":["Janssen Research and Development LLC, Raritan, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-8487-7894","affiliations":[{"raw_affiliation_string":"Janssen Research and Development LLC, Raritan, NJ, USA","institution_ids":["https://openalex.org/I4210151386"]}]},{"author_position":"last","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier Cabrera","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101982963"],"corresponding_institution_ids":["https://openalex.org/I4210151386"],"apc_list":null,"apc_paid":null,"fwci":4.4786,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":{"value":0.95974226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"19","issue":"5","first_page":"2817","last_page":"2828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9835000038146973,"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/T12676","display_name":"Machine Learning and ELM","score":0.9797999858856201,"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/random-forest","display_name":"Random forest","score":0.9689264893531799},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.7431708574295044},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6036466360092163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5648541450500488},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.520759105682373},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48911815881729126},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.42257213592529297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41257593035697937},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.34908729791641235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.328808456659317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3063523471355438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29908639192581177},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06764984130859375}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.9689264893531799},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.7431708574295044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6036466360092163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5648541450500488},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.520759105682373},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48911815881729126},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.42257213592529297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41257593035697937},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34908729791641235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328808456659317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3063523471355438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29908639192581177},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06764984130859375},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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":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":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tcbb.2021.3089417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3089417","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34129502","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34129502","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9923687","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9923687","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Comput Biol Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9923687","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9923687","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Comput Biol Bioinform","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.75,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G2572748579","display_name":null,"funder_award_id":"R01- HL150065","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W811317874","https://openalex.org/W1277945432","https://openalex.org/W1492273171","https://openalex.org/W1520812622","https://openalex.org/W1546989560","https://openalex.org/W1592785605","https://openalex.org/W2022604714","https://openalex.org/W2023611240","https://openalex.org/W2043175314","https://openalex.org/W2089898582","https://openalex.org/W2090436764","https://openalex.org/W2091374137","https://openalex.org/W2092419054","https://openalex.org/W2103291381","https://openalex.org/W2143426320","https://openalex.org/W2147272585","https://openalex.org/W2148825532","https://openalex.org/W2306302840","https://openalex.org/W2423455227","https://openalex.org/W2530623388","https://openalex.org/W2591165109","https://openalex.org/W2911964244","https://openalex.org/W6632791947","https://openalex.org/W6635383313"],"related_works":["https://openalex.org/W2370014976","https://openalex.org/W2350399852","https://openalex.org/W3047864323","https://openalex.org/W4238714840","https://openalex.org/W2383809451","https://openalex.org/W2381368487","https://openalex.org/W2994963386","https://openalex.org/W2367020632","https://openalex.org/W4230157703","https://openalex.org/W2298795098"],"abstract_inverted_index":{"Ensemble":[0],"methods":[1],"such":[2],"as":[3,86,104],"random":[4,39,57,84,90,94,101,155,163],"forest":[5,40,58,102,156],"works":[6],"well":[7],"on":[8],"high-dimensional":[9,110],"datasets.":[10],"However,":[11],"when":[12,166],"the":[13,22,27,53,61,115,131,150,158],"number":[14,23],"of":[15,24,29,37,55,63,117,133,161],"features":[16,168],"is":[17,33],"extremely":[18],"large":[19],"compared":[20],"to":[21,88,98,137],"samples":[25],"and":[26,123,141],"percentage":[28],"truly":[30],"informative":[31,71],"feature":[32,147],"very":[34,170],"small,":[35],"performance":[36,54,116],"traditional":[38,56,93,162],"decline":[41],"significantly.":[42],"To":[43],"this":[44,99],"end,":[45],"we":[46,113,128],"develop":[47],"a":[48],"novel":[49],"approach":[50,119],"that":[51,153],"enhance":[52],"by":[59,82],"reducing":[60],"contribution":[62],"trees":[64],"whose":[65],"nodes":[66],"are":[67,169],"populated":[68],"with":[69],"less":[70],"features.":[72],"The":[73],"proposed":[74],"method":[75],"selects":[76],"eligible":[77],"subsets":[78],"at":[79],"each":[80],"node":[81],"weighted":[83],"sampling":[85,91],"opposed":[87],"simple":[89],"in":[92,120],"forest.":[95],"We":[96],"refer":[97],"modified":[100],"algorithm":[103],"\"Enriched":[105],"Random":[106],"Forest\".":[107],"Using":[108],"several":[109],"micro-array":[111],"datasets,":[112],"evaluate":[114],"our":[118],"both":[121],"regression":[122],"classification":[124],"settings.":[125],"In":[126],"addition,":[127],"also":[129],"demonstrate":[130],"effectiveness":[132],"balanced":[134],"leave-one-out":[135],"cross-validation":[136],"reduce":[138],"computational":[139],"load":[140],"decrease":[142],"sample":[143],"size":[144],"while":[145],"computing":[146],"weights.":[148],"Overall,":[149],"results":[151],"indicate":[152],"enriched":[154],"improves":[157],"prediction":[159],"accuracy":[160],"forest,":[164],"especially":[165],"relevant":[167],"few.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":8}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}