{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912088,0.0006794339,0.0007234614,0.003370058,0.0004868096,0.000934415,0.001062503,0.0008368455,0.001317808],"category_scores_gemma":[0.004849113,0.0002929804,0.0005140748,0.001899463,0.0005343849,0.00103715,0.0005828492,0.0004833212,0.0005990249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001249874,"about_ca_system_score_gemma":0.0009410035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009970807,"about_ca_topic_score_gemma":0.0074321,"domain_scores_codex":[0.9992943,0.000141517,0.00004410314,0.0001760787,0.0003010722,0.00004294682],"domain_scores_gemma":[0.9978301,0.000843314,0.0002770473,0.0002530276,0.0007157106,0.00008085097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002628526,0.000108506,0.01108711,0.0002625625,0.0001516413,0.0001320988,0.00008148745,0.7944101,0.0168751,0.01031392,0.00455302,0.1617616],"study_design_scores_gemma":[0.000005085113,0.00001125526,0.001048124,0.000003425058,0.000008017572,0.00003435342,0.00000676097,0.9922506,0.003170802,0.003016386,0.0004378221,0.000007290064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1105956,0.0003767777,0.8846951,0.0001779763,0.00001533091,0.000134719,0.0006316472,0.001694845,0.001677956],"genre_scores_gemma":[0.5405874,0.0002450459,0.4550457,0.00005427165,0.00002379844,0.0001650517,0.002231009,0.0002029246,0.00144486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009970807,"threshold_uncertainty_score":0.01982558,"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."}}