{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00698427,0.001101426,0.001498629,0.003158016,0.0006901448,0.001366463,0.001264473,0.001597442,0.001487635],"category_scores_gemma":[0.0187035,0.0004859276,0.00111962,0.001624338,0.0004599421,0.001806857,0.0006637622,0.001016582,0.001425508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005989645,"about_ca_system_score_gemma":0.0007998252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002045757,"about_ca_topic_score_gemma":0.002093313,"domain_scores_codex":[0.9961908,0.001504534,0.0004658046,0.0006822675,0.00101964,0.0001370132],"domain_scores_gemma":[0.9889599,0.008050322,0.000625285,0.0005621378,0.001661923,0.0001403559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001349343,0.000831361,0.05583665,0.0007231768,0.0005555422,0.0009223924,0.0003111984,0.1093797,0.04145944,0.002976094,0.003528006,0.7821271],"study_design_scores_gemma":[0.00005347653,0.0002081945,0.004463321,0.00007419122,0.0001337285,0.0006702913,0.0001055765,0.9655777,0.01990999,0.007179095,0.001562682,0.00006177639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06947459,0.0004599589,0.9263757,0.0002742173,0.00008243205,0.0002629738,0.0003585136,0.001715622,0.0009960064],"genre_scores_gemma":[0.2818917,0.0001777614,0.7162321,0.0001995057,0.00007812254,0.0001948689,0.0007557226,0.00005505657,0.000415258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00698427,"threshold_uncertainty_score":0.03693676,"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."}}