{"id":"https://openalex.org/W3192479474","doi":"https://doi.org/10.1145/3459930.3469545","title":"Frontier","display_name":"Frontier","publication_year":2021,"publication_date":"2021-07-30","ids":{"openalex":"https://openalex.org/W3192479474","doi":"https://doi.org/10.1145/3459930.3469545","mag":"3192479474"},"language":"en","primary_location":{"id":"doi:10.1145/3459930.3469545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459930.3469545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074552594","display_name":"Anwica Kashfeen","orcid":null},"institutions":[{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]},{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anwica Kashfeen","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042463953","display_name":"Leonard McMillan","orcid":"https://orcid.org/0000-0002-8453-0847"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonard McMillan","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074552594"],"corresponding_institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"],"apc_list":null,"apc_paid":null,"fwci":0.0804,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43450013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9980999827384949,"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":0.6827923059463501},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5292056798934937},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5245863795280457},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4865254759788513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46963047981262207},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3699652850627899},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34194082021713257},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24501073360443115},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2168930470943451},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1343112587928772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827923059463501},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5292056798934937},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5245863795280457},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4865254759788513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46963047981262207},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3699652850627899},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34194082021713257},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24501073360443115},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2168930470943451},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1343112587928772}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459930.3469545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459930.3469545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1489909987","https://openalex.org/W1537923221","https://openalex.org/W1965368044","https://openalex.org/W1973862547","https://openalex.org/W2007736033","https://openalex.org/W2021344630","https://openalex.org/W2046137036","https://openalex.org/W2049071198","https://openalex.org/W2096128575","https://openalex.org/W2121332208","https://openalex.org/W2132141594","https://openalex.org/W2146821392","https://openalex.org/W2157890550","https://openalex.org/W2161488606","https://openalex.org/W2168909179","https://openalex.org/W2300605489","https://openalex.org/W2531715486","https://openalex.org/W2619212644","https://openalex.org/W2624585284","https://openalex.org/W2963995493","https://openalex.org/W2973134747","https://openalex.org/W2998336860","https://openalex.org/W6676286517"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2787993192","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W2773861473"],"abstract_inverted_index":{"Transposable":[0],"Elements":[1],"(TEs)":[2],"are":[3,25,33,40,233],"DNA":[4],"subsequences":[5],"that":[6,149],"have":[7],"historically":[8],"copied":[9],"themselves":[10],"throughout":[11],"a":[12,17,26,85,125,180],"genome.":[13],"Apart":[14],"from":[15],"constituting":[16],"large":[18],"fraction":[19],"of":[20,29,43,62,79,120,142,154],"all":[21],"eukaryotic":[22],"genomes,":[23],"TEs":[24,39],"significant":[27],"source":[28],"genetic":[30],"variation":[31],"and":[32,75,92,99,112,203,219],"directly":[34],"responsible":[35],"for":[36,54,87,104,129],"many":[37],"diseases.":[38],"also":[41],"one":[42],"the":[44,60,80,118,131,140,152,167,185],"most":[45],"difficult":[46],"genomic":[47],"regions":[48],"to":[49,145,163,183,210],"analyze.":[50],"A":[51],"typical":[52],"approach":[53],"identifying":[55,130],"TE":[56,74,81,90,143,187],"insertions":[57],"(TEi)":[58],"involves":[59],"detection":[61],"split-reads,":[63],"which":[64],"requires":[65],"checking":[66],"if":[67],"each":[68,88,174],"read":[69,168],"can":[70,217],"be":[71],"split":[72],"into":[73],"non-TE":[76],"parts.":[77],"Identification":[78],"part":[82],"depends":[83],"on":[84,109],"model":[86],"distinct":[89],"class,":[91],"these":[93],"classes":[94],"vary":[95],"significantly":[96],"both":[97],"within":[98],"between":[100],"species.":[101],"Previous":[102],"methods":[103,162],"detecting":[105],"segregating":[106],"TEis":[107],"depend":[108],"template":[110],"libraries":[111],"their":[113],"computational":[114],"cost":[115],"increases":[116],"with":[117],"number":[119],"templates.":[121],"Here":[122],"we":[123,178],"propose":[124],"novel":[126],"template-free":[127],"method":[128],"split-reads":[132],"containing":[133],"TEi":[134,176],"boundaries":[135],"called":[136],"Frontier.":[137],"We":[138,157],"leverage":[139],"pervasiveness":[141],"sequences":[144],"identify":[146],"candidate":[147],"reads":[148,225],"might":[150],"include":[151],"boundary":[153,177],"an":[155,229],"insertion.":[156],"then":[158],"apply":[159,179],"machine":[160],"learning":[161],"further":[164],"classify":[165,220],"whether":[166],"includes":[169],"actual":[170],"TE-like":[171],"sequence.":[172],"For":[173],"predicted":[175],"second":[181],"classifier":[182],"infer":[184],"corresponding":[186],"type":[188],"(LINE,":[189],"SINE,":[190],"ALU,":[191],"ERV/LTR).":[192],"Both":[193],"classifiers":[194],"achieve":[195],"high":[196],"precision":[197],"(>":[198,201,206],".9),":[199],"recall":[200],".8)":[202,207],"F1":[204],"score":[205],"when":[208],"applied":[209],"real":[211],"data.":[212],"The":[213],"resulting":[214],"trained":[215],"model,":[216],"detect":[218],"about":[221],"50":[222],"million":[223],"frontier":[224],"in":[226],"less":[227],"than":[228],"hour.":[230],"Frontier":[231],"codes":[232],"available":[234],"at":[235],"github":[236],"https://github.com/Anwica/Frontier.":[237]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-08-16T00:00:00"}