{"id":"W2089818979","doi":"10.1109/tcbb.2011.142","title":"Clustering 100,000 Protein Structure Decoys in Minutes","year":2011,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Pairwise comparison; Computer science; Cluster (spacecraft); Centroid; Benchmark (surveying); Pruning; Data mining; Hierarchical clustering; Pattern recognition (psychology); Single-linkage clustering; Selection (genetic algorithm); Artificial intelligence; Algorithm; Correlation clustering; 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":[0.0001505508,0.0002153374,0.0001747676,0.0001848017,0.0001497552,0.00002183206,0.0002201614,0.0002742813,0.00007286448],"category_scores_gemma":[0.00004058731,0.0001915174,0.00005475435,0.0001355798,0.0001582043,0.00002112717,0.00002000789,0.0002676917,0.0000136747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001651169,"about_ca_system_score_gemma":0.00005267127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002625973,"about_ca_topic_score_gemma":0.0001116803,"domain_scores_codex":[0.998974,0.00005359289,0.0004518036,0.0001827722,0.00009199932,0.0002458363],"domain_scores_gemma":[0.9994538,0.00004852936,0.0001342746,0.0002261725,0.00006297525,0.000074201],"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":[0.003147603,0.001676097,0.03991342,0.001950679,0.001272364,0.00002786773,0.01719032,0.3074864,0.05007682,0.004078217,0.001454495,0.5717257],"study_design_scores_gemma":[0.007518856,0.005385405,0.03690185,0.0004032937,0.0001332171,0.0006799186,0.00174342,0.839967,0.07625045,0.02023981,0.007874131,0.002902708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4403822,0.0000433601,0.5577962,0.0001129443,0.0002106376,0.0003519704,0.0001599825,0.00003577087,0.0009069408],"genre_scores_gemma":[0.810431,0.00002154713,0.1888976,0.0003419875,0.00003293657,0.00001717233,0.0001536876,0.00001121165,0.0000927952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.568823,"threshold_uncertainty_score":0.7809852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01645178177001421,"score_gpt":0.2612231025323662,"score_spread":0.244771320762352,"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."}}