{"id":"W3102488048","doi":"10.1093/nar/gkaa1036","title":"OpenProt 2021: deeper functional annotation of the coding potential of eukaryotic genomes","year":2020,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; PROTEO; Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Canada Research Chairs; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Compute Canada; Université de Sherbrooke","keywords":"RefSeq; Annotation; Biology; Ensembl; ORFS; Genome; Computational biology; Open reading frame; Proteogenomics; Genome project; Ribosome profiling; Resource (disambiguation); Computer science; Bioinformatics; Genomics; Genetics; Translation (biology); Messenger RNA; Gene; Peptide sequence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004809632,0.00007062533,0.0001088004,0.00003313313,0.0001140463,0.00001442402,0.0003168018,0.000094978,0.0004521813],"category_scores_gemma":[0.0002525463,0.00005358166,0.00008826947,0.0002013187,0.0001502932,0.000005272208,0.0002541378,0.0001216415,0.00001974894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008503836,"about_ca_system_score_gemma":0.0001124678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076481,"about_ca_topic_score_gemma":0.000001446907,"domain_scores_codex":[0.9987472,0.0002297346,0.0001850703,0.0002143618,0.0004446568,0.000178985],"domain_scores_gemma":[0.9993736,0.00002280484,0.00006193783,0.0002360981,0.0002490512,0.00005647945],"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":[0.0001731221,0.00002396549,0.001444373,0.00004014477,0.00003263023,7.824483e-7,0.00008498832,0.00008622197,0.9916818,0.0005269177,0.000648522,0.005256558],"study_design_scores_gemma":[0.0002861216,0.0002876465,0.009432635,0.000016498,0.000008498623,0.000002583955,0.0002475382,0.0002546628,0.9870403,0.000368567,0.001988527,0.00006646419],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925089,0.0004102437,0.004153149,0.001147982,0.00008587575,0.0003886382,0.00001832441,0.00000281301,0.001284],"genre_scores_gemma":[0.9985728,0.00009498886,0.0006954647,0.00006862201,0.0001990654,0.00001873912,0.00001360972,0.0000143204,0.000322353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007988263,"threshold_uncertainty_score":0.4951068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04828975142444485,"score_gpt":0.2968414377096892,"score_spread":0.2485516862852443,"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."}}