{"id":"https://openalex.org/W7225612174","doi":"https://doi.org/10.21203/rs.3.rs-11435705/v1","title":"The Alternative but Intolerant Paradox: Non-Canonical (GC-AG and AT-AC) Splice Sites Break the Standard Evolutionary Rules of Splicing","display_name":"The Alternative but Intolerant Paradox: Non-Canonical (GC-AG and AT-AC) Splice Sites Break the Standard Evolutionary Rules of Splicing","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225612174","doi":"https://doi.org/10.21203/rs.3.rs-11435705/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11435705/v1","doi":"https://doi.org/10.21203/rs.3.rs-11435705/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11435705/v1","pdf_url":"https://www.researchsquare.com/article/rs-11435705/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","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.researchsquare.com/article/rs-11435705/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120026367","display_name":"Kelvin Msoka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405279685","display_name":"Tanzania Veterinary Laboratory Agency","ror":"https://ror.org/01vqrfz95","country_code":"TZ","type":"government","lineage":["https://openalex.org/I248621492","https://openalex.org/I4405279685","https://openalex.org/I4405280427"]}],"countries":["TZ"],"is_corresponding":true,"raw_author_name":"Kelvin Msoka","raw_affiliation_strings":["Tanzania Veterinary Laboratory Agency"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tanzania Veterinary Laboratory Agency","institution_ids":["https://openalex.org/I4405279685"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5120026367"],"corresponding_institution_ids":["https://openalex.org/I4405279685"],"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":0.9955999851226807,"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":0.9955999851226807,"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":0.0020000000949949026,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.0005000000237487257,"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/non-canonical-splice-sites","display_name":"non-canonical splice sites","score":0.9900000095367432},{"id":"https://openalex.org/keywords/alternative-splicing","display_name":"alternative splicing","score":0.875},{"id":"https://openalex.org/keywords/purifying-selection","display_name":"purifying selection","score":0.7699999809265137},{"id":"https://openalex.org/keywords/population-genetic-diversity","display_name":"population genetic variation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/variant-burden","display_name":"variant burden","score":0.7879999876022339}],"concepts":[{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.8705000281333923},{"id":"https://openalex.org/C194583182","wikidata":"https://www.wikidata.org/wiki/Q21114084","display_name":"Alternative splicing","level":4,"score":0.7688000202178955},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6740999817848206},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.5978999733924866},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.5630999803543091},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5117999911308289},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4577000141143799},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4075999855995178},{"id":"https://openalex.org/C3641667","wikidata":"https://www.wikidata.org/wiki/Q1295959","display_name":"Effective population size","level":4,"score":0.390500009059906},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3887999951839447},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C195054827","wikidata":"https://www.wikidata.org/wiki/Q504568","display_name":"Founder effect","level":5,"score":0.3587000072002411},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.35040000081062317},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C2779040068","wikidata":"https://www.wikidata.org/wiki/Q7229807","display_name":"Population genomics","level":5,"score":0.30790001153945923},{"id":"https://openalex.org/C44465124","wikidata":"https://www.wikidata.org/wiki/Q713623","display_name":"Clade","level":4,"score":0.30149999260902405},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C26589402","wikidata":"https://www.wikidata.org/wiki/Q7068267","display_name":"Nucleotide diversity","level":5,"score":0.2702000141143799},{"id":"https://openalex.org/C62257209","wikidata":"https://www.wikidata.org/wiki/Q5487490","display_name":"Splice site mutation","level":5,"score":0.26809999346733093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11435705/v1","doi":"https://doi.org/10.21203/rs.3.rs-11435705/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11435705/v1","pdf_url":"https://www.researchsquare.com/article/rs-11435705/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11435705/v1","doi":"https://doi.org/10.21203/rs.3.rs-11435705/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11435705/v1","pdf_url":"https://www.researchsquare.com/article/rs-11435705/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","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/W7225612174.pdf","grobid_xml":"https://content.openalex.org/works/W7225612174.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117974740","https://openalex.org/W2951214078","https://openalex.org/W7169755097","https://openalex.org/W2155684118","https://openalex.org/W7225137601","https://openalex.org/W7070875115","https://openalex.org/W4408532459","https://openalex.org/W2112767659","https://openalex.org/W2163570826","https://openalex.org/W3008717153"],"abstract_inverted_index":{"Abstract":[0],"Background:":[1],"The":[2],"prevailing":[3],"evolutionary":[4,100,209],"paradigm":[5],"in":[6,222,250],"splicing":[7],"dictates":[8],"that":[9,26],"constitutive":[10],"splice":[11,20,43,76,203],"sites":[12,21,44,162,176,194,204],"are":[13,49,119],"under":[14],"strict":[15],"purifying":[16],"selection,":[17],"while":[18],"alternative":[19,123],"act":[22],"as":[23],"\"evolutionary":[24],"sponges\"":[25],"tolerate":[27],"higher":[28],"levels":[29],"of":[30,72,143,248],"genetic":[31,146],"variation":[32,147],"to":[33,62,133,159,187,244],"facilitate":[34],"transcript":[35,91],"diversity.":[36],"However,":[37,131],"it":[38],"remains":[39],"unknown":[40],"whether":[41],"non-canonical":[42,237],"(GC-AG":[45],"and":[46,84,106,154],"AT-AC)":[47,157],"which":[48],"predominantly":[50,255],"alternativefollow":[51],"this":[52],"standard":[53,135,207],"rule":[54],"or":[55],"if":[56],"their":[57,90,220],"specialized":[58],"roles":[59],"subject":[60],"them":[61],"distinct":[63],"population-genetic":[64],"constraints.":[65],"Methods:":[66],"I":[67,88],"conducted":[68],"a":[69,94,139,240],"systematic":[70],"analysis":[71],"492,133":[73],"unique":[74],"human":[75],"junctions":[77,118],"from":[78],"GENCODE":[79],"v50,":[80],"isolating":[81],"8,007":[82],"GC-AG":[83,153,175],"278":[85],"AT-AC":[86,193],"junctions.":[87],"quantified":[89],"usage":[92,124],"using":[93,110],"continuous":[95],"\"architecture":[96],"fraction\"":[97],"metric,":[98],"nucleotide-level":[99],"conservation":[101,170,181],"(phyloP":[102],"across":[103],"100":[104],"vertebrates),":[105],"population":[107,145,234],"variant":[108,149],"burden":[109],"1000":[111],"Genomes":[112],"Phase":[113],"3":[114],"data.":[115],"Results:":[116],"Non-canonical":[117,202],"overwhelmingly":[120],"skewed":[121],"toward":[122],"(Kruskal-Wallis":[125],"p":[126],"=":[127,164,184,190,199],"2.94":[128],"\u00d7":[129],"10\u207b\u00b2\u2079\u2076).":[130],"contrary":[132],"the":[134,167,206,231,246],"paradigm,":[136],"they":[137],"harbor":[138],"significantly":[140],"lower":[141],"density":[142],"standing":[144],"(median":[148,163],"counts:":[150],"61.0":[151],"for":[152,156,236],"74.0":[155],"compared":[158,186],"canonical":[160,257],"GT-AG":[161,188,258],"81.0).":[165],"At":[166],"nucleotide":[168],"level,":[169],"profiles":[171],"reveal":[172],"striking":[173],"divergence:":[174],"display":[177],"attenuated":[178],"donor":[179],"motif":[180],"(mean":[182,189,198],"phyloP":[183],"2.00)":[185],"4.50),":[191],"whereas":[192],"exhibit":[195],"intense":[196],"hyper-conservation":[197],"6.23).":[200],"Conclusions:":[201],"break":[205],"\"alternative-tolerant\"":[208],"rule,":[210],"exhibiting":[211],"an":[212],"\"alternative":[213],"but":[214],"intolerant\"":[215],"phenotype.":[216],"This":[217],"paradox":[218],"reflects":[219],"localization":[221],"highly":[223],"constrained,":[224],"essential":[225],"genomic":[226],"regions.":[227],"These":[228],"findings":[229],"provide":[230],"first":[232],"empirical":[233],"baseline":[235],"sites,":[238],"offering":[239],"vital":[241],"calibration":[242],"dataset":[243],"prevent":[245],"misclassification":[247],"variants":[249],"clinical":[251],"genomics":[252],"pipelines":[253],"trained":[254],"on":[256],"sites.":[259]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
