{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002717777,0.001195378,0.001726526,0.002579361,0.00112656,0.001417008,0.001687993,0.001221031,0.001344575],"category_scores_gemma":[0.00762042,0.0005566009,0.001396428,0.002023168,0.0004266554,0.00178385,0.001455447,0.001290827,0.0009805667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073218,"about_ca_system_score_gemma":0.001167454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006288286,"about_ca_topic_score_gemma":0.007136373,"domain_scores_codex":[0.9981726,0.0004059269,0.0001427349,0.0005369767,0.0005851507,0.0001564211],"domain_scores_gemma":[0.9970703,0.0009392933,0.0002660654,0.0006747949,0.0009409784,0.0001086094],"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":[0.0008528312,0.0001947479,0.01651714,0.000280257,0.0005426654,0.0001743393,0.0003787537,0.288572,0.02607819,0.003818224,0.01139643,0.6511945],"study_design_scores_gemma":[0.00001996988,0.00003389098,0.003295098,0.00001306697,0.00004157581,0.00008295863,0.00004215569,0.9852814,0.00578932,0.003962798,0.001397019,0.00004067116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05265279,0.0003939334,0.9403897,0.0001932195,0.00009709793,0.0001209718,0.0008637465,0.004377421,0.0009111557],"genre_scores_gemma":[0.2902341,0.0001885057,0.7058903,0.0000989848,0.000055109,0.0002344122,0.001940134,0.0003782221,0.0009802796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006288286,"threshold_uncertainty_score":0.01437318,"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."}}