{"id":"W4386560750","doi":"10.3389/fmolb.2023.1257550","title":"A curated census of pathogenic and likely pathogenic UTR variants and evaluation of deep learning models for variant effect prediction","year":2023,"lang":"en","type":"article","venue":"Frontiers in Molecular Biosciences","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Ontario Genomics","funders":"","keywords":"Untranslated region; Pathogenicity; Genetics; Computational biology; Biology; Confidence interval; Bioinformatics; Gene; Medicine; Internal medicine","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":[0.003326787,0.0009276465,0.0009245873,0.004481727,0.0009063649,0.001021639,0.0009956596,0.001139156,0.002041661],"category_scores_gemma":[0.01194645,0.0003627427,0.001390285,0.002587181,0.0005139962,0.0005047274,0.001345719,0.0008060967,0.001141881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006689554,"about_ca_system_score_gemma":0.001450393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006225689,"about_ca_topic_score_gemma":0.01012857,"domain_scores_codex":[0.9974964,0.0005124779,0.0003159847,0.0008463473,0.0006465992,0.0001821402],"domain_scores_gemma":[0.9932028,0.00360585,0.000604027,0.001016381,0.001227572,0.0003432854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003524418,0.0006835226,0.5592335,0.003305399,0.001883668,0.01064825,0.001130017,0.05967289,0.08851686,0.004306253,0.04647478,0.2206205],"study_design_scores_gemma":[0.0008150989,0.001350626,0.4117613,0.001103992,0.00172752,0.01961029,0.001104925,0.403783,0.05654621,0.01077107,0.09113771,0.0002881905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9032383,0.003682394,0.03510863,0.0003071064,0.0000960679,0.000236057,0.05167377,0.003004734,0.002652894],"genre_scores_gemma":[0.7500417,0.00106414,0.05931326,0.0003275815,0.00006598156,0.000284853,0.1871495,0.0007212546,0.001031757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006225689,"threshold_uncertainty_score":0.01759392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01283622021230062,"score_gpt":0.2504469162033067,"score_spread":0.2376106959910061,"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."}}