{"id":"https://openalex.org/W3213117415","doi":"https://doi.org/10.1109/access.2021.3127957","title":"NASCUP: Nucleic Acid Sequence Classification by Universal Probability","display_name":"NASCUP: Nucleic Acid Sequence Classification by Universal Probability","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3213117415","doi":"https://doi.org/10.1109/access.2021.3127957","mag":"3213117415"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3127957","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3127957","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09614131.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09614131.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031552594","display_name":"Sunyoung Kwon","orcid":"https://orcid.org/0000-0003-3433-1409"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sunyoung Kwon","raw_affiliation_strings":["School of Biomedical Convergence Engineering, Pusan National University, Yangsan, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Biomedical Convergence Engineering, Pusan National University, Yangsan, South Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001186750","display_name":"Gyuwan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gyuwan Kim","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070152050","display_name":"Byunghan Lee","orcid":"https://orcid.org/0000-0002-6727-0975"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byunghan Lee","raw_affiliation_strings":["Seoul National University of Science and Technology, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology, Seoul, South Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081493752","display_name":"Jongsik Chun","orcid":"https://orcid.org/0000-0003-3385-5171"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongsik Chun","raw_affiliation_strings":["Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, South Korea","School of Biological Sciences, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Biological Sciences, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086877012","display_name":"Sungroh Yoon","orcid":"https://orcid.org/0000-0002-2367-197X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":["Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, South Korea","Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101647166","display_name":"Young-Han Kim","orcid":"https://orcid.org/0000-0001-7255-8757"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young-Han Kim","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031552594"],"corresponding_institution_ids":["https://openalex.org/I4921948"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11235656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"162779","last_page":"162791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9984999895095825,"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":0.9984999895095825,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9979000091552734,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7071642279624939},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6961255669593811},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5592881441116333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5010678768157959},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4668721854686737},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4104592502117157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4025473892688751},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35384565591812134},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33949780464172363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15215876698493958},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13735651969909668},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12927696108818054},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08962851762771606},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0752783715724945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071642279624939},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6961255669593811},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5592881441116333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5010678768157959},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4668721854686737},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4104592502117157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025473892688751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35384565591812134},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33949780464172363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15215876698493958},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13735651969909668},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12927696108818054},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08962851762771606},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0752783715724945}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3127957","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3127957","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09614131.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:60eeda97bee9459eb699411cf0a8d944","is_oa":true,"landing_page_url":"https://doaj.org/article/60eeda97bee9459eb699411cf0a8d944","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 162779-162791 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3127957","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3127957","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09614131.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1214977761","display_name":null,"funder_award_id":"2018R1A2B","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2203846861","display_name":null,"funder_award_id":"the BK21 FOUR","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G30685149","display_name":null,"funder_award_id":"BK21 FOUR","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G4995453646","display_name":null,"funder_award_id":"BK21 FOUR","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G5164132823","display_name":null,"funder_award_id":"BK21 FOUR Program","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G6125236940","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G6957768356","display_name":null,"funder_award_id":"Biotechnology","funder_id":"https://openalex.org/F4320322110","funder_display_name":"Korea Research Institute of Bioscience and Biotechnology"},{"id":"https://openalex.org/G6988067448","display_name":null,"funder_award_id":"2020-0-01450","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7155487561","display_name":null,"funder_award_id":"postdoc","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G7444592284","display_name":null,"funder_award_id":"2018R1A2B3001628","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7685055460","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7990100567","display_name":null,"funder_award_id":"2020-0-01450","funder_id":"https://openalex.org/F4320321284","funder_display_name":"Pusan National University"},{"id":"https://openalex.org/G83507041","display_name":null,"funder_award_id":"2020-0-01450","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8790935500","display_name":null,"funder_award_id":"2018R1A2B3001628","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320295","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321284","display_name":"Pusan National University","ror":"https://ror.org/01an57a31"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320321294","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322035","display_name":"Rural Development Administration","ror":"https://ror.org/03xs9yg50"},{"id":"https://openalex.org/F4320322110","display_name":"Korea Research Institute of Bioscience and Biotechnology","ror":"https://ror.org/03ep23f07"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320327756","display_name":"National University of Science and Technology","ror":"https://ror.org/019vsm959"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320329803","display_name":"LG Electronics","ror":"https://ror.org/03ddh2c27"},{"id":"https://openalex.org/F4320332500","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213117415.pdf","grobid_xml":"https://content.openalex.org/works/W3213117415.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1541535159","https://openalex.org/W1968908999","https://openalex.org/W1981155179","https://openalex.org/W1983661866","https://openalex.org/W1988925586","https://openalex.org/W1994920552","https://openalex.org/W1999120268","https://openalex.org/W2000072710","https://openalex.org/W2011485152","https://openalex.org/W2013610892","https://openalex.org/W2033387638","https://openalex.org/W2034285706","https://openalex.org/W2054658115","https://openalex.org/W2057393527","https://openalex.org/W2072970694","https://openalex.org/W2097413543","https://openalex.org/W2108718991","https://openalex.org/W2110309669","https://openalex.org/W2129902114","https://openalex.org/W2129995544","https://openalex.org/W2130979840","https://openalex.org/W2132119275","https://openalex.org/W2142439271","https://openalex.org/W2146235863","https://openalex.org/W2153990926","https://openalex.org/W2154775341","https://openalex.org/W2155066423","https://openalex.org/W2156125289","https://openalex.org/W2158381555","https://openalex.org/W2163294786","https://openalex.org/W2166064672","https://openalex.org/W2169929748","https://openalex.org/W2174375947","https://openalex.org/W2181908191","https://openalex.org/W2478708596","https://openalex.org/W2792227582","https://openalex.org/W3123899698","https://openalex.org/W4236236547","https://openalex.org/W6681108551"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2389214306","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2965083567","https://openalex.org/W2113096305","https://openalex.org/W1977636359"],"abstract_inverted_index":{"Nucleic":[0],"acid":[1],"sequence":[2,124],"classification":[3,25,43,79,100],"is":[4],"a":[5,29,41],"fundamental":[6],"task":[7],"in":[8,88,107],"the":[9,15,81],"field":[10],"of":[11,18,26,49,83],"bioinformatics.":[12],"Due":[13],"to":[14,114],"increasing":[16],"amount":[17],"unlabeled":[19],"nucleotide":[20,50],"sequences,":[21],"fast":[22],"and":[23,56,76,91,111,122],"accurate":[24],"them":[27],"on":[28],"large":[30],"scale":[31],"has":[32],"become":[33],"crucial.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"developed":[39],"NASCUP,":[40],"new":[42],"method":[44],"that":[45],"captures":[46],"statistical":[47],"structures":[48],"sequences":[51],"by":[52],"compact":[53],"context-tree":[54],"models":[55],"universal":[57],"probability":[58],"from":[59],"information":[60],"theory.":[61],"A":[62],"comprehensive":[63],"experimental":[64],"study":[65],"involving":[66],"nine":[67],"public":[68],"databases":[69,106],"for":[70,103],"functional":[71],"non-coding":[72],"RNA,":[73],"microbial":[74],"taxonomy":[75],"coding/non-coding":[77],"RNA":[78],"demonstrates":[80],"advantages":[82],"NASCUP":[84,97],"over":[85],"widely-used":[86],"alternatives":[87],"efficiency,":[89],"accuracy,":[90],"scalability":[92],"across":[93],"all":[94],"datasets":[95],"considered.":[96],"achieved":[98],"BLAST-like":[99],"accuracy":[101],"consistently":[102],"several":[104],"large-scale":[105],"orders-of-magnitude":[108],"reduced":[109],"runtime,":[110],"was":[112],"applied":[113],"other":[115],"bioinformatics":[116],"tasks":[117],"such":[118],"as":[119],"outlier":[120],"detection":[121],"synthetic":[123],"generation.":[125]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
