{"id":"https://openalex.org/W7223036977","doi":"https://doi.org/10.1186/s12864-026-13421-3","title":"Gene body architecture predicts isoform diversity across eukaryotic genomes","display_name":"Gene body architecture predicts isoform diversity across eukaryotic genomes","publication_year":2026,"publication_date":"2026-10-21","ids":{"openalex":"https://openalex.org/W7223036977","doi":"https://doi.org/10.1186/s12864-026-13421-3"},"language":"en","primary_location":{"id":"doi:10.1186/s12864-026-13421-3","doi":"https://doi.org/10.1186/s12864-026-13421-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13421-3","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12864-026-13421-3","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159132180","display_name":"Quinton Brohart","orcid":"https://orcid.org/0009-0008-1089-8973","observed_orcids":["https://orcid.org/0009-0008-1089-8973"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I4401200393","display_name":"Ottawa Institute of Systems Biology","ror":"https://ror.org/047xz1e88","country_code":"CA","type":"facility","lineage":["https://openalex.org/I153718931","https://openalex.org/I4401200393"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Quinton Brohart","raw_affiliation_strings":["Department of Biochemistry, Microbiology & Immunology, University of Ottawa, Ottawa, Canada","Ottawa Institute of Systems Biology, Ottawa, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0008-1089-8973","affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Microbiology & Immunology, University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"Ottawa Institute of Systems Biology, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I4401200393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011450761","display_name":"Arvind Singh Mer","orcid":"https://orcid.org/0000-0001-8510-7963","observed_orcids":["https://orcid.org/0000-0001-8510-7963"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I4388482656","display_name":"Ottawa Hospital Research Institute","ror":"https://ror.org/05jtef216","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I153718931","https://openalex.org/I2800722420","https://openalex.org/I4388482656"]},{"id":"https://openalex.org/I4401200393","display_name":"Ottawa Institute of Systems Biology","ror":"https://ror.org/047xz1e88","country_code":"CA","type":"facility","lineage":["https://openalex.org/I153718931","https://openalex.org/I4401200393"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Arvind Mer","raw_affiliation_strings":["Department of Biochemistry, Microbiology & Immunology, University of Ottawa, Ottawa, Canada","Ottawa Hospital Research Institute, Ottawa, ON, Canada","Ottawa Institute of Systems Biology, Ottawa, ON, Canada","School of Electrical Engineering & Computer Science, University of Ottawa, Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8510-7963","affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Microbiology & Immunology, University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"Ottawa Hospital Research Institute, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I4388482656"]},{"raw_affiliation_string":"Ottawa Institute of Systems Biology, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I4401200393"]},{"raw_affiliation_string":"School of Electrical Engineering & Computer Science, University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011450761"],"corresponding_institution_ids":["https://openalex.org/I153718931","https://openalex.org/I4388482656","https://openalex.org/I4401200393"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68431105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9843999743461609,"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":0.9843999743461609,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.004399999976158142,"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":0.003599999938160181,"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/alternative-splicing","display_name":"alternative splicing","score":0.8199999928474426},{"id":"https://openalex.org/keywords/isoform-diversity","display_name":"isoform diversity","score":0.9359999895095825},{"id":"https://openalex.org/keywords/eukaryotic-genomes","display_name":"eukaryotic genomes","score":0.9330000281333923},{"id":"https://openalex.org/keywords/gene-structure","display_name":"gene structure","score":0.5189999938011169},{"id":"https://openalex.org/keywords/transcriptome","display_name":"transcriptome","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.8906999826431274},{"id":"https://openalex.org/C53345823","wikidata":"https://www.wikidata.org/wiki/Q5531554","display_name":"Gene isoform","level":3,"score":0.6358000040054321},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.635699987411499},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5321000218391418},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3959999978542328},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.3278999924659729},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.3000999987125397},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C81977670","wikidata":"https://www.wikidata.org/wiki/Q585259","display_name":"Genetic diversity","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C186836561","wikidata":"https://www.wikidata.org/wiki/Q1931516","display_name":"Microarray","level":4,"score":0.2863999903202057},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s12864-026-13421-3","doi":"https://doi.org/10.1186/s12864-026-13421-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13421-3","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s12864-026-13421-3","doi":"https://doi.org/10.1186/s12864-026-13421-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12864-026-13421-3","pdf_url":null,"source":{"id":"https://openalex.org/S28614077","display_name":"BMC Genomics","issn_l":"1471-2164","issn":["1471-2164"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Genomics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392750655","https://openalex.org/W2077811489","https://openalex.org/W4399506197","https://openalex.org/W4410148190","https://openalex.org/W4386268661","https://openalex.org/W4417070499","https://openalex.org/W4378172336","https://openalex.org/W4411946888","https://openalex.org/W4417297365","https://openalex.org/W4327683133"],"abstract_inverted_index":{"Alternative":[0],"splicing":[1],"generates":[2],"transcript":[3,55,209],"and":[4,27,38,48,57,76,90,109,122,126,145,152,185,189,198],"isoform":[5,32,64,114,140,177],"diversity,":[6],"but":[7,72],"the":[8,35,205],"gene-level":[9,58],"features":[10,29,159,184],"that":[11,63,156],"distinguish":[12],"isoform-rich":[13,80],"genes":[14,17,81],"from":[15],"simpler":[16],"remain":[18],"incompletely":[19],"defined.":[20],"We":[21],"examined":[22],"whether":[23,39],"structural,":[24],"regulatory,":[25],"sequence-derived,":[26],"functional":[28],"jointly":[30],"explain":[31],"complexity":[33],"in":[34,107,149,175],"human":[36,139],"genome":[37,75],"these":[40],"relationships":[41],"are":[42],"conserved":[43,182],"across":[44,68],"mouse,":[45],"Drosophila":[46,110],",":[47],"zebrafish":[49],"genomes":[50],"as":[51],"well.":[52],"Using":[53],"curated":[54],"annotations":[56],"biomolecular":[59],"features,":[60],"we":[61],"found":[62],"diversity":[65,178],"is":[66,179],"pervasive":[67],"all":[69],"four":[70],"species":[71],"varies":[73],"by":[74,181,187],"biotype.":[77],"Across":[78],"species,":[79],"were":[82,96],"consistently":[83],"associated":[84,118,128],"with":[85,99,119,129,142],"longer":[86],"introns,":[87],"shorter":[88],"exons,":[89],"increased":[91],"exon-intron":[92],"organization.":[93],"UTR":[94,101],"associations":[95,106],"more":[97],"variable,":[98],"3\u2032":[100],"length":[102],"showing":[103],"stronger":[104],"positive":[105],"humans":[108],".":[111],"In":[112],"humans,":[113],"count":[115],"was":[116],"negatively":[117],"GC":[120],"content":[121],"CpG":[123],"island":[124],"density":[125],"positively":[127],"protein-protein":[130],"interaction":[131],"network":[132],"size.":[133],"Machine":[134],"learning":[135],"based":[136],"modeling":[137],"predicted":[138],"counts":[141],"strong":[143],"performance":[144],"retained":[146],"predictive":[147,194],"signal":[148],"mouse.":[150],"PCA":[151],"UMAP":[153],"further":[154],"showed":[155],"isoform-associated":[157],"gene":[158,168],"form":[160],"a":[161,173],"continuous,":[162],"structured":[163],"manifold":[164],"rather":[165],"than":[166],"discrete":[167],"classes.":[169],"These":[170],"findings":[171],"support":[172],"model":[174],"which":[176],"shaped":[180],"gene-structural":[183],"modulated":[186],"lineage-":[188],"biotype-specific":[190],"regulatory":[191],"architecture.":[192],"Integrating":[193],"modeling,":[195],"feature":[196],"attribution,":[197],"dimensionality":[199],"reduction":[200],"provides":[201],"complementary":[202],"insight":[203],"into":[204],"genomic":[206],"organization":[207],"underlying":[208],"diversity.":[210]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-10-21T00:00:00"}
