{"id":"W2156847802","doi":"10.1093/bioinformatics/btl094","title":"Combining multi-species genomic data for microRNA identification using a Naïve Bayes classifier","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; Pennsylvania Department of Health; National Science Foundation","keywords":"False positive paradox; Bayes' theorem; Naive Bayes classifier; Classifier (UML); Computer science; Artificial intelligence; Gene prediction; Genome; Computational biology; Machine learning; Data mining; Gene; Biology; Support vector machine; Bayesian probability; Genetics","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":[0.000206664,0.0001394404,0.0001149155,0.00005608942,0.0001449071,0.0001019541,0.0003371025,0.0001227882,0.000005905808],"category_scores_gemma":[0.00006733067,0.0001444969,0.00006174747,0.00006125173,0.00006724337,0.00002731217,0.000204239,0.000036158,0.00001270821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004146466,"about_ca_system_score_gemma":0.00008576682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001099486,"about_ca_topic_score_gemma":0.00002831048,"domain_scores_codex":[0.9990335,0.00001519286,0.0004486858,0.0002042564,0.00009367065,0.0002047656],"domain_scores_gemma":[0.9988711,0.00001270962,0.0002735755,0.0006952747,0.000108022,0.00003925031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002320903,0.00004395909,0.0006460162,0.00008935116,0.00003257515,1.464014e-7,0.00004258045,0.0003324915,0.9924705,0.0001329859,0.005618883,0.0005673015],"study_design_scores_gemma":[0.002105818,0.00006481558,0.04117727,0.00006071142,0.0001545661,0.00002573984,0.0004502575,0.559899,0.2853684,0.0001287631,0.1098927,0.0006719816],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6374567,0.0004609545,0.3604721,0.00003725807,0.0002242917,0.0005007974,0.0006593167,0.00002592283,0.0001627012],"genre_scores_gemma":[0.8517374,0.0000301767,0.1390504,0.00008837089,0.0003340486,0.00001852108,0.00809124,0.00003712531,0.0006126458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7071021,"threshold_uncertainty_score":0.5892414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05732768182420857,"score_gpt":0.2917214077298999,"score_spread":0.2343937259056913,"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."}}