{"id":"W7117134935","doi":"10.64898/2025.12.22.695962","title":"Large generative mRNA language foundation model for efficient coding sequence generation and design with mRNA-GPT","year":2025,"lang":"","type":"article","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Cybermedia Center, Osaka University; Kitasato University; National Institute of Advanced Industrial Science and Technology","keywords":"Messenger RNA; Generative grammar; Coding (social sciences); Transformer; Generative model; Coding region; Translation (biology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005483368,0.0008583892,0.0006477467,0.0004209701,0.0003002494,0.0006725928,0.001161663,0.001174046,0.00364998],"category_scores_gemma":[0.002204477,0.0005491556,0.001239787,0.0003945832,0.000654453,0.0008878959,0.0006462486,0.001767364,0.001408364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043898,"about_ca_system_score_gemma":0.0009908675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00469598,"about_ca_topic_score_gemma":0.007442478,"domain_scores_codex":[0.9997794,0.00005134245,0.00001117561,0.00007255944,0.00004557991,0.00004002354],"domain_scores_gemma":[0.999302,0.0004397142,0.00004245392,0.00006419209,0.0001184848,0.00003312394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005579068,0.00003096652,0.000725049,0.00005793313,0.00002471425,0.000123567,0.00004481377,0.9643547,0.00465433,0.00518398,0.001974903,0.02276919],"study_design_scores_gemma":[0.000004650631,0.000008919334,0.00002511296,0.000002007978,0.000003380542,0.000009894915,0.000002475832,0.9973233,0.0007885252,0.001575329,0.0002541493,0.000002195426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1477598,0.0008153229,0.8354279,0.0009082448,0.0001928246,0.0001205966,0.001311136,0.00606176,0.007402433],"genre_scores_gemma":[0.8220229,0.0003364373,0.1646189,0.0007088929,0.00006657343,0.0003691969,0.003027062,0.0008615616,0.007988607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00469598,"threshold_uncertainty_score":0.01221043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02406877019909174,"score_gpt":0.2704597717761565,"score_spread":0.2463910015770648,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}