{"id":"https://openalex.org/W7214678343","doi":"https://doi.org/10.64898/2026.09.24.754173","title":"RNASeek: A Cross-Phyla Generative Foundation Model for Multipurpose RNA Modeling and Reinforcement Learning-Based Design","display_name":"RNASeek: A Cross-Phyla Generative Foundation Model for Multipurpose RNA Modeling and Reinforcement Learning-Based Design","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214678343","doi":"https://doi.org/10.64898/2026.09.24.754173","pmid":"https://pubmed.ncbi.nlm.nih.gov/42856293","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13648417"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.24.754173","doi":"https://doi.org/10.64898/2026.09.24.754173","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754173","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754173.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","license_id":"https://openalex.org/licenses/cc-by","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754173.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104047822","display_name":"Shiyuan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyuan Chen","raw_affiliation_strings":["Graduate program in Genetics, Genomics and Bioinformatics, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate program in Genetics, Genomics and Bioinformatics, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128882694","display_name":"Neil R. Fernandes","orcid":"https://orcid.org/0009-0003-5043-9353","observed_orcids":["https://orcid.org/0009-0003-5043-9353"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil R. Fernandes","raw_affiliation_strings":["Division of Biomedical Sciences, School of Medicine, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biomedical Sciences, School of Medicine, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102991986","display_name":"Wei Vivian Li","orcid":"https://orcid.org/0000-0002-2087-2709","observed_orcids":["https://orcid.org/0000-0002-2087-2709","https://orcid.org/0000-0002-9288-5648"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Vivian Li","raw_affiliation_strings":["Department of Statistics, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153336970","display_name":"Lili Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lili Wang","raw_affiliation_strings":["Department of Medical Sciences, Irving Medical Center, Columbia University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Sciences, Irving Medical Center, Columbia University, NY, USA","institution_ids":["https://openalex.org/I2799503643","https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140611249","display_name":"Zhenyu Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenyu Jia","raw_affiliation_strings":["Department of Botany & Plant Sciences, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Botany & Plant Sciences, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046263844","display_name":"Joy S. Xiang","orcid":"https://orcid.org/0000-0002-6400-1876","observed_orcids":["https://orcid.org/0000-0002-6400-1876"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joy S. Xiang","raw_affiliation_strings":["Division of Biomedical Sciences, School of Medicine, University of California, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6400-1876","affiliations":[{"raw_affiliation_string":"Division of Biomedical Sciences, School of Medicine, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046263844"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9932000041007996,"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":0.9932000041007996,"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/T12610","display_name":"RNA regulation and disease","score":0.001500000013038516,"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/T10604","display_name":"RNA Research and Splicing","score":0.0007999999797903001,"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/generative-foundation-models","display_name":"generative foundation models","score":0.7770000100135803},{"id":"https://openalex.org/keywords/rna-sequence-design","display_name":"RNA sequence design","score":0.8790000081062317},{"id":"https://openalex.org/keywords/mrna-stability","display_name":"mRNA stability","score":0.7170000076293945},{"id":"https://openalex.org/keywords/exon-intron-boundaries","display_name":"exon-intron boundaries","score":0.7039999961853027},{"id":"https://openalex.org/keywords/deepseek","display_name":"DeepSeek","score":0.5189999938011169},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.9089999794960022},{"id":"https://openalex.org/keywords/rna-function-prediction","display_name":"RNA function prediction","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C76346623","wikidata":"https://www.wikidata.org/wiki/Q205858","display_name":"Ribozyme","level":4,"score":0.8245000243186951},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49070000648498535},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C1342335","wikidata":"https://www.wikidata.org/wiki/Q6545871","display_name":"Ligase ribozyme","level":5,"score":0.4691999852657318},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43709999322891235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C148625055","wikidata":"https://www.wikidata.org/wiki/Q418840","display_name":"Riboswitch","level":5,"score":0.413100004196167},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39910000562667847},{"id":"https://openalex.org/C105130999","wikidata":"https://www.wikidata.org/wiki/Q414976","display_name":"Pseudoknot","level":4,"score":0.398499995470047},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3172000050544739},{"id":"https://openalex.org/C126142528","wikidata":"https://www.wikidata.org/wiki/Q3771876","display_name":"Nucleic acid structure","level":4,"score":0.3158999979496002},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.24.754173","doi":"https://doi.org/10.64898/2026.09.24.754173","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754173","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754173.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13648417","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13648417/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13648417/pdf/nihpp-2026.09.24.754173v1.pdf","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmid:42856293","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856293","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.09.24.754173","doi":"https://doi.org/10.64898/2026.09.24.754173","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754173","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754173.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G203323003","display_name":"Acquisition of a Scalable Storage Cluster for Data Intensive NIH Research","funder_award_id":"S10OD016290","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2939395128","display_name":"Research Infrastructure: MRI: Acquisition of a Big Data HPC Cluster for Interdisciplinary Research and Training","funder_award_id":"2215705","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4970370522","display_name":"MRI: Acquisition of a Big Data Compute Cluster for Interdisciplinary Research","funder_award_id":"1429826","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214678343.pdf","grobid_xml":"https://content.openalex.org/works/W7214678343.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4410808104","https://openalex.org/W4413786633"],"related_works":["https://openalex.org/W4403023684","https://openalex.org/W4390975839","https://openalex.org/W7155526483","https://openalex.org/W7154387017","https://openalex.org/W7129011143","https://openalex.org/W7222441505","https://openalex.org/W4402839662","https://openalex.org/W4406696763","https://openalex.org/W4409345421","https://openalex.org/W4412785638"],"abstract_inverted_index":{"RNA":[0,34,65,206],"plays":[1],"central":[2],"roles":[3],"in":[4,91],"regulating":[5],"information":[6],"flow":[7],"and":[8,27,57,68,76,88,104,119,139,161,191,214],"provides":[9,215],"a":[10,30,47,54,60,80,92,199,216],"versatile":[11],"substrate":[12],"for":[13,64,219],"engineering":[14,220],"biological":[15],"functions.":[16],"While":[17],"large":[18],"language":[19,25],"models":[20,36,138],"(LLMs)":[21],"have":[22],"transformed":[23],"natural":[24],"processing":[26],"protein":[28],"design,":[29],"general":[31,217],"framework":[32,202],"connecting":[33],"foundation":[35,50],"to":[37,99,146,208],"functional":[38,134],"sequence":[39,66,77,110,212],"design":[40,78,213],"remains":[41],"limited.":[42],"Here,":[43],"we":[44],"present":[45],"RNASeek,":[46],"1.6-billion-parameter":[48],"generative":[49],"model":[51],"built":[52],"on":[53,59],"DeepSeek":[55],"architecture":[56],"trained":[58],"cross-phyla":[61],"transcriptomic":[62],"corpus":[63],"representation":[67],"generation.":[69],"Natural-language":[70],"tokens":[71],"enable":[72],"flexible":[73],"conditional":[74],"prediction":[75],"using":[79],"unified":[81,200],"backbone.":[82],"RNASeek":[83,98,197],"captures":[84],"species-specific":[85],"transcript":[86],"features":[87,111],"intron-exon":[89],"boundaries":[90],"zero-shot":[93],"setting.":[94],"We":[95,131],"then":[96],"fine-tune":[97],"predict":[100],"ribozyme":[101,116],"self-cleavage":[102],"activity":[103],"viral":[105],"mRNA":[106,129],"stability,":[107,121],"revealing":[108],"interpretable":[109],"associated":[112,127],"with":[113,128,153,223],"function,":[114],"including":[115],"loop":[117],"flexibility":[118],"stem":[120],"as":[122,124,136],"well":[123],"AU-rich":[125],"motifs":[126],"stability.":[130],"use":[132],"these":[133],"predictors":[135],"reward":[137],"apply":[140],"Group":[141],"Relative":[142],"Policy":[143],"Optimization":[144],"(GRPO)":[145],"update":[147],"RNASeek's":[148],"generation":[149,157],"policy":[150],"toward":[151],"sequences":[152,183],"desired":[154,224],"properties.":[155,225],"GRPO-guided":[156],"produces":[158],"faster-cleaving":[159],"ribozymes":[160,173],"stability-enhancing":[162],"3'":[163,181,194],"UTRs":[164],"while":[165,179],"satisfying":[166],"user-specified":[167],"IUPAC":[168],"constraints.":[169],"Experimentally":[170],"validated":[171],"RNASeek-generated":[172,180],"achieve":[174],"wild-type":[175],"levels":[176],"of":[177,187],"activity,":[178],"UTR":[182],"exceed":[184],"the":[185,188],"performance":[186],"training":[189],"data":[190],"benchmarked":[192],"AI-generated":[193],"UTRs.":[195],"Together,":[196],"establishes":[198],"pretrain-predict-optimize":[201],"that":[203],"connects":[204],"learned":[205],"function":[207],"controllable":[209],"de":[210],"novo":[211],"strategy":[218],"regulatory":[221],"RNAs":[222]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-09-29T00:00:00"}