{"id":"W2098566726","doi":"10.1093/bioinformatics/bth124","title":"Evaluation and optimization of clustering in gene expression data analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Cluster analysis; Computer science; Partition (number theory); Identification (biology); Data mining; Stability (learning theory); Cluster (spacecraft); Expression (computer science); Gene; Computational biology; Consensus clustering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Biology; Genetics; Correlation clustering; Mathematics; CURE data clustering algorithm","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":[0.01498834,0.001543047,0.002186423,0.00456368,0.001356128,0.002282807,0.002095489,0.001711407,0.0008829802],"category_scores_gemma":[0.04244475,0.0007361317,0.001424901,0.004064882,0.002085675,0.001830691,0.001955653,0.001366855,0.0005562286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002364946,"about_ca_system_score_gemma":0.002118323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005001848,"about_ca_topic_score_gemma":0.00331139,"domain_scores_codex":[0.9901302,0.005061425,0.0008618169,0.001464306,0.00222072,0.0002615416],"domain_scores_gemma":[0.9717856,0.01774605,0.002328822,0.001810631,0.005892973,0.0004358499],"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":[0.0007666594,0.0002222712,0.02235016,0.0009118348,0.0005185321,0.0001341839,0.0005129452,0.6540633,0.01438694,0.008863596,0.003316735,0.2939529],"study_design_scores_gemma":[0.00002631744,0.0001063937,0.003559785,0.00003326674,0.00004795105,0.00007582245,0.00006335281,0.9793534,0.008881023,0.006968,0.0008558974,0.00002879914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0418,0.0008051412,0.9549412,0.000260641,0.00003056748,0.0002102206,0.0002732198,0.001115965,0.0005631367],"genre_scores_gemma":[0.3491301,0.0003517692,0.6475092,0.0001049375,0.00006667076,0.0003756228,0.001292296,0.0004846297,0.0006848402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01498834,"threshold_uncertainty_score":0.07926685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0391304351557178,"score_gpt":0.3075528175625202,"score_spread":0.2684223824068024,"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."}}