{"id":"W4412068931","doi":"10.1101/2025.07.03.662928","title":"An expanded reference catalog of translated open reading frames for biomedical research","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Institute of Cancer Research; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"National Cancer Institute; National Institutes of Health; HORIZON EUROPE European Innovation Council; European Molecular Biology Laboratory; Oncode Institute; CureSearch for Children's Cancer; Stichting Villa Joep; Deutsche Forschungsgemeinschaft; National Human Genome Research Institute; Morgan Adams Foundation; Hope Foundation; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; European Commission; Hyundai Hope On Wheels; National Science Foundation","keywords":"Annotation; Computer science; Ensembl; Set (abstract data type); Reading (process); Information retrieval; Limiting; Data science; Artificial intelligence; Genome; Genomics; Linguistics; Biology; 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":[0.01300296,0.001644176,0.002642242,0.01808471,0.001472972,0.003901045,0.003213002,0.001903267,0.01964587],"category_scores_gemma":[0.027941,0.000634574,0.00177249,0.01552163,0.0007957079,0.003375145,0.003394295,0.002779473,0.01883521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001973741,"about_ca_system_score_gemma":0.007635118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00569857,"about_ca_topic_score_gemma":0.008057295,"domain_scores_codex":[0.9938252,0.001177709,0.001621355,0.001417997,0.001637382,0.0003204333],"domain_scores_gemma":[0.9728621,0.007726181,0.002087369,0.005466786,0.01090265,0.0009548092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005776828,0.0001473735,0.008701187,0.01505897,0.0003189105,0.001142143,0.001417738,0.001474467,0.0466604,0.02241733,0.3168303,0.5852536],"study_design_scores_gemma":[0.00004076515,0.00007449342,0.00810038,0.002461628,0.000248332,0.0008096823,0.0001582229,0.0007889824,0.005617692,0.004505323,0.9770887,0.0001057521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03330122,0.1425484,0.215952,0.007755339,0.009443824,0.0008945706,0.5231531,0.01627066,0.05068088],"genre_scores_gemma":[0.02323673,0.03828759,0.1957489,0.002349375,0.001448182,0.0009727028,0.726222,0.002378702,0.009355908],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01964587,"threshold_uncertainty_score":0.06876707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05264798121583906,"score_gpt":0.3384967615387492,"score_spread":0.2858487803229101,"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."}}