{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001665233,0.000160376,0.0001307398,0.00004811839,0.00008241283,0.00003461505,0.0001878713,0.0003122563,0.00002772198],"category_scores_gemma":[0.0001119113,0.0001124653,0.00003474741,0.0001134089,0.00006965129,0.000004307155,0.00008906848,0.0002081335,0.000004015822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008686879,"about_ca_system_score_gemma":0.00004322986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001818948,"about_ca_topic_score_gemma":0.00003514892,"domain_scores_codex":[0.9992021,0.00006508963,0.0001340278,0.0003555277,0.00008746785,0.0001557632],"domain_scores_gemma":[0.9995879,0.000009369561,0.00005002735,0.0002566028,0.00005471669,0.00004140661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002585517,0.00002414435,0.00009775564,0.00001665773,0.00002782753,0.00000297117,0.00002888067,0.00009918658,0.9564614,0.01529798,0.00003570082,0.02764892],"study_design_scores_gemma":[0.0001475816,0.0001599956,0.0000602203,0.00003182928,0.00001048882,0.00000734729,0.0000311996,0.003322715,0.9903886,0.003998848,0.001681881,0.000159296],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7556028,0.003227805,0.2386031,0.0004753539,0.00005053153,0.0004107404,0.000009646233,0.00003073533,0.001589286],"genre_scores_gemma":[0.9818397,0.0001505537,0.01571748,0.000581577,0.00004307888,0.00004762894,0.00006645217,0.0000115487,0.001541967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2262369,"threshold_uncertainty_score":0.4586203,"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."}}