{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002486614,0.0003736938,0.0005739914,0.0002697643,0.0001837453,0.0001443832,0.001752232,0.001217968,0.00001795098],"category_scores_gemma":[0.0005758044,0.0003830729,0.0001305757,0.0003340797,0.0002098087,0.00001637042,0.0006972317,0.0004695839,0.000003264406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005118051,"about_ca_system_score_gemma":0.001124168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001547829,"about_ca_topic_score_gemma":0.000004595432,"domain_scores_codex":[0.9969828,0.000417054,0.0005588246,0.001058199,0.0003588298,0.0006242815],"domain_scores_gemma":[0.9970399,0.00009472489,0.0002453457,0.001621348,0.0007218849,0.0002767986],"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":[0.0002368927,0.0002185789,0.0002399991,0.0004414176,0.0001555371,0.000002534374,0.00001685641,0.000003375532,0.9970351,0.001169616,0.0004524676,0.00002760643],"study_design_scores_gemma":[0.00050109,0.0003598616,0.0005642028,0.0005007815,0.00005315318,1.119618e-8,0.000008799919,0.00004783321,0.9833125,0.00004585503,0.0141942,0.0004117153],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9684533,0.002282014,0.02292323,0.0002037152,0.0007446171,0.003101557,0.002143047,0.00008269175,0.00006575038],"genre_scores_gemma":[0.9770772,0.0003380376,0.0213549,0.00006376289,0.0002684937,0.000781936,0.00001870966,0.00006693228,0.00003003521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01374174,"threshold_uncertainty_score":0.9998621,"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."}}