{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000239598,0.0001731865,0.0002061546,0.0001380723,0.00003899871,0.00002752946,0.0002059933,0.0001216371,0.00000191745],"category_scores_gemma":[0.0000293202,0.0001685672,0.00008149041,0.000132081,0.00005360599,0.00001414691,0.0001739963,0.00009536817,0.0000194713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003690891,"about_ca_system_score_gemma":0.0001137885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002805744,"about_ca_topic_score_gemma":0.00009702732,"domain_scores_codex":[0.9989228,0.00001339836,0.0005403814,0.0001327712,0.0001074424,0.0002832427],"domain_scores_gemma":[0.9994174,0.00000428775,0.0001664757,0.000278238,0.00005822529,0.00007531964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001677696,0.001436266,0.001149618,0.007110783,0.0003255948,0.000005280182,0.01518199,0.2763372,0.3092034,0.0009039193,0.002878686,0.3837896],"study_design_scores_gemma":[0.01768657,0.003185747,0.001892273,0.001982148,0.0001304776,0.0003970135,0.009710403,0.300106,0.6234621,0.003764511,0.03331543,0.004367412],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.554139,0.0001695151,0.4385563,0.00001993015,0.00008814788,0.0008505792,0.00007603203,0.00001453947,0.00608593],"genre_scores_gemma":[0.4850048,0.00008517683,0.5140857,0.0002424948,0.00009993375,0.00005397992,0.0003319745,0.00002000065,0.00007600441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3794222,"threshold_uncertainty_score":0.6873971,"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."}}