{"id":"https://openalex.org/W3181172718","doi":"https://doi.org/10.31274/etd-20210609-38","title":"Discovering relationships between genotype and phenotype: Machine learning approaches","display_name":"Discovering relationships between genotype and phenotype: Machine learning approaches","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3181172718","doi":"https://doi.org/10.31274/etd-20210609-38","mag":"3181172718"},"language":"en","primary_location":{"id":"doi:10.31274/etd-20210609-38","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-38","pdf_url":"https://dr.lib.iastate.edu/bitstreams/d213f4c6-2ac1-4ca5-9348-7c11b8615b31/download","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dr.lib.iastate.edu/bitstreams/d213f4c6-2ac1-4ca5-9348-7c11b8615b31/download","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080779529","display_name":"Kyoung Tak Cho","orcid":"https://orcid.org/0000-0002-3353-7301"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyoung Tak Cho","raw_affiliation_strings":["Department of Computer Science, Iowa State University, Ames, IA, United States,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University, Ames, IA, United States,","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080779529"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9976999759674072,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9976999759674072,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.996999979019165,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9957000017166138,"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/phenotype","display_name":"Phenotype","score":0.6108028888702393},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.57138991355896},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35811495780944824},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34868067502975464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3412737250328064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3367787003517151},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32529860734939575},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11437442898750305}],"concepts":[{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.6108028888702393},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.57138991355896},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35811495780944824},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34868067502975464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3412737250328064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3367787003517151},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32529860734939575},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11437442898750305}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.31274/etd-20210609-38","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-38","pdf_url":"https://dr.lib.iastate.edu/bitstreams/d213f4c6-2ac1-4ca5-9348-7c11b8615b31/download","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},{"id":"pmh:oai:lib.dr.iastate.edu:etd-9484","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=9484&context=etd","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Graduate Theses and Dissertations","raw_type":"text"},{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/ywAbO0gv","is_oa":false,"landing_page_url":"https://dr.lib.iastate.edu/handle/20.500.12876/ywAbO0gv","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dissertation"}],"best_oa_location":{"id":"doi:10.31274/etd-20210609-38","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-38","pdf_url":"https://dr.lib.iastate.edu/bitstreams/d213f4c6-2ac1-4ca5-9348-7c11b8615b31/download","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3181172718.pdf","grobid_xml":"https://content.openalex.org/works/W3181172718.grobid-xml"},"referenced_works_count":110,"referenced_works":["https://openalex.org/W203615339","https://openalex.org/W1500435738","https://openalex.org/W1505191356","https://openalex.org/W1831548991","https://openalex.org/W1973626596","https://openalex.org/W1981509058","https://openalex.org/W1984708728","https://openalex.org/W1985468934","https://openalex.org/W1988581590","https://openalex.org/W2005336557","https://openalex.org/W2006075770","https://openalex.org/W2014704298","https://openalex.org/W2020336239","https://openalex.org/W2027351435","https://openalex.org/W2044534398","https://openalex.org/W2055043387","https://openalex.org/W2057253402","https://openalex.org/W2060384656","https://openalex.org/W2079436890","https://openalex.org/W2093519658","https://openalex.org/W2096358531","https://openalex.org/W2106006432","https://openalex.org/W2109715166","https://openalex.org/W2128289656","https://openalex.org/W2133191750","https://openalex.org/W2134941832","https://openalex.org/W2136773811","https://openalex.org/W2138486754","https://openalex.org/W2138785419","https://openalex.org/W2141865968","https://openalex.org/W2145477956","https://openalex.org/W2150774511","https://openalex.org/W2151397621","https://openalex.org/W2154776515","https://openalex.org/W2158714788","https://openalex.org/W2159833474","https://openalex.org/W2164686527","https://openalex.org/W2168909179","https://openalex.org/W2171963266","https://openalex.org/W2229670862","https://openalex.org/W2254411337","https://openalex.org/W2293903575","https://openalex.org/W2295653214","https://openalex.org/W2299928498","https://openalex.org/W2424628474","https://openalex.org/W2515922456","https://openalex.org/W2547405129","https://openalex.org/W2561267978","https://openalex.org/W2568830712","https://openalex.org/W2581040748","https://openalex.org/W2582416435","https://openalex.org/W2597444305","https://openalex.org/W2606176360","https://openalex.org/W2623168030","https://openalex.org/W2763916255","https://openalex.org/W2765944784","https://openalex.org/W2768308516","https://openalex.org/W2769823402","https://openalex.org/W2792382948","https://openalex.org/W2883756413","https://openalex.org/W2884730312","https://openalex.org/W2886966121","https://openalex.org/W2890017579","https://openalex.org/W2896262061","https://openalex.org/W2898982100","https://openalex.org/W2899669628","https://openalex.org/W2901365579","https://openalex.org/W2903489885","https://openalex.org/W2911666059","https://openalex.org/W2915583118","https://openalex.org/W2921808728","https://openalex.org/W2922701384","https://openalex.org/W2936250992","https://openalex.org/W2937169286","https://openalex.org/W2949074212","https://openalex.org/W2950150251","https://openalex.org/W2950326881","https://openalex.org/W2950744570","https://openalex.org/W2951022399","https://openalex.org/W2951737218","https://openalex.org/W2952663747","https://openalex.org/W2952932047","https://openalex.org/W2953233126","https://openalex.org/W2964163184","https://openalex.org/W2967837349","https://openalex.org/W2968752241","https://openalex.org/W2972586262","https://openalex.org/W2986205472","https://openalex.org/W2998539163","https://openalex.org/W3001191610","https://openalex.org/W3002262829","https://openalex.org/W3028573392","https://openalex.org/W3087561936","https://openalex.org/W4236137412","https://openalex.org/W4239510810","https://openalex.org/W4241067242","https://openalex.org/W4252732282","https://openalex.org/W4287901611","https://openalex.org/W4297824538","https://openalex.org/W6615538834","https://openalex.org/W6630229306","https://openalex.org/W6636737901","https://openalex.org/W6645515742","https://openalex.org/W6655609597","https://openalex.org/W6657404746","https://openalex.org/W6665308405","https://openalex.org/W6669978091","https://openalex.org/W6678459093","https://openalex.org/W6817491142","https://openalex.org/W6821113053"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2134373856","https://openalex.org/W2385665726","https://openalex.org/W2347271704","https://openalex.org/W2391157579","https://openalex.org/W3029453589","https://openalex.org/W2325793530","https://openalex.org/W2036624756","https://openalex.org/W2372977423","https://openalex.org/W2387402244"],"abstract_inverted_index":{"The":[0],"history":[1,6],"of":[2,7,48,129,200,213,252,257,278,301,327],"science":[3],"is":[4,24,35,61],"the":[5,36,44,53,58,109,115,122,138,211,229,255,258,263,272,279,284,291,325,348,351,357],"finding":[8],"true":[9],"belief":[10],"from":[11,16,108],"observations.":[12],"Humans":[13],"build":[14],"knowledge":[15],"observations,":[17],"experiences,":[18],"and/or":[19],"other":[20],"knowledge.":[21],"Sometimes,":[22],"it":[23,239],"difficult":[25],"to":[26,38,55,65,73,104,141,185,243,316,345],"understand":[27,347],"a":[28,127,218,225,236,354],"phenomenon":[29],"with":[30,228,294],"superficial":[31],"observation.":[32],"Observed":[33],"data":[34,49,76,329],"key":[37],"solve":[39],"problems":[40],"around":[41],"us.":[42],"As":[43],"size":[45,256,269],"and":[46,69,84,99,119,131,168,178,181,191,238,265,319,330,335,340,356],"complexity":[47,212,264],"grows,":[50],"so":[51],"does":[52],"need":[54],"accurately":[56],"process":[57],"data.":[59,111,337],"There":[60],"now":[62],"an":[63],"opportunity":[64],"apply":[66],"artificial":[67],"intelligence":[68],"machine":[70,101,143,311],"learning":[71,102,144,312],"approaches":[72,103,313],"large-scale":[74],"multi-omic":[75],"sets":[77],"in":[78,121,235,250,324,353,360],"new":[79,183,219],"areas":[80],"such":[81],"as":[82],"agriculture":[83],"crop":[85],"improvement.":[86],"In":[87],"this":[88],"study,":[89],"we":[90,113,136,175,216,270,289],"focus":[91],"on":[92,283,298],"maize":[93,123],"(Zea":[94],"mays":[95],"L.)":[96],"genomic":[97,110,161,334],"data,":[98],"applied":[100,137,290],"discover":[105],"meaningful":[106],"features":[107],"First":[112],"explored":[114],"relationship":[116,349],"between":[117,231,333,350],"phenotype":[118],"genotype":[120],"genome":[124],"by":[125],"building":[126],"database":[128],"images":[130],"genomes":[132],"called":[133],"MaizeDIG.":[134],"Second,":[135],"k-mer":[139,156,164,170,188,193,220,268,274,292],"concept":[140],"construct":[142],"frameworks":[145],"for":[146,160],"predicting":[147],"gene":[148,151,248],"expression":[149],"using":[150],"sequences.":[152],"We":[153,223],"describe":[154],"two":[155,247],"Naive":[157,165,171,205],"Bayes":[158,166,172,206],"classifiers":[159],"sequence":[162],"classification:":[163],"(NB(k))":[167],"two-phase":[169],"(tNB(k)).":[173],"Finally,":[174],"extend":[176],"NB(k)":[177,280],"tNB(t)":[179],"methods":[180,184],"propose":[182,217,271],"represent":[186,210],"sequence:":[187],"distance":[189,221,226,230],"model":[190],"reduced":[192,273,307],"alphabet":[194,203,261,275,308],"model.\\nNB(k)":[195],"only":[196],"considers":[197],"relative":[198],"frequencies":[199],"each":[201],"respective":[202],"under":[204],"classifier.":[207],"To":[208],"better":[209,346],"protein":[214],"structure,":[215],"model.":[222,276],"constructed":[224],"matrix":[227],"all":[232],"pairwise":[233],"k-mers":[234],"sequence,":[237],"can":[240,342],"be":[241,343],"used":[242,344],"measure":[244],"or":[245,304],"compare":[246],"sequences":[249],"terms":[251],"similarity.":[253],"Since":[254],"amino":[259,287,302],"acid":[260],"affects":[262],"therefore":[266],"limits":[267],"Instead":[277],"approach":[281],"based":[282,297],"traditional":[285],"20":[286],"acids,":[288],"method":[293],"smaller-sized":[295],"groupings":[296],"physico-chemical":[299],"properties":[300],"acids":[303],"randomly":[305],"generated":[306],"groupings.":[309],"Our":[310],"allow":[314],"researchers":[315],"predict":[317],"when":[318],"where":[320],"genes":[321,352],"are":[322],"expressed":[323],"absence":[326],"experimental":[328],"make":[331],"links":[332],"phenotypic":[336],"These":[338],"predictions":[339],"linkages":[341],"plant":[355],"traits":[358],"observed":[359],"farmers'":[361],"fields.":[362]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}