{"id":"W2408920437","doi":"10.1038/srep16971","title":"Combined Mapping of Multiple clUsteriNg ALgorithms (COMMUNAL): A Robust Method for Selection of Cluster Number, K","year":2015,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity","funders":"U.S. National Library of Medicine; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Cluster analysis; Computer science; Set (abstract data type); Data mining; sort; Single-linkage clustering; CURE data clustering algorithm; Affinity propagation; Stability (learning theory); Correlation clustering; Consensus clustering; Cluster (spacecraft); Data set; Determining the number of clusters in a data set; Complete-linkage clustering; Clustering high-dimensional data; Pattern recognition (psychology); Artificial intelligence; Machine learning; Information retrieval","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":[0.001357255,0.00008555526,0.0001487498,0.00007131489,0.00007471564,0.00002485276,0.0001042337,0.00008590695,0.000008509699],"category_scores_gemma":[0.0002207943,0.00008134441,0.00009057354,0.0002130132,0.00006438613,0.000007063706,0.00008919029,0.00003672043,5.376802e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001829582,"about_ca_system_score_gemma":0.0001309099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003175471,"about_ca_topic_score_gemma":0.00002335599,"domain_scores_codex":[0.9988198,0.00006880946,0.0004241137,0.0003593013,0.0001923057,0.000135652],"domain_scores_gemma":[0.9985989,0.00001411825,0.0004113132,0.0004487828,0.0004603208,0.0000665303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008045633,0.00007049907,0.005191743,0.00005305078,0.00002226582,3.577055e-7,0.0001731429,0.002839186,0.97802,0.000004021219,0.01056857,0.002976776],"study_design_scores_gemma":[0.00069523,0.00009082835,0.000602126,0.00003744624,0.00001385566,0.00003356015,0.0003332798,0.04010265,0.9264755,0.0003006112,0.03119798,0.0001169433],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3039099,0.00007449034,0.6928781,0.00005631174,0.002182689,0.0004109115,0.000004715896,0.00001224122,0.0004706489],"genre_scores_gemma":[0.9001662,0.000002877017,0.09778522,0.00001613371,0.00005689856,0.00005095013,0.0001201573,0.00001284481,0.001788704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5962563,"threshold_uncertainty_score":0.3317128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.048644546604193,"score_gpt":0.3125900545353345,"score_spread":0.2639455079311415,"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."}}