{"id":"W2158564991","doi":"10.1186/1471-2105-8-239","title":"Probabilistic prediction and ranking of human protein-protein interactions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Ranking (information retrieval); Computer science; Probabilistic logic; Bayes' theorem; Naive Bayes classifier; False positive rate; Set (abstract data type); False discovery rate; Bayesian probability; Data mining; Machine learning; Protein–protein interaction; Protein function prediction; Human proteome project; Bayesian network; Interaction network; Function (biology); Computational biology; Artificial intelligence; Protein function; Proteomics; Biology; Support vector machine; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004906371,0.00014033,0.0001440169,0.00007721278,0.000119267,0.00002870153,0.0001142853,0.0001301997,0.000009236079],"category_scores_gemma":[0.00005818288,0.0001295489,0.00006108091,0.00008872849,0.0001163967,0.00001704564,0.0001084182,0.0001164925,0.00000389198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001633361,"about_ca_system_score_gemma":0.0000418473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000758884,"about_ca_topic_score_gemma":0.00006166704,"domain_scores_codex":[0.9989243,0.00001286932,0.0006121103,0.0001056376,0.0001245761,0.0002204733],"domain_scores_gemma":[0.9992776,0.00001206856,0.0002709078,0.0002718483,0.00009077518,0.00007681729],"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":[0.0006199725,0.0004348384,0.007559059,0.004119939,0.0003495238,0.000002056466,0.003481947,0.001441177,0.8809838,0.02702525,0.001933448,0.07204894],"study_design_scores_gemma":[0.01102456,0.005545228,0.0317751,0.002254965,0.0004111602,0.0003713171,0.006976616,0.3206996,0.5489891,0.02059668,0.04808699,0.003268712],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7534229,0.00009564882,0.2398196,0.00001277909,0.00009946089,0.0007004489,0.00002874864,0.00002171753,0.005798679],"genre_scores_gemma":[0.9621929,0.000006576184,0.03711959,0.00003673134,0.0001327875,0.00001839014,0.0001164231,0.00001373056,0.0003628819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3319947,"threshold_uncertainty_score":0.5282852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01380876975229888,"score_gpt":0.2508298393515291,"score_spread":0.2370210695992302,"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."}}