{"id":"W1510029899","doi":"10.1186/1471-2105-5-45","title":"A hybrid clustering approach to recognition of protein families in 114 microbial genomes","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Medical Research Council; University of Queensland","keywords":"Cluster analysis; Markov chain; Data mining; Single-linkage clustering; Complete-linkage clustering; Computer science; Hierarchical clustering; Computational biology; Correlation clustering; Biology; Artificial intelligence; CURE data clustering algorithm; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008345481,0.0004724604,0.0004836881,0.002983415,0.0008551042,0.0009226452,0.001024743,0.0005957056,0.001584432],"category_scores_gemma":[0.002711721,0.0003057206,0.0008896404,0.002788156,0.0002699232,0.0005045213,0.0008851151,0.0004118446,0.0005533271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001429906,"about_ca_system_score_gemma":0.0007903283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006270755,"about_ca_topic_score_gemma":0.009034391,"domain_scores_codex":[0.9990258,0.0002274304,0.00008775025,0.0002458929,0.0003507052,0.00006235642],"domain_scores_gemma":[0.9991208,0.000243819,0.00006226215,0.0001425914,0.0003861194,0.00004440713],"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":[0.001328443,0.0003143912,0.02169781,0.0008560107,0.0007090482,0.0003246722,0.001289806,0.1619747,0.1494464,0.01141046,0.004588955,0.6460593],"study_design_scores_gemma":[0.0001029103,0.0001989547,0.01612251,0.00004667358,0.0002016602,0.0005831539,0.0005073443,0.9125348,0.0474496,0.01221845,0.009947056,0.0000867706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3582895,0.0006698982,0.6310032,0.000149258,0.00002658004,0.0003680817,0.002468839,0.0038109,0.003213745],"genre_scores_gemma":[0.2878616,0.0001388724,0.707347,0.00003282596,0.000007188626,0.0003088507,0.003401048,0.0001847634,0.0007178165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006270755,"threshold_uncertainty_score":0.01246852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01509399789692153,"score_gpt":0.2116076477395259,"score_spread":0.1965136498426043,"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."}}