{"id":"W2946841580","doi":"10.1093/bioinformatics/bty211","title":"Inference of the human polyadenylation code","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"Polyadenylation; Cleavage and polyadenylation specificity factor; Untranslated region; Computational biology; Genetics; Biology; Three prime untranslated region; Gene; Human genome; Inference; Genome; Computer science; Artificial intelligence; Messenger RNA","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":[0.0007139219,0.0005934702,0.0004170794,0.001036304,0.0003252922,0.0008460101,0.0008336497,0.001314121,0.005127644],"category_scores_gemma":[0.005587625,0.0004413278,0.0007506687,0.0006995368,0.000630753,0.0007567919,0.0005282424,0.001511182,0.001394214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001141703,"about_ca_system_score_gemma":0.0009882211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009041146,"about_ca_topic_score_gemma":0.007110449,"domain_scores_codex":[0.9994354,0.0000943776,0.00001954936,0.0003050229,0.00008714003,0.00005858669],"domain_scores_gemma":[0.9972013,0.002179472,0.0001198409,0.0001672827,0.0002423246,0.0000898785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007570413,0.0001826654,0.03316171,0.0002967899,0.0001073494,0.000756451,0.0001597932,0.7518614,0.007192725,0.02143608,0.01677254,0.1673154],"study_design_scores_gemma":[0.00001952964,0.00001223974,0.001306934,0.00002080558,0.000006977254,0.00007302759,0.000009525586,0.9781525,0.001403968,0.01793503,0.001051948,0.000007524092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2424297,0.001305035,0.726759,0.001783395,0.0001871288,0.0001614676,0.01410203,0.004384892,0.008887413],"genre_scores_gemma":[0.8640993,0.0004934053,0.1128037,0.0006034418,0.0001565138,0.0001935161,0.0156825,0.0003128827,0.00565483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009041146,"threshold_uncertainty_score":0.01797706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02283891265290327,"score_gpt":0.3096751317458032,"score_spread":0.2868362190928999,"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."}}