{"id":"W1548667080","doi":"","title":"Clustering labeled data and cross-validation for classification with few positives in yeast","year":2004,"lang":"en","type":"article","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"False positive paradox; Cluster analysis; Computer science; Artificial intelligence; Machine learning; Classifier (UML); Biological data; Binary classification; Data mining; Unsupervised learning; Hierarchical clustering; Pattern recognition (psychology); Support vector machine; Bioinformatics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02825193,0.002478663,0.002636764,0.002526006,0.003234833,0.00279192,0.004122891,0.005221346,0.00103809],"category_scores_gemma":[0.03291998,0.001302386,0.002519728,0.001650433,0.002390589,0.001817131,0.002540499,0.003173362,0.001234649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808316,"about_ca_system_score_gemma":0.002068175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0102839,"about_ca_topic_score_gemma":0.01061725,"domain_scores_codex":[0.9828152,0.0105171,0.001222376,0.002929036,0.001680488,0.0008358302],"domain_scores_gemma":[0.9643291,0.0231632,0.001016558,0.005731015,0.005095205,0.0006648528],"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":[0.004235171,0.001645549,0.04314925,0.0008685992,0.002549129,0.0005874347,0.001030023,0.4482504,0.03730099,0.004365763,0.01307798,0.4429397],"study_design_scores_gemma":[0.00009130513,0.0001719482,0.004033034,0.00005610824,0.0001669442,0.0001203643,0.0001514696,0.9793894,0.01140881,0.003506757,0.000858692,0.0000451378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.434894,0.002107013,0.5524442,0.0006583415,0.0003142793,0.0005277313,0.001254827,0.006503,0.001296649],"genre_scores_gemma":[0.7323064,0.0002475555,0.2559149,0.000421465,0.00008513864,0.0004875674,0.007594417,0.0009012079,0.002041362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02825193,"threshold_uncertainty_score":0.1494123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04007134510667652,"score_gpt":0.3349870701226844,"score_spread":0.2949157250160078,"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."}}