{"id":"https://openalex.org/W2136527659","doi":"https://doi.org/10.31274/etd-180810-1705","title":"Abstraction-based probabilistic models for sequence classification","display_name":"Abstraction-based probabilistic models for sequence classification","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2136527659","doi":"https://doi.org/10.31274/etd-180810-1705","mag":"2136527659"},"language":"en","primary_location":{"id":"doi:10.31274/etd-180810-1705","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-180810-1705","pdf_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=2037&context=etd","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University, Digital Repository","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=2037&context=etd","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"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":"Cornelia Caragea","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089085275"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9940000176429749,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9904999732971191,"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/abstraction","display_name":"Abstraction","score":0.6603775024414062},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6068675518035889},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6013782024383545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5450593829154968},{"id":"https://openalex.org/keywords/miller","display_name":"Miller","score":0.5167576670646667},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.4104246497154236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.392996609210968},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.13028419017791748},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09303539991378784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07977169752120972}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6603775024414062},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6068675518035889},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6013782024383545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450593829154968},{"id":"https://openalex.org/C2777496998","wikidata":"https://www.wikidata.org/wiki/Q1536587","display_name":"Miller","level":2,"score":0.5167576670646667},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.4104246497154236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.392996609210968},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.13028419017791748},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09303539991378784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07977169752120972},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.31274/etd-180810-1705","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-180810-1705","pdf_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=2037&context=etd","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University, Digital Repository","raw_type":"dissertation"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.3494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.3494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/cuc23/papers/thesis.pdf","raw_type":"text"},{"id":"pmh:oai:lib.dr.iastate.edu:etd-2037","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/etd/11022","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"}],"best_oa_location":{"id":"doi:10.31274/etd-180810-1705","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-180810-1705","pdf_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=2037&context=etd","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University, Digital Repository","raw_type":"dissertation"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.41999998688697815},{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":109,"referenced_works":["https://openalex.org/W64805031","https://openalex.org/W106244805","https://openalex.org/W193142705","https://openalex.org/W628139972","https://openalex.org/W1251130462","https://openalex.org/W1479807131","https://openalex.org/W1487588218","https://openalex.org/W1490760466","https://openalex.org/W1498183065","https://openalex.org/W1500385977","https://openalex.org/W1523949738","https://openalex.org/W1528489993","https://openalex.org/W1530340949","https://openalex.org/W1550206324","https://openalex.org/W1555273987","https://openalex.org/W1555585125","https://openalex.org/W1556860917","https://openalex.org/W1570713908","https://openalex.org/W1571733964","https://openalex.org/W1584444527","https://openalex.org/W1590548082","https://openalex.org/W1597533204","https://openalex.org/W1598266570","https://openalex.org/W1604842785","https://openalex.org/W1619260253","https://openalex.org/W1663973292","https://openalex.org/W1766290689","https://openalex.org/W1800493452","https://openalex.org/W1849729440","https://openalex.org/W1860480534","https://openalex.org/W1908728294","https://openalex.org/W1994851566","https://openalex.org/W2001141328","https://openalex.org/W2009570821","https://openalex.org/W2010425028","https://openalex.org/W2019363670","https://openalex.org/W2020016327","https://openalex.org/W2020694521","https://openalex.org/W2022169621","https://openalex.org/W2023871516","https://openalex.org/W2032315246","https://openalex.org/W2033791543","https://openalex.org/W2044758663","https://openalex.org/W2047275065","https://openalex.org/W2049122170","https://openalex.org/W2050035935","https://openalex.org/W2053186076","https://openalex.org/W2063768466","https://openalex.org/W2064580901","https://openalex.org/W2078029048","https://openalex.org/W2096152098","https://openalex.org/W2096814070","https://openalex.org/W2097730395","https://openalex.org/W2097826433","https://openalex.org/W2099111195","https://openalex.org/W2099438806","https://openalex.org/W2102719186","https://openalex.org/W2103723258","https://openalex.org/W2104244040","https://openalex.org/W2105732805","https://openalex.org/W2113709557","https://openalex.org/W2115013148","https://openalex.org/W2116483826","https://openalex.org/W2119423166","https://openalex.org/W2119733112","https://openalex.org/W2121947440","https://openalex.org/W2122876804","https://openalex.org/W2125838338","https://openalex.org/W2127831831","https://openalex.org/W2132827946","https://openalex.org/W2134610083","https://openalex.org/W2135863341","https://openalex.org/W2138105615","https://openalex.org/W2138224681","https://openalex.org/W2138745909","https://openalex.org/W2139212933","https://openalex.org/W2140209831","https://openalex.org/W2146950091","https://openalex.org/W2147073365","https://openalex.org/W2147206923","https://openalex.org/W2147880316","https://openalex.org/W2148264799","https://openalex.org/W2148603752","https://openalex.org/W2148737169","https://openalex.org/W2149982649","https://openalex.org/W2152458080","https://openalex.org/W2154053567","https://openalex.org/W2154122057","https://openalex.org/W2154293623","https://openalex.org/W2154683974","https://openalex.org/W2156571267","https://openalex.org/W2157444450","https://openalex.org/W2160072419","https://openalex.org/W2160842254","https://openalex.org/W2161549461","https://openalex.org/W2161899637","https://openalex.org/W2162630660","https://openalex.org/W2162915993","https://openalex.org/W2167044614","https://openalex.org/W2168272116","https://openalex.org/W2170654002","https://openalex.org/W2171108400","https://openalex.org/W2402405544","https://openalex.org/W2490467459","https://openalex.org/W2504658994","https://openalex.org/W2799002609","https://openalex.org/W2895423403","https://openalex.org/W2962735828","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3036113924","https://openalex.org/W3155555900","https://openalex.org/W3187290648","https://openalex.org/W4233121562","https://openalex.org/W2277421000","https://openalex.org/W3034420249","https://openalex.org/W4237177488","https://openalex.org/W2058016970","https://openalex.org/W1926181953","https://openalex.org/W4200577870"],"abstract_inverted_index":{"Many":[0],"applications":[1,159],"e.g.,":[2],"biomolecular":[3],"sequence":[4,162,181],"analysis,":[5,12],"image":[6],"classification,":[7,9],"text":[8,164,351],"social":[10],"network":[11],"among":[13],"others":[14],"require":[15],"classification":[16,182,353],"of":[17,63,77,93,118,129,171,213,228,256,270,280,317,364,392,399,414,444,449],"topologically":[18,51,74,84,155,459],"structured":[19,52,75,85,156,460],"data,":[20],"i.e.":[21],"data":[22,86,95,157,174,263,286,326,373],"whose":[23],"topology":[24],"reflects":[25],"intrinsic":[26],"dependencies":[27,305],"between":[28,306],"the":[29,35,61,78,91,94,116,127,148,169,173,188,200,211,225,253,257,262,268,271,278,285,310,325,330,362,365,368,412,434,441,445],"constituent":[30],"elements":[31],"that":[32,96,112,216,303,342,371,387,430],"make":[33,126],"up":[34],"data.":[36,53,165,461],"Hence,":[37],"there":[38],"is":[39,97],"a":[40,57,100,178,249],"growing":[41],"need":[42],"for":[43,46,65,314,451],"automated":[44],"methods":[45],"building":[47,452],"predictive":[48,152,254,385,456],"models":[49,153,259,295,302,386,420,429,457],"from":[50,83,115,154,458],"Machine":[54],"learning":[55,82,130,144],"offers":[56],"promising":[58],"approach":[59,142,223],"to":[60,69,88,99,105,109,125,133,143,160,242,251,337,383,396],"design":[62],"algorithms":[64,450],"training":[66],"computer":[67],"programs":[68],"efficiently":[70],"and":[71,163,195,198,237,290,355,378,418,454],"accurately":[72],"classify":[73],"data.\\nOne":[76],"main":[79],"challenges":[80],"in":[81,184,190,202,210,345,425,437,447],"has":[87,104],"do":[89],"with":[90,158,411,423],"representation":[92,103,175,264,327,374],"presented":[98],"learner.":[101],"The":[102],"be":[106],"rich":[107,123],"enough":[108],"capture":[110,304],"distinctions":[111],"are":[113,193,205,217,298,343,421],"relevant":[114],"standpoint":[117],"learning,":[119],"but":[120],"not":[121,206],"so":[122],"as":[124,209],"task":[128],"harder":[131],"due":[132],"overfitting.\\nAgainst":[134],"this":[135,438],"background,":[136],"we":[137,167,288],"present":[138],"an":[139,346],"abstraction-based":[140,222,419],"probabilistic":[141],"accurate":[145,453],"and,":[146,308,424],"at":[147,309],"same":[149,311],"time,":[150,312],"compact":[151,315],"biological":[161],"Specifically,":[166],"address":[168],"problem":[170],"simplifying":[172,284,372],"used":[176,328],"by":[177,219,233,260,283,329,333,375],"learner":[179],"on":[180,350],"tasks":[183,354,360],"two":[185],"settings:":[186],"(i)":[187],"setting":[189,201],"which":[191,203],"sequences":[192,204,215],"independent":[194,207],"identically":[196],"distributed":[197],"(ii)":[199],"(e.g.,":[208],"case":[212],"protein":[214,356],"linked":[218],"function).":[220],"Our":[221],"exploits":[224],"complementary":[226],"strengths":[227],"super-structuring":[229,266,377,405],"(constructing":[230],"complex":[231],"features":[232,241,393],"combining":[234,376],"existing":[235],"features)":[236],"abstraction":[238,275,292,347,379],"(grouping":[239],"similar":[240,335],"generate":[243,338],"more":[244,339],"abstract":[245,340],"features).":[246],"Super-structuring":[247,417],"provides":[248],"way":[250],"increase":[252],"accuracy":[255],"learned":[258,272],"enriching":[261],"(hence,":[265],"increases":[267],"complexity":[269],"models),":[273],"whereas":[274],"helps":[276],"reduce":[277],"number":[279,391],"model":[281],"parameters":[282],"representation.\\nFurthermore,":[287],"introduce":[289],"study":[291],"augmented":[293],"Markov":[294],"(AAMMs).":[296],"AAMMs":[297,323],"directed":[299],"acyclic":[300],"graphical":[301],"variables":[307],"allow":[313],"representations":[316],"conditional":[318],"probability":[319],"tables.":[320],"More":[321],"precisely,":[322],"simplify":[324],"standard":[331],"MMs":[332],"grouping":[334],"entities":[336,341],"organized":[344],"hierarchy.\\nExperimental":[348],"results":[349,369],"document":[352],"subcellular":[357],"localization":[358],"prediction":[359],"demonstrate":[361],"feasibility":[363],"proposed":[366],"approach:":[367],"show":[370],"makes":[380],"it":[381],"possible":[382],"construct":[384],"use":[388,431],"substantially":[389],"smaller":[390],"(by":[394],"one":[395],"three":[397],"orders":[398],"magnitude)":[400],"than":[401],"those":[402],"obtained":[403],"using":[404],"alone":[406],"(whose":[407],"size":[408],"grows":[409],"exponentially":[410],"length":[413],"direct":[415],"dependencies).":[416],"competitive":[422],"some":[426],"cases,":[427],"outperform,":[428],"only":[432],"super-structuring.\\nCollectively,":[433],"techniques":[435],"developed":[436],"thesis":[439],"advance":[440],"current":[442],"state":[443],"art":[446],"terms":[448],"concise":[455]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}