{"id":"W4401901310","doi":"10.1101/2024.08.26.609813","title":"Learning transcriptome architecture from sequence with a long-context RNA foundation model","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Research in Immunology and Cancer; McGill University; Mila - Quebec Artificial Intelligence Institute; Genome Canada","funders":"","keywords":"Foundation (evidence); Transcriptome; Context (archaeology); Architecture; RNA-Seq; RNA; Computational biology; Computer science; Biology; Gene expression; Geography; Genetics; Paleontology; Archaeology; Gene","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004044929,0.0003933747,0.0003251121,0.000258156,0.0002205685,0.0005243746,0.0005932961,0.0006509483,0.0009844754],"category_scores_gemma":[0.00120745,0.0003504498,0.0006672063,0.0001899639,0.0004588921,0.0004893598,0.0003670478,0.001045774,0.0002387142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006811984,"about_ca_system_score_gemma":0.000657184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002697039,"about_ca_topic_score_gemma":0.005556651,"domain_scores_codex":[0.9998819,0.00003631638,0.000004077648,0.00004709123,0.00001852488,0.0000121859],"domain_scores_gemma":[0.9994771,0.0003548962,0.0000387317,0.00005278811,0.00004937465,0.00002719077],"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":[0.00003317193,0.00001440444,0.0009444592,0.00002011901,0.00001816937,0.00005406533,0.00002171828,0.9775863,0.004558478,0.006768571,0.0004486001,0.009531962],"study_design_scores_gemma":[0.000001707666,0.000004577973,0.00006389657,0.000001210204,0.000001589328,0.000003532143,0.000001438826,0.9966128,0.0004344035,0.002776561,0.0000967713,0.000001425395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1600398,0.0001612419,0.8351763,0.0003639442,0.00003896655,0.00002756323,0.0005045194,0.001483093,0.002204563],"genre_scores_gemma":[0.8619956,0.000137747,0.133197,0.0001948295,0.00003885321,0.0001278474,0.001383548,0.0002066597,0.002718019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002697039,"threshold_uncertainty_score":0.005362689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01400219727410663,"score_gpt":0.219886685172135,"score_spread":0.2058844878980284,"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."}}