{"id":"W2120815702","doi":"10.1093/bioinformatics/bti1040","title":"ExonHunter: a comprehensive approach to gene finding","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Annotation; Hidden Markov model; Gene prediction; Probabilistic logic; Set (abstract data type); Sequence (biology); Markov chain; Extension (predicate logic); Data mining; Artificial intelligence; Machine learning; Gene; Genome; Genetics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001767067,0.00008540764,0.00006747269,0.00004968384,0.0001433991,0.00006762808,0.0006748206,0.00004339789,9.29954e-7],"category_scores_gemma":[0.000001603519,0.00005905487,0.00003327843,0.0002633682,0.00008650836,0.000004566964,0.0001589756,0.00005293541,0.00001640658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009268369,"about_ca_system_score_gemma":0.0000189145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002618248,"about_ca_topic_score_gemma":0.000004134205,"domain_scores_codex":[0.9993395,0.00002179816,0.0001551943,0.0002220389,0.00009074963,0.0001707652],"domain_scores_gemma":[0.9995515,0.0000146002,0.0000403488,0.0003309931,0.00002406553,0.00003853587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005101534,0.001589435,0.004588107,0.00008097455,0.00009210959,9.265168e-7,0.0142136,0.09209768,0.1599213,0.04017558,0.07363579,0.6135535],"study_design_scores_gemma":[0.0004122018,0.0002067157,0.01373572,0.00001291044,0.00001097605,0.00005119868,0.001098338,0.06666889,0.008390477,0.0006943238,0.9081886,0.0005296121],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2367634,0.0003139538,0.7584493,0.0006082423,0.00008227594,0.0006138367,0.000008882598,0.00001141056,0.003148692],"genre_scores_gemma":[0.9101133,0.00002681231,0.08720454,0.002057926,0.0003982151,0.000122292,0.00003036399,0.000003832053,0.00004269663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8345528,"threshold_uncertainty_score":0.2408188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02161260978141782,"score_gpt":0.2653430076089932,"score_spread":0.2437303978275753,"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."}}