{"id":"W4388233024","doi":"10.1038/s42003-023-05480-z","title":"KMD clustering: robust general-purpose clustering of biological data","year":2023,"lang":"en","type":"article","venue":"Communications Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Cluster analysis; Silhouette; Computer science; Hyperparameter; Hierarchical clustering; CURE data clustering algorithm; Correlation clustering; Single-linkage clustering; Data mining; Clustering high-dimensional data; Artificial intelligence; Canopy clustering algorithm; Pattern recognition (psychology); Generalization; Consensus clustering; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004299218,0.002112805,0.002229832,0.003521295,0.002000713,0.002281523,0.004884564,0.002121175,0.002641155],"category_scores_gemma":[0.01149593,0.001311375,0.00247837,0.003854146,0.001314378,0.001764115,0.004145037,0.002347589,0.004449723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001626869,"about_ca_system_score_gemma":0.003058747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004830222,"about_ca_topic_score_gemma":0.007879398,"domain_scores_codex":[0.9964328,0.0009654096,0.0002636533,0.001011722,0.001133632,0.000192716],"domain_scores_gemma":[0.9970559,0.0005536473,0.0003029954,0.001233298,0.0007104577,0.0001437374],"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":[0.0006468224,0.0002369343,0.004405688,0.001964732,0.001029731,0.0003024788,0.0007339481,0.2101503,0.05327718,0.03459975,0.07911591,0.6135365],"study_design_scores_gemma":[0.00006533535,0.00008132016,0.001877936,0.0000722569,0.00005817556,0.000303683,0.0000902828,0.9114882,0.02561266,0.03690259,0.02329465,0.0001529461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002340204,0.0002082989,0.9905503,0.00008285532,0.0000538063,0.0001300804,0.0005933809,0.005723004,0.0003180819],"genre_scores_gemma":[0.02923763,0.0002294088,0.9648738,0.0001240085,0.00004061446,0.0003580543,0.002814735,0.00134472,0.0009770008],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004884564,"threshold_uncertainty_score":0.02273673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2509509066328703,"score_gpt":0.3863604570029971,"score_spread":0.1354095503701268,"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."}}