{"id":"W4231631488","doi":"10.1002/sam.10048","title":"Application of model selection technique in chemogenomic data analysis","year":2009,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Dependency (UML); Model selection; Bayesian network; Selection (genetic algorithm); Data set; Construct (python library); Set (abstract data type); Bayesian information criterion; Bayesian probability; Artificial intelligence; Machine learning","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":[0.003160074,0.00008825453,0.0001941107,0.0003413763,0.0002034785,0.0001159588,0.002686789,0.00004381318,0.000009733284],"category_scores_gemma":[0.000389165,0.00006205279,0.00002219586,0.002041051,0.0002293609,0.00009190332,0.0009764574,0.0001166998,3.050274e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001487426,"about_ca_system_score_gemma":0.0002022108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005699668,"about_ca_topic_score_gemma":0.0001828307,"domain_scores_codex":[0.9983661,0.00006184894,0.0003715202,0.0007285735,0.0003013888,0.0001706112],"domain_scores_gemma":[0.9971499,0.0000250876,0.0002455386,0.002402206,0.00008936419,0.0000878814],"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":[0.0001051006,0.0001667824,0.03295345,0.000006167884,0.0004759506,9.067872e-7,0.0000731061,0.005304689,0.8409288,0.0006281099,0.003024012,0.1163329],"study_design_scores_gemma":[0.00009782268,0.00003435621,0.07728657,0.00000340856,0.0007935162,0.000008586549,0.0001184972,0.9186658,0.002197942,0.0002941002,0.0004101389,0.0000893083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04005169,0.000114921,0.9582765,0.0002857827,0.000008282562,0.00006949441,0.001157023,0.000002232892,0.00003414971],"genre_scores_gemma":[0.8999087,0.0002955307,0.09507871,0.00006750048,0.00003794195,0.000002011336,0.004599843,0.000002507324,0.000007241304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9133611,"threshold_uncertainty_score":0.4992768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04998375380142114,"score_gpt":0.3711030331056732,"score_spread":0.321119279304252,"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."}}