{"id":"https://openalex.org/W110893188","doi":null,"title":"Finding Genes Related to Disease Using Statistical Learning","display_name":"Finding Genes Related to Disease Using Statistical Learning","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W110893188","mag":"110893188"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt2s4020fj","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2s4020fj","pdf_url":"https://escholarship.org/uc/item/2s4020fj","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/2s4020fj","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067727757","display_name":"Benjamin Alan Goldstein","orcid":"https://orcid.org/0000-0001-5261-3632","observed_orcids":["https://orcid.org/0000-0001-5261-3632"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Benjamin A. Goldstein","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5261-3632","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5067727757"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.006800000090152025,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10885","display_name":"Gene expression and cancer classification","score":0.0031999999191612005,"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/genetic-association","display_name":"genetic association","score":0.7889999747276306},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphisms","display_name":"single nucleotide polymorphisms","score":0.878000020980835},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.75},{"id":"https://openalex.org/keywords/multiple-sclerosis","display_name":"multiple sclerosis","score":0.7329999804496765},{"id":"https://openalex.org/keywords/genome-wide-association-data","display_name":"genome-wide association data","score":0.6470000147819519},{"id":"https://openalex.org/keywords/sparsity","display_name":"sparsity","score":0.531000018119812},{"id":"https://openalex.org/keywords/super-learner","display_name":"super learner","score":0.675000011920929},{"id":"https://openalex.org/keywords/wald-test","display_name":"Wald test","score":0.8119999766349792},{"id":"https://openalex.org/keywords/influence-function","display_name":"influence function","score":0.8320000171661377},{"id":"https://openalex.org/keywords/candidate-gene-studies","display_name":"candidate gene association","score":0.6679999828338623},{"id":"https://openalex.org/keywords/type-i-error-control","display_name":"type I error control","score":0.5699999928474426},{"id":"https://openalex.org/keywords/statistical-learning-algorithms","display_name":"statistical learning algorithms","score":0.6539999842643738},{"id":"https://openalex.org/keywords/breast-cancer","display_name":"breast cancer","score":0.382999986410141},{"id":"https://openalex.org/keywords/breast-cancer-subtypes","display_name":"breast cancer subtypes","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6050807237625122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5779590606689453},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5501195192337036},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.542330265045166},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.5174520611763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.498382568359375},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.4893278479576111},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.48620906472206116},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4744254946708679},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.4711538553237915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45629382133483887},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.44122177362442017},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.4399663507938385},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4145479202270508},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4014561176300049},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2258693277835846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19262179732322693},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.17459961771965027},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16262012720108032},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13882267475128174},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt2s4020fj","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2s4020fj","pdf_url":"https://escholarship.org/uc/item/2s4020fj","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},{"id":"pmh:qt2s4020fj","doi":null,"is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/2s4020fj","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Goldstein, Benjamin Alan. (2011). Finding Genes Related to Disease Using Statistical Learning. UC Berkeley: Biostatistics. Retrieved from: http://www.escholarship.org/uc/item/2s4020fj","raw_type":"dissertation"},{"id":"mag:110893188","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt2s4020fj/qt2s4020fj.pdf?t=mtfex5","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt2s4020fj","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/2s4020fj","pdf_url":"https://escholarship.org/uc/item/2s4020fj","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[{"score":0.5683000087738037,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000892114","display_name":"Berkeley Training Program in Genomics and Computational Biology","funder_award_id":"T32HG000047","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W110893188.pdf","grobid_xml":"https://content.openalex.org/works/W110893188.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W14944000","https://openalex.org/W98862427","https://openalex.org/W133122663","https://openalex.org/W1507255258","https://openalex.org/W1516193414","https://openalex.org/W1520812622","https://openalex.org/W1530689820","https://openalex.org/W1534477342","https://openalex.org/W1605688901","https://openalex.org/W1608401492","https://openalex.org/W1678131841","https://openalex.org/W1840338487","https://openalex.org/W1875061881","https://openalex.org/W1966525597","https://openalex.org/W1969482724","https://openalex.org/W1983364819","https://openalex.org/W1987971958","https://openalex.org/W1994130453","https://openalex.org/W2004811917","https://openalex.org/W2013577952","https://openalex.org/W2018331991","https://openalex.org/W2032481853","https://openalex.org/W2034500646","https://openalex.org/W2034900106","https://openalex.org/W2039634280","https://openalex.org/W2047081748","https://openalex.org/W2053360677","https://openalex.org/W2068852101","https://openalex.org/W2073738917","https://openalex.org/W2081098333","https://openalex.org/W2094013223","https://openalex.org/W2097364929","https://openalex.org/W2100483895","https://openalex.org/W2110065044","https://openalex.org/W2122189635","https://openalex.org/W2128207034","https://openalex.org/W2134592457","https://openalex.org/W2143481518","https://openalex.org/W2150965754","https://openalex.org/W2158416439","https://openalex.org/W2164392039","https://openalex.org/W2167277498","https://openalex.org/W2169986380","https://openalex.org/W2292188568","https://openalex.org/W2477400917","https://openalex.org/W2493995810","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2914369697","https://openalex.org/W7098463784"],"related_works":["https://openalex.org/W2158416439","https://openalex.org/W2007342566","https://openalex.org/W2047860559","https://openalex.org/W1973956579","https://openalex.org/W2215288704","https://openalex.org/W1492273171","https://openalex.org/W4412899391","https://openalex.org/W11871619","https://openalex.org/W2044863747","https://openalex.org/W7017456879"],"abstract_inverted_index":{"This":[0],"dissertation":[1],"consists":[2],"of":[3,6,22,50,87,98,152,171,221,291,306,342,345,350,383,406,460,479,492,530,569,577,613],"the":[4,33,45,54,64,72,96,157,168,172,187,204,208,218,224,250,340,357,361,364,377,386,403,407,412,423,458,461,490,515,528,540,555,567,601,605,614,625,631],"analyses":[5,454,627],"three":[7,34],"separate":[8,453],"genetic":[9,59,148,285],"association":[10,286,341],"datasets.":[11],"Each":[12],"represents":[13,167],"a":[14,19,343,561,573,583,645],"unique":[15,191],"data":[16,180,192,199,270],"structure":[17],"with":[18,129,147,259,310,347,376],"different":[20],"question":[21,47],"interest":[23,384],"that":[24,115,142,303,422,494,628,637,644],"therefore":[25],"require":[26],"distinct":[27],"approaches":[28,317],"and":[29,181,235,328,389,419,431,472,513,534,557,588,597],"methodologies.":[30],"As":[31,91,150],"such,":[32],"substantive":[35],"chapters":[36],"(2-4)":[37],"can":[38],"each":[39,49,75],"stand":[40],"on":[41,161,271,279,509,538],"their":[42,162],"own.":[43],"However,":[44,543],"over-arching":[46],"in":[48,126,223,284,560,624],"these":[51,116,536],"studies":[52],"is":[53,114,138,201,336,369,385,391,400,415,432,444,502,525,580,595,642],"same:":[55],"which":[56,504,550],"genes":[57,255,302,493,505,516,556],"(or":[58],"material)":[60],"are":[61,74,304,308,314,329,354,455,495,638],"related":[62,105],"to":[63,83,102,106,175,185,214,244,276,294,299,363,393,410,446,485,510,526,539,553,590,599,604,609,621,633],"disease":[65,107],"or":[66],"outcome":[67,349,585],"being":[68,570],"studied.":[69],"Moreover,":[70,253],"while":[71],"methodologies":[73,82],"distinct,":[76],"they":[77,322],"all":[78],"incorporate":[79],"statistical":[80,99,334,373,500],"learning":[81,100,374],"obtain":[84,411],"some":[85,246,315],"modicum":[86],"inference.Study":[88],"1":[89],"-":[90,264,465],"computational":[92],"power":[93],"has":[94,108,143,269],"improved":[95],"application":[97,170],"algorithms":[101,117],"finding":[103],"SNPs":[104,128,238,307],"become":[109,476],"more":[110,120,433,439,562,571],"ubiquitous.":[111],"The":[112,133,381,442,522],"hope":[113],"will":[118],"be":[119,215,507,518,591],"capable":[121],"than":[122,435],"typical":[123,209,523],"marginal":[124],"testing":[125,339],"detecting":[127],"higher":[130],"order":[131],"effects.":[132],"Random":[134],"Forests":[135],"(RF)":[136],"algorithm":[137,141,174,188,379],"one":[139,268,272,288,552],"such":[140,468,511,652],"seen":[144],"increased":[145],"use":[146,186],"data.":[149,225,252],"part":[151],"its":[153],"output,":[154],"RF":[155,173,241],"ranks":[156],"predictor":[158],"variables":[159,346,362],"(SNPs)":[160],"relative":[163],"importance.The":[164],"present":[165],"study":[166,576],"first":[169],"Genome":[176],"Wide":[177],"Association":[178],"(GWA)":[179],"investigates":[182],"how":[183,514],"best":[184],"for":[189,203,217,318,338,520,630],"this":[190,320,390],"structure.":[193],"A":[194,333,366,397,593],"multiple":[195],"sclerosis":[196],"(MS)":[197],"GWA":[198],"set":[200,344,491,529],"used":[202,581],"analysis.":[205,521],"Results":[206],"indicate":[207],"tuning":[210],"parameter":[211,382],"settings":[212],"need":[213],"adjusted":[216],"high":[219],"degree":[220],"sparsity":[222],"Furthermore,":[226],"most":[227],"meaningful":[228,622],"results":[229,623],"were":[230,239,261],"obtained":[231],"when":[232],"both":[233,417],"unimportant":[234],"overly":[236],"important":[237,499],"removed.":[240],"was":[242,586],"able":[243],"replicate":[245],"previous":[247],"findings":[248],"using":[249,371,402],"same":[251],"four":[254,610],"not":[256,330,649],"previously":[257],"associated":[258,309],"MS":[260,448],"identified.Study":[262],"2":[263],"In":[265],"many":[266,544],"analyses,":[267,467],"level":[273],"but":[274,297],"desires":[275],"draw":[277],"inference":[278],"another":[280],"level.":[281],"For":[282],"example,":[283],"studies,":[287],"observes":[289],"units":[290],"DNA":[292],"referred":[293],"as":[295,469],"SNPs,":[296],"wants":[298],"determine":[300],"whether":[301],"comprised":[305],"disease.":[311],"While":[312],"there":[313],"available":[316],"addressing":[319],"issue,":[321],"usually":[323],"involve":[324],"making":[325],"parametric":[326,436],"assumptions":[327,353],"easily":[331],"generalizable.":[332],"test":[335,399,424,443],"proposed":[337,401],"an":[348,394,447],"interest.":[351],"No":[352],"made":[355],"about":[356],"functional":[358],"form":[359],"relating":[360],"outcome.":[365],"general":[367,440],"function":[368],"fit":[370,596],"any":[372],"algorithm,":[375],"SuperLearner":[378],"suggested.":[380],"cross-validated":[387,408],"risk":[388,409],"compared":[392],"expected":[395],"risk.":[396],"Wald":[398],"influence":[404],"curve":[405],"variance.":[413],"It":[414,641],"shown":[416,643],"theoretically":[418],"via":[420],"simulation":[421],"maintains":[425],"appropriate":[426],"type":[427],"I":[428],"error":[429],"control":[430],"powerful":[434],"tests":[437],"under":[438],"alternatives.":[441],"applied":[445],"candidate":[449],"gene":[450,480,574],"study.":[451],"Three":[452],"performed":[456],"highlighting":[457],"flexibility":[459],"approach.":[462,564],"Study":[463],"3":[464],"Secondary":[466],"Gene":[470],"Ontology":[471],"Motif":[473],"analysis,":[474],"have":[475,547,650],"central":[477],"components":[478],"expression":[481,545,575],"experiments,":[482],"allowing":[483],"researchers":[484],"derive":[486],"biological":[487],"understanding":[488],"from":[489],"differentially":[496,531,615],"expressed.":[497],"An":[498],"task":[501],"determining":[503],"should":[506,517],"passed":[508],"programs":[512],"grouped":[519],"approach":[524,647],"cluster":[527],"expressed":[532,616],"genes,":[533],"pass":[535],"clusters":[537],"secondary":[541,626],"analyses.":[542],"experiments":[546],"specific":[548,606],"hypotheses":[549,636],"allow":[551,629],"analyze":[554],"group":[558],"them":[559],"targeted":[563],"To":[565],"illustrate":[566],"utility":[568],"specific,":[572],"C.":[578],"elegans":[579],"where":[582],"particular":[584],"observed":[587],"hoped":[589],"explained.":[592],"generalmodel":[594],"analyzed":[598],"estimate":[600],"parameters":[602],"corresponding":[603],"hypothesis,":[607],"leading":[608],"natural":[611],"groupings":[612,619],"genes.":[617],"These":[618],"lead":[620],"biologist":[632],"make":[634],"robust":[635,653],"experimentally":[639],"confirmed.":[640],"traditional":[646],"would":[648],"yielded":[651],"findings.":[654]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}