{"id":"W2007139266","doi":"10.1186/1471-2105-10-260","title":"MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Institute for Materials Science; Natural Sciences and Engineering Research Council of Canada; Korea Research Council of Fundamental Science and Technology","keywords":"Cluster analysis; Computer science; Data mining; Rand index; Pattern recognition (psychology); Single-linkage clustering; Microarray analysis techniques; Clustering high-dimensional data; DNA microarray; Artificial intelligence; Ensemble learning; Gene chip analysis; CURE data clustering algorithm; Correlation clustering; Biology; Gene; Genetics; Gene expression","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":[0.0001348941,0.0001184372,0.0001156953,0.00006874565,0.00006355986,0.00002427663,0.0001620284,0.0001286989,0.00000592913],"category_scores_gemma":[0.00004424613,0.0001096377,0.00006740668,0.0001201889,0.00003757942,0.00001409002,0.00003204782,0.00005057059,0.000007548761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002050572,"about_ca_system_score_gemma":0.0001020582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003153381,"about_ca_topic_score_gemma":0.00001573427,"domain_scores_codex":[0.9992028,0.00002452773,0.0003755822,0.0001333582,0.0001073144,0.0001564405],"domain_scores_gemma":[0.9992117,0.000005118935,0.0002705685,0.0003538363,0.0001059328,0.00005281576],"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":[0.00003856268,0.00003942024,0.0006219103,0.00004804378,0.000006847564,4.554598e-8,0.0001629108,0.002348534,0.9920816,0.00003336263,0.0003567268,0.004262071],"study_design_scores_gemma":[0.00066638,0.0001169068,0.01588021,0.00004965796,0.0000206398,0.000009444691,0.000604366,0.5611185,0.4165502,0.00001767292,0.004739901,0.0002261189],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1810655,0.0001545487,0.8172517,0.00004161487,0.0001239625,0.0001705888,0.000009312028,0.00001650664,0.001166254],"genre_scores_gemma":[0.77863,0.00007216898,0.2208102,0.0001246117,0.00005580945,0.000003356234,0.00007328395,0.000009020272,0.0002216106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5975645,"threshold_uncertainty_score":0.4470897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05225903524028005,"score_gpt":0.3035386235021323,"score_spread":0.2512795882618523,"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."}}