{"id":"W4409150422","doi":"10.1038/s41467-025-58588-7","title":"CodonTransformer: a multispecies codon optimizer using context-aware neural networks","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; The Scarborough Hospital","funders":"University of Toronto Scarborough; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fondation Bettencourt Schueller; Centre National de la Recherche Scientifique; University of Toronto; Institut National de la Santé et de la Recherche Médicale","keywords":"Computer science; ENCODE; Genetic code; Codon usage bias; Security token; Encoding (memory); Context (archaeology); Theoretical computer science; Robustness (evolution); Artificial intelligence; Computational biology; Genome; DNA; Biology; Genetics; Gene; Computer network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005113566,0.0009711874,0.0005850382,0.0003311176,0.0003299712,0.000620831,0.001632445,0.001077097,0.004348775],"category_scores_gemma":[0.001235369,0.0005091189,0.0008532628,0.0002917592,0.0003694241,0.001037317,0.0008322563,0.001460531,0.001503024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008844353,"about_ca_system_score_gemma":0.001080375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004416673,"about_ca_topic_score_gemma":0.007858019,"domain_scores_codex":[0.9998597,0.00002666153,0.00000838352,0.00004958309,0.00003342288,0.00002230156],"domain_scores_gemma":[0.9998184,0.00007315558,0.00002121622,0.00003324006,0.00003534872,0.00001859381],"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":[0.0005120049,0.0002646388,0.003787708,0.0003284304,0.0002548975,0.0003425429,0.000137502,0.7295243,0.03943174,0.01321653,0.01843968,0.1937601],"study_design_scores_gemma":[0.00002054271,0.00003719038,0.0001081022,0.00000689941,0.000009838713,0.00002787913,0.000005568551,0.9893594,0.005557864,0.002868103,0.00198776,0.00001096289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09774497,0.0008264775,0.844619,0.0004677054,0.0002783567,0.0001905846,0.001895734,0.04833797,0.005639232],"genre_scores_gemma":[0.4545475,0.0004308476,0.5277152,0.0005587548,0.00005747599,0.0004061935,0.003798873,0.003892593,0.008592592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004416673,"threshold_uncertainty_score":0.01454812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0187407699122401,"score_gpt":0.2981871889560236,"score_spread":0.2794464190437835,"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."}}