{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003281655,0.003460434,0.002352888,0.007107585,0.00174934,0.004937985,0.002158459,0.001704477,0.02453714],"category_scores_gemma":[0.006227064,0.001646242,0.002518568,0.005824334,0.000520549,0.003215795,0.003569844,0.002611148,0.03237446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008782713,"about_ca_system_score_gemma":0.002047954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002076318,"about_ca_topic_score_gemma":0.002865064,"domain_scores_codex":[0.9976828,0.0003790138,0.0002731668,0.0006172482,0.0007391278,0.0003086119],"domain_scores_gemma":[0.9965684,0.0009839332,0.0006401769,0.0005738542,0.0008465605,0.0003870277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003488474,0.0002008292,0.005567759,0.007557648,0.0006259286,0.001224798,0.001111508,0.001371657,0.09450959,0.00485851,0.7139294,0.1655539],"study_design_scores_gemma":[0.0002220681,0.0002157763,0.01128214,0.0007931326,0.0002822928,0.001765109,0.0002541424,0.002637421,0.01956868,0.005006243,0.957699,0.0002740264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.03862631,0.01031488,0.1142093,0.001731456,0.002595783,0.0003884415,0.7042592,0.1108772,0.01699745],"genre_scores_gemma":[0.01872437,0.001970824,0.1040422,0.0005327702,0.0004356088,0.000385743,0.8565338,0.01306255,0.004312114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02453714,"threshold_uncertainty_score":0.08208495,"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."}}