{"id":"W4411428681","doi":"10.1038/s42256-025-01044-4","title":"Generalized biological foundation model with unified nucleic acid and protein language","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"Limiting; Computer science; Foundation (evidence); Nucleic acid; Computational biology; Biological data; RNA; Artificial intelligence; Biology; Bioinformatics; Engineering; Genetics; 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":[0.0007220402,0.0003883427,0.0007423979,0.0006956526,0.0004504813,0.0008213961,0.001362401,0.0009309452,0.002097659],"category_scores_gemma":[0.002245794,0.0002867414,0.0008371478,0.0004525815,0.0009063127,0.001796099,0.0008012853,0.001041736,0.0004801574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016269,"about_ca_system_score_gemma":0.00161648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008938453,"about_ca_topic_score_gemma":0.01008276,"domain_scores_codex":[0.9997718,0.0000693259,0.00001058361,0.00005728429,0.00004628479,0.00004480227],"domain_scores_gemma":[0.9992102,0.000365066,0.00008819528,0.00008852088,0.0001685232,0.00007948374],"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":[0.0001099966,0.00005130698,0.002095927,0.0000536361,0.00005205594,0.0001811947,0.0001070624,0.8998992,0.002171821,0.07645527,0.00198475,0.01683776],"study_design_scores_gemma":[0.000005900978,0.000009643078,0.0001036952,0.000003238185,0.000003403143,0.00001130655,0.000004478913,0.9886603,0.0001188571,0.01075368,0.0003212078,0.00000418162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2884409,0.0006114489,0.6957332,0.001073363,0.0001213368,0.0000740645,0.001004156,0.001211595,0.0117299],"genre_scores_gemma":[0.9413614,0.0001995155,0.05106095,0.0002304511,0.00005240809,0.0001657255,0.001070163,0.00009762122,0.005761757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008938453,"threshold_uncertainty_score":0.01777285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008705454329113174,"score_gpt":0.2724784050386553,"score_spread":0.2637729507095421,"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."}}