{"id":"https://openalex.org/W2120921048","doi":"https://doi.org/10.1186/2043-9113-2-13","title":"Splitting random forest (SRF) for determining compact sets of genes that distinguish between cancer subtypes","display_name":"Splitting random forest (SRF) for determining compact sets of genes that distinguish between cancer subtypes","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2120921048","doi":"https://doi.org/10.1186/2043-9113-2-13","mag":"2120921048","pmid":"https://pubmed.ncbi.nlm.nih.gov/22616791"},"language":"en","primary_location":{"id":"doi:10.1186/2043-9113-2-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2043-9113-2-13","pdf_url":"https://jclinbioinformatics.biomedcentral.com/counter/pdf/10.1186/2043-9113-2-13","source":{"id":"https://openalex.org/S141199735","display_name":"Journal of Clinical Bioinformatics","issn_l":"2043-9113","issn":["2043-9113"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Clinical Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://jclinbioinformatics.biomedcentral.com/counter/pdf/10.1186/2043-9113-2-13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109365550","display_name":"Xiaowei Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108791","display_name":"University Hospitals Cleveland Medical Center","ror":"https://ror.org/01gc0wp38","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799343972","https://openalex.org/I4210108791"]},{"id":"https://openalex.org/I4390039247","display_name":"Case Comprehensive Cancer Center","ror":"https://ror.org/00fpjq451","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4390039247","https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaowei Guan","raw_affiliation_strings":["Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA. jsb42@case.edu","Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA. jsb42@case.edu","institution_ids":["https://openalex.org/I4210108791"]},{"raw_affiliation_string":"Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA","institution_ids":["https://openalex.org/I4390039247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071940002","display_name":"Mark R. Chance","orcid":"https://orcid.org/0000-0002-2991-6405"},"institutions":[{"id":"https://openalex.org/I4210095809","display_name":"Abterra Biosciences (United States)","ror":"https://ror.org/00wvn7664","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095809"]},{"id":"https://openalex.org/I4390039247","display_name":"Case Comprehensive Cancer Center","ror":"https://ror.org/00fpjq451","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4390039247","https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark R Chance","raw_affiliation_strings":["Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA","Center for Proteomics and Bioinformatics, 10900 Euclid Ave., BRB 930, Cleveland, OH, 44106-4988, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA","institution_ids":["https://openalex.org/I4390039247"]},{"raw_affiliation_string":"Center for Proteomics and Bioinformatics, 10900 Euclid Ave., BRB 930, Cleveland, OH, 44106-4988, USA","institution_ids":["https://openalex.org/I4210095809"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051948022","display_name":"Jill S. Barnholtz\u2010Sloan","orcid":"https://orcid.org/0000-0001-6190-9304"},"institutions":[{"id":"https://openalex.org/I4210095809","display_name":"Abterra Biosciences (United States)","ror":"https://ror.org/00wvn7664","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095809"]},{"id":"https://openalex.org/I4390039247","display_name":"Case Comprehensive Cancer Center","ror":"https://ror.org/00fpjq451","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4390039247","https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jill S Barnholtz-Sloan","raw_affiliation_strings":["Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA","Center for Proteomics and Bioinformatics, 10900 Euclid Ave., BRB 930, Cleveland, OH, 44106-4988, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Comprehensive Cancer Center, 11100 Euclid Avenue, Cleveland, OH, USA","institution_ids":["https://openalex.org/I4390039247"]},{"raw_affiliation_string":"Center for Proteomics and Bioinformatics, 10900 Euclid Ave., BRB 930, Cleveland, OH, 44106-4988, USA","institution_ids":["https://openalex.org/I4210095809"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051948022"],"corresponding_institution_ids":["https://openalex.org/I4210095809","https://openalex.org/I4390039247"],"apc_list":null,"apc_paid":null,"fwci":0.9679,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79615614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":"1","first_page":"13","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11297","display_name":"Ferroptosis and cancer prognosis","score":0.4507000148296356,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11297","display_name":"Ferroptosis and cancer prognosis","score":0.4507000148296356,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.16200000047683716,"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":0.13600000739097595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7975748777389526},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5472450256347656},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.49762848019599915},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.36866295337677},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33981502056121826},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.33880698680877686},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3182171583175659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2546190023422241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2411201298236847}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7975748777389526},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5472450256347656},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49762848019599915},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.36866295337677},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33981502056121826},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.33880698680877686},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3182171583175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2546190023422241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2411201298236847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/2043-9113-2-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2043-9113-2-13","pdf_url":"https://jclinbioinformatics.biomedcentral.com/counter/pdf/10.1186/2043-9113-2-13","source":{"id":"https://openalex.org/S141199735","display_name":"Journal of Clinical Bioinformatics","issn_l":"2043-9113","issn":["2043-9113"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Clinical Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22616791","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22616791","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 clinical bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:2448489","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3444418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/2043-9113-2-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2043-9113-2-13","pdf_url":"https://jclinbioinformatics.biomedcentral.com/counter/pdf/10.1186/2043-9113-2-13","source":{"id":"https://openalex.org/S141199735","display_name":"Journal of Clinical Bioinformatics","issn_l":"2043-9113","issn":["2043-9113"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Clinical Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.75,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G1603508747","display_name":null,"funder_award_id":"P30 CA043703","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G4637436490","display_name":null,"funder_award_id":"CA043703","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G5822270753","display_name":null,"funder_award_id":"CA043703","funder_id":"https://openalex.org/F4320310595","funder_display_name":"Case Comprehensive Cancer Center, Case Western Reserve University"},{"id":"https://openalex.org/G7107337173","display_name":null,"funder_award_id":"P30-CA043703","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320310595","display_name":"Case Comprehensive Cancer Center, Case Western Reserve University","ror":"https://ror.org/051fd9666"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2120921048.pdf","grobid_xml":"https://content.openalex.org/works/W2120921048.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1510554288","https://openalex.org/W1520812622","https://openalex.org/W1546709038","https://openalex.org/W1565487242","https://openalex.org/W1884926395","https://openalex.org/W1969761972","https://openalex.org/W1994191702","https://openalex.org/W2055475004","https://openalex.org/W2092918255","https://openalex.org/W2108819945","https://openalex.org/W2113942802","https://openalex.org/W2114292508","https://openalex.org/W2115380778","https://openalex.org/W2119387367","https://openalex.org/W2119862467","https://openalex.org/W2122769974","https://openalex.org/W2125697820","https://openalex.org/W2127823872","https://openalex.org/W2129463704","https://openalex.org/W2131593373","https://openalex.org/W2131994307","https://openalex.org/W2132619562","https://openalex.org/W2135046866","https://openalex.org/W2148564254","https://openalex.org/W2150638747","https://openalex.org/W2151240681","https://openalex.org/W2156711378","https://openalex.org/W2157795344","https://openalex.org/W2157840751","https://openalex.org/W2160697532","https://openalex.org/W2161289668","https://openalex.org/W2477400917","https://openalex.org/W2911964244","https://openalex.org/W2913846351","https://openalex.org/W3085162807","https://openalex.org/W4285719527","https://openalex.org/W4294107304"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3193043704","https://openalex.org/W3171520305","https://openalex.org/W1924178503","https://openalex.org/W4308716060","https://openalex.org/W4280648719","https://openalex.org/W3135126032","https://openalex.org/W4386937079","https://openalex.org/W2034625591"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,58,70,101,129,260],"identification":[2],"of":[3,7,214,267,275],"very":[4],"small":[5],"subsets":[6],"predictive":[8,28],"variables":[9],"is":[10,60,263],"an":[11,264],"important":[12,215],"to\u03c0c":[13],"that":[14,53,208,271,295],"has":[15],"not":[16],"often":[17],"been":[18],"considered":[19],"in":[20,169,190,225],"the":[21,63,149,211,223,229,273,292],"literature.":[22],"In":[23],"order":[24],"to":[25,49,61,93],"discover":[26],"highly":[27],"yet":[29],"compact":[30,109],"gene":[31,76,110,127,205,216],"set":[32],"classifiers":[33,77],"from":[34,95],"whole":[35],"genome":[36],"expression":[37],"data,":[38],"a":[39],"non-parametric,":[40],"iterative":[41],"algorithm,":[42],"Splitting":[43],"Random":[44],"Forest":[45],"(SRF),":[46],"was":[47,198],"developed":[48],"robustly":[50],"identify":[51],"genes":[52,122,227,233,276],"distinguish":[54],"between":[55,115,201,228],"molecular":[56],"subtypes.":[57,298],"goal":[59],"improve":[62],"prediction":[64,90,139],"accuracy":[65],"while":[66],"considering":[67],"sparsity.":[68],"RESULTS:":[69],"optimal":[71],"SRF":[72,209,261],"50":[73,151,194],"run":[74],"(SRF50)":[75],"for":[78,113,157,162,167,178,183,188,241,248,257,278],"glioblastoma":[79],"(GB),":[80],"breast":[81],"(BC)":[82],"and":[83,134,137,148,203,231,239,246,250,255,287],"ovarian":[84],"cancer":[85,117,297],"(OC)":[86],"subtypes":[87,118],"had":[88],"overall":[89,136],"rates":[91],"comparable":[92],"those":[94],"published":[96,126,204,232],"datasets":[97],"upon":[98],"validation":[99],"(80.1%-91.7%).":[100],"SRF50":[102,130,170,191,202,230],"sets":[103,111,131,234],"outperformed":[104],"other":[105],"methods":[106],"by":[107],"identifying":[108],"needed":[112,277],"distinguishing":[114],"tested":[116],"(10-200":[119],"fold":[120],"fewer":[121],"than":[123],"ANOVA":[124,152,195],"or":[125],"sets).":[128],"achieved":[132],"superior":[133],"robust":[135,279],"subtype":[138],"accuracies":[140],"when":[141],"compared":[142],"with":[143],"single":[144,172],"random":[145],"forest":[146],"(RF)":[147],"Top":[150,193],"results":[153],"(80.1%":[154],"vs":[155,160,165,171,176,181,186,192],"77.8%":[156],"GB;":[158,179,242],"84.0%":[159,180],"74.1%":[161],"BC;":[163,184,249],"89.8%":[164,185],"88.9%":[166],"OC":[168,189],"RF":[173],"comparison;":[174],"80.1%":[175],"77.2%":[177],"82.7%":[182],"87.0%":[187],"comparison).":[196],"There":[197],"significant":[199],"overlap":[200,224],"sets,":[206],"showing":[207],"identifies":[210],"relevant":[212],"sub-sets":[213],"lists.":[217],"Through":[218],"Ingenuity":[219],"Pathway":[220],"Analysis":[221],"(IPA),":[222],"\"hub\"":[226],"were":[235],"RB1,":[236],"\u03c0K3R1,":[237],"PDGFBB":[238,254],"ERK1/2":[240,247,256],"ESR1,":[243],"MYC,":[244],"NFkB":[245],"Akt,":[251],"FN1,":[252],"NFkB,":[253],"OC.":[258],"CONCLUSIONS:":[259],"approach":[262],"effective":[265],"driver":[266],"biomarker":[268],"discovery":[269],"research":[270],"reduces":[272],"number":[274],"classification,":[280],"dissects":[281],"complex,":[282],"high":[283],"dimensional":[284],"\"omic\"":[285],"data":[286],"provides":[288],"novel":[289],"insights":[290],"into":[291],"cellular":[293],"mechanisms":[294],"define":[296]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}