{"id":"W2067516565","doi":"10.1186/1471-2105-11-25","title":"Calibur: a tool for clustering large numbers of protein decoys","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Decoy; Cluster analysis; Bottleneck; Engineering; Artificial intelligence; Data mining; Computer science","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":[0.0001954917,0.0001254037,0.0001375964,0.00002923009,0.00005595787,0.00001861553,0.0001868088,0.0002058855,0.000009779759],"category_scores_gemma":[0.0001645204,0.0001118635,0.0001067797,0.00004901594,0.00004760079,0.000008505038,0.0001123087,0.00008819487,0.00000328708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004640699,"about_ca_system_score_gemma":0.00009184553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000485835,"about_ca_topic_score_gemma":0.0002388461,"domain_scores_codex":[0.999238,0.000006910223,0.0003255247,0.0001025933,0.00009316686,0.000233828],"domain_scores_gemma":[0.9993555,0.00001006252,0.0001540527,0.0003470648,0.00008364117,0.00004967498],"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":[0.0006890885,0.0001917527,0.009643976,0.003155033,0.0001959245,0.000001154618,0.0008167201,0.0007089664,0.9485918,0.01216934,0.00248594,0.0213503],"study_design_scores_gemma":[0.004992057,0.0008256817,0.001426721,0.00009754288,0.00008321278,0.00007603078,0.0004627826,0.3956052,0.4470903,0.002040355,0.1461294,0.001170719],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3879938,0.00002436166,0.6100796,0.00001283433,0.0001591208,0.0006404668,0.0001462955,0.00001464196,0.0009289051],"genre_scores_gemma":[0.443345,0.000004920302,0.5557595,0.0001340681,0.0001429668,0.00007673095,0.0002007674,0.00002130383,0.0003147647],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5015015,"threshold_uncertainty_score":0.4561663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0061356032309907,"score_gpt":0.2435954316298637,"score_spread":0.2374598283988731,"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."}}