{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003915292,0.00005313418,0.00007583406,0.0001162102,0.00001970689,0.00001065811,0.0001125843,0.00006089274,0.000006348683],"category_scores_gemma":[0.00007037519,0.00004889605,0.00001546628,0.0002031106,0.00001790743,0.00001506188,0.000121413,0.00002074479,3.577975e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001524311,"about_ca_system_score_gemma":0.00005973551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000762728,"about_ca_topic_score_gemma":0.00003647205,"domain_scores_codex":[0.9994125,0.00002168896,0.0002290005,0.0001145743,0.0001621675,0.00006008329],"domain_scores_gemma":[0.9993975,0.00000223433,0.000120623,0.0003828333,0.00007327888,0.00002359029],"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":[0.00002151257,0.00002992754,0.00117256,0.00002768264,0.00003666928,5.287818e-8,0.0002279061,0.8226481,0.1699091,0.000007356511,0.00004739163,0.005871702],"study_design_scores_gemma":[0.0008925916,0.00004251485,0.003527691,0.00002796649,0.0001164679,0.00000132483,0.000234115,0.8249481,0.1699388,0.00003190145,0.0001386064,0.00009998614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1734197,0.0003206728,0.8256227,0.000038773,0.00003945328,0.0001692521,0.00001821409,0.000004180725,0.0003670525],"genre_scores_gemma":[0.9037711,0.0002633014,0.0952856,0.00002400519,0.00001530031,0.000006902768,0.0006241814,0.000003571627,0.00000605403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7303514,"threshold_uncertainty_score":0.1993923,"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."}}