{"id":"https://openalex.org/W7214601170","doi":"https://doi.org/10.64898/2026.09.22.753378","title":"Non3nExonFinder: transcript-aware identification of shared non-triplet coding exons","display_name":"Non3nExonFinder: transcript-aware identification of shared non-triplet coding exons","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214601170","doi":"https://doi.org/10.64898/2026.09.22.753378"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.22.753378","doi":"https://doi.org/10.64898/2026.09.22.753378","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753378","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753378.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753378.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103552615","display_name":"Sung\u2010Yeon Lee","orcid":"https://orcid.org/0000-0002-1047-2357","observed_orcids":["https://orcid.org/0000-0002-1047-2357"]},"institutions":[{"id":"https://openalex.org/I4210129256","display_name":"Macrogen (South Korea)","ror":"https://ror.org/03qan5r71","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210129256"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sung-Yeon Lee","raw_affiliation_strings":["GEM Division, Macrogen Inc., Seoul, Republic of Korea, 07573"],"raw_orcid":"https://orcid.org/0000-0002-1047-2357","affiliations":[{"raw_affiliation_string":"GEM Division, Macrogen Inc., Seoul, Republic of Korea, 07573","institution_ids":["https://openalex.org/I4210129256"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052377558","display_name":"Joo-Hee Lee","orcid":"https://orcid.org/0000-0002-7721-8935","observed_orcids":["https://orcid.org/0000-0002-7721-8935","https://orcid.org/0000-0001-9957-6701"]},"institutions":[{"id":"https://openalex.org/I4210129256","display_name":"Macrogen (South Korea)","ror":"https://ror.org/03qan5r71","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210129256"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joo-Hee Lee","raw_affiliation_strings":["GEM Division, Macrogen Inc., Seoul, Republic of Korea, 07573"],"raw_orcid":"https://orcid.org/0000-0001-9957-6701","affiliations":[{"raw_affiliation_string":"GEM Division, Macrogen Inc., Seoul, Republic of Korea, 07573","institution_ids":["https://openalex.org/I4210129256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103552615"],"corresponding_institution_ids":["https://openalex.org/I4210129256"],"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/T10604","display_name":"RNA Research and Splicing","score":0.6855000257492065,"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/T10604","display_name":"RNA Research and Splicing","score":0.6855000257492065,"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":0.15950000286102295,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.08089999854564667,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exon-deletion","display_name":"exon deletion","score":0.6729999780654907},{"id":"https://openalex.org/keywords/loss-of-function-screen","display_name":"loss-of-function screen","score":0.7929999828338623},{"id":"https://openalex.org/keywords/transcript-isoforms","display_name":"mRNA isoforms","score":0.8029999732971191},{"id":"https://openalex.org/keywords/coding-sequences","display_name":"coding sequences","score":0.6690000295639038},{"id":"https://openalex.org/keywords/exon-annotation","display_name":"exon annotation","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.9480000138282776},{"id":"https://openalex.org/C36823959","wikidata":"https://www.wikidata.org/wiki/Q373027","display_name":"Exon","level":3,"score":0.8669999837875366},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5637999773025513},{"id":"https://openalex.org/C190017056","wikidata":"https://www.wikidata.org/wiki/Q5420611","display_name":"Exon shuffling","level":5,"score":0.5595999956130981},{"id":"https://openalex.org/C156446351","wikidata":"https://www.wikidata.org/wiki/Q7682435","display_name":"Tandem exon duplication","level":4,"score":0.5364000201225281},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5135999917984009},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.47130000591278076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4505999982357025},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3716000020503998},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.33489999175071716},{"id":"https://openalex.org/C141674004","wikidata":"https://www.wikidata.org/wiki/Q1344256","display_name":"Ensembl","level":5,"score":0.32820001244544983},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.31529998779296875},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C39917842","wikidata":"https://www.wikidata.org/wiki/Q1384125","display_name":"Exon trapping","level":5,"score":0.289900004863739},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2849000096321106},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.22.753378","doi":"https://doi.org/10.64898/2026.09.22.753378","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753378","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753378.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.22.753378","doi":"https://doi.org/10.64898/2026.09.22.753378","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753378","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753378.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214601170.pdf","grobid_xml":"https://content.openalex.org/works/W7214601170.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1973094248","https://openalex.org/W2085544097","https://openalex.org/W2131478115","https://openalex.org/W2159358696","https://openalex.org/W2162634302","https://openalex.org/W2173732482","https://openalex.org/W2594658880","https://openalex.org/W2623060578","https://openalex.org/W2911398169","https://openalex.org/W2921119983","https://openalex.org/W2939923831","https://openalex.org/W2945567049","https://openalex.org/W3111061871","https://openalex.org/W4224014283","https://openalex.org/W4399638148","https://openalex.org/W4400474986","https://openalex.org/W4411900524","https://openalex.org/W7118767708"],"related_works":["https://openalex.org/W4413111797","https://openalex.org/W2161611988","https://openalex.org/W2049082836","https://openalex.org/W7202342101","https://openalex.org/W2008195396","https://openalex.org/W2976684908","https://openalex.org/W7098253615","https://openalex.org/W2414585354","https://openalex.org/W1994658343","https://openalex.org/W2422020567"],"abstract_inverted_index":{"ABSTRACT":[0],"Selection":[1],"of":[2,27,146,159],"an":[3,8,53],"appropriate":[4],"coding":[5,45,61,77],"exon":[6,13,28,42,135],"is":[7],"important":[9],"upstream":[10,154],"step":[11],"in":[12,41,107],"deletion-based":[14],"loss-of-function":[15],"strategies,":[16],"particularly":[17],"for":[18,57,79,156],"genes":[19,126],"with":[20,85,140,143],"multiple":[21,31],"transcript":[22],"isoforms.":[23],"However,":[24],"manual":[25],"comparison":[26],"structures":[29],"across":[30,63,124],"transcripts":[32,110],"can":[33],"be":[34],"time-consuming":[35],"and":[36,44,76,89,96,129],"may":[37],"overlook":[38],"transcript-specific":[39,134],"differences":[40],"boundaries":[43],"sequence":[46],"(CDS)":[47],"composition.":[48],"Non3nExonFinder":[49,72,141,150],"was":[50],"developed":[51],"as":[52,113],"interactive":[54],"R/Shiny-based":[55],"tool":[56],"identifying":[58],"shared":[59],"non-triplet":[60],"exons":[62,84,103],"user-defined":[64],"human":[65,128],"or":[66],"mouse":[67],"NCBI":[68],"RefSeq":[69,121],"protein-coding":[70],"transcripts.":[71],"evaluates":[73],"exon/CDS":[74],"annotations":[75],"contributions":[78],"each":[80],"transcript,":[81],"identifies":[82],"common":[83],"identical":[86],"genomic":[87],"boundaries,":[88],"prioritizes":[90],"candidates":[91],"based":[92],"on":[93],"CDS-only":[94,102],"status":[95],"coding-length":[97],"divisibility":[98],"by":[99],"three.":[100],"Non-triplet":[101],"that":[104],"are":[105,111],"internal":[106],"all":[108,147],"selected":[109],"classified":[112],"high-confidence":[114],"candidates.":[115],"Independent":[116],"reconstruction":[117],"from":[118],"the":[119],"original":[120],"GTF":[122],"files":[123],"80":[125],"(40":[127],"40":[130],"mouse),":[131],"comprising":[132],"6,848":[133],"instances,":[136],"showed":[137],"complete":[138],"concordance":[139],"outputs,":[142],"exact":[144],"recovery":[145],"candidate":[148],"sets.":[149],"provides":[151],"a":[152],"reproducible":[153],"framework":[155],"transcript-aware":[157],"prioritization":[158],"exon-deletion":[160],"targets.":[161]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-29T00:00:00"}