{"id":"W2138003801","doi":"10.1093/bioinformatics/bth351","title":"Protein complex prediction via cost-based clustering","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":668,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health; University of Toronto","keywords":"Cluster analysis; Computer science; Scalability; Data mining; Partition (number theory); Identification (biology); Biological network; Protein function prediction; Caenorhabditis elegans; Computational biology; Protein function; Machine learning; Biology; Mathematics; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001739111,0.0001810113,0.0001337806,0.00005127281,0.0001329389,0.00005600803,0.000193525,0.0001795287,0.00001775285],"category_scores_gemma":[0.00001574268,0.0001704765,0.00008561479,0.00008918672,0.00006971605,0.00001248078,0.00009735288,0.0001048043,0.00007018661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004761605,"about_ca_system_score_gemma":0.0001015658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008920393,"about_ca_topic_score_gemma":0.00002452058,"domain_scores_codex":[0.9989736,0.000009415706,0.0004402753,0.0001171207,0.000155955,0.0003036415],"domain_scores_gemma":[0.9992957,0.000003114062,0.0001598446,0.0003616019,0.00006591915,0.0001138517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007603734,0.0006673419,0.0008176204,0.001630566,0.0004466685,0.00001142647,0.001694281,0.3634143,0.3719793,0.002482502,0.01887151,0.2372241],"study_design_scores_gemma":[0.005308786,0.001048965,0.001139827,0.0001683593,0.00004643011,0.0000754146,0.0002920673,0.8001881,0.05437536,0.0007267407,0.1357055,0.0009244187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03687418,0.00004687402,0.9569559,0.0001934985,0.0002058201,0.0008047072,0.00007127411,0.00006050132,0.004787212],"genre_scores_gemma":[0.9034337,0.00001277748,0.09423505,0.001060207,0.000246778,0.00006489016,0.0007903316,0.00002622183,0.0001300387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8665595,"threshold_uncertainty_score":0.6951829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507396375421566,"score_gpt":0.2276197204721511,"score_spread":0.2125457567179354,"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."}}