{"id":"W4399243300","doi":"10.1002/bimj.202300173","title":"A Bayesian hierarchical hidden Markov model for clustering and gene selection: Application to kidney cancer gene expression data","year":2024,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; University of Minnesota","keywords":"Cluster analysis; Bayesian information criterion; Hierarchical clustering; Gene selection; Bayesian probability; Selection (genetic algorithm); Computational biology; Gene; Computer science; Gene expression; Biology; Genetics; Artificial intelligence; Microarray analysis techniques","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006601122,0.0006477396,0.001633717,0.001177654,0.001059055,0.00120703,0.002216758,0.001177142,0.002029782],"category_scores_gemma":[0.01299575,0.0007391073,0.001548023,0.001973785,0.0006134681,0.0008182555,0.001158696,0.00175389,0.001032861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001455577,"about_ca_system_score_gemma":0.00236565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02060711,"about_ca_topic_score_gemma":0.02824723,"domain_scores_codex":[0.9974691,0.001577119,0.0001122531,0.0003368439,0.0003845257,0.0001202355],"domain_scores_gemma":[0.9947804,0.004196872,0.0002237489,0.0002207616,0.0004614149,0.0001167434],"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":[0.0003799494,0.0001511916,0.005879651,0.0002131029,0.0003615242,0.0002323958,0.0004314286,0.7761707,0.003195289,0.03764942,0.006534001,0.1688013],"study_design_scores_gemma":[0.00002063408,0.00001392584,0.0005347712,0.000009018559,0.00001537315,0.00002496627,0.00001128076,0.9849476,0.0001895905,0.0135709,0.000645092,0.00001677581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007373949,0.0002201197,0.9909594,0.0002365755,0.00002716319,0.00007680307,0.0003299513,0.0005086865,0.0002673697],"genre_scores_gemma":[0.1610644,0.0005001882,0.8322196,0.0003114879,0.00009831542,0.0009718035,0.002303063,0.0003360097,0.00219514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02060711,"threshold_uncertainty_score":0.04097432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03490070020174878,"score_gpt":0.3351226840831841,"score_spread":0.3002219838814353,"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."}}