{"id":"https://openalex.org/W7160856559","doi":"https://doi.org/10.1093/bioinformatics/btag285","title":"CodonMoE: DNA language models for codon-dependent mRNA prediction","display_name":"CodonMoE: DNA language models for codon-dependent mRNA prediction","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160856559","doi":"https://doi.org/10.1093/bioinformatics/btag285","pmid":"https://pubmed.ncbi.nlm.nih.gov/42108565"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag285","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag285","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135865207","display_name":"Shiyi Du","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyi Du","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135898940","display_name":"Litian Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Litian Liang","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027903849","display_name":"J Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Li","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,"],"raw_orcid":"https://orcid.org/0000-0002-0118-5516","affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , PA 15213,","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113653378"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5109138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.7678999900817871,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.7678999900817871,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.08789999783039093,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.01730000041425228,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/adapter","display_name":"Adapter (computing)","score":0.5928000211715698},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49239999055862427},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4318000078201294},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.40959998965263367},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.367900013923645},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3440999984741211},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013999819755554},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4871000051498413},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C10853874","wikidata":"https://www.wikidata.org/wiki/Q180618","display_name":"Genetic code","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27959999442100525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2556000053882599}],"mesh":[{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag285","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag285","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42108565","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42108565","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13224961","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13224961/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag285","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag285","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6568096280097961,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3788099519","display_name":null,"funder_award_id":"R01HG012470","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3858817854","display_name":null,"funder_award_id":"III-2232121","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2025653905","https://openalex.org/W2137983211","https://openalex.org/W2150884987","https://openalex.org/W2883945062","https://openalex.org/W2902966040","https://openalex.org/W2935703330","https://openalex.org/W3127238141","https://openalex.org/W3166142427","https://openalex.org/W3177828909","https://openalex.org/W3203588026","https://openalex.org/W3211795435","https://openalex.org/W4213095938","https://openalex.org/W4220991830","https://openalex.org/W4297243391","https://openalex.org/W4318669939","https://openalex.org/W4388979610","https://openalex.org/W4400188610"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Genomic":[1],"language":[2,74,164],"models":[3,16,35,75,123],"(gLMs)":[4],"face":[5],"a":[6,68,89,158],"fundamental":[7],"efficiency":[8],"challenge:":[9],"one":[10],"must":[11],"either":[12],"maintain":[13],"separate":[14],"specialized":[15,144],"for":[17,185],"each":[18],"biological":[19,41],"modality":[20],"(DNA":[21],"and":[22,50,120,171,188],"RNA)":[23],"or":[24],"develop":[25],"large":[26],"multimodal":[27],"architectures.":[28],"Both":[29],"approaches":[30],"impose":[31],"significant":[32],"computational":[33,173],"burdens-modality-specific":[34],"require":[36],"redundant":[37],"infrastructure":[38],"despite":[39],"inherent":[40],"connections,":[42],"while":[43,151,175],"multi-modal":[44],"architectures":[45],"demand":[46],"increased":[47],"parameter":[48],"counts":[49],"extensive":[51],"cross-modality":[52],"pretraining.":[53,82],"RESULTS:":[54],"To":[55],"address":[56],"this":[57],"limitation,":[58],"we":[59],"introduce":[60],"CodonMoE":[61,87,126],"(Adaptive":[62],"Mixture":[63],"of":[64,97],"Codon":[65],"Reformative":[66],"Experts),":[67],"lightweight":[69],"adapter":[70],"that":[71],"transforms":[72],"DNA":[73,122,169],"into":[76],"effective":[77],"RNA":[78,106,114,145],"analyzers":[79],"without":[80],"RNA-specific":[81],"Our":[83],"theoretical":[84],"analysis":[85],"establishes":[86],"as":[88],"universal":[90],"approximator":[91],"at":[92,195],"the":[93,133,186,191],"codon":[94,102],"level,":[95],"capable":[96],"mapping":[98],"arbitrary":[99],"functions":[100],"from":[101],"sequences":[103],"to":[104,189],"codon-dependent":[105],"properties":[107],"given":[108],"sufficient":[109],"expert":[110],"capacity.":[111],"Across":[112],"four":[113],"prediction":[115],"tasks":[116],"spanning":[117],"stability,":[118],"expression,":[119],"regulation,":[121],"augmented":[124],"with":[125,132],"significantly":[127],"outperform":[128],"their":[129],"unmodified":[130],"counterparts,":[131],"HyenaDNA+CodonMoE":[134],"series":[135],"achieving":[136,152],"state-of-the-art":[137],"results":[138,192],"using":[139],"80%":[140],"fewer":[141],"parameters":[142],"than":[143],"models.":[146],"By":[147],"maintaining":[148],"sub-quadratic":[149],"complexity":[150],"superior":[153],"performance,":[154],"our":[155],"approach":[156],"provides":[157],"principled":[159],"path":[160],"toward":[161],"unifying":[162],"genomic":[163],"modeling,":[165],"leveraging":[166],"more":[167],"abundant":[168],"data":[170],"reducing":[172],"overhead":[174],"preserving":[176],"modality-specific":[177],"performance":[178],"advantages.":[179],"AVAILABILITY":[180],"AND":[181],"IMPLEMENTATION:":[182],"Source":[183],"code":[184],"method":[187],"reproduce":[190],"is":[193],"available":[194],"https://github.com/Kingsford-Group/CodonMoE.":[196]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2026-05-12T00:00:00"}