{"id":"W2952106966","doi":"10.1093/bioinformatics/btz064","title":"Variational infinite heterogeneous mixture model for semi-supervised clustering of heart enhancers","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Enhancer; Cluster analysis; Computer science; Python (programming language); Inference; Context (archaeology); Mixture model; Dirichlet process; Machine learning; Data mining; Artificial intelligence; Biology; Gene; Genetics; Gene expression","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":[0.00008646812,0.00009503795,0.0001111,0.00004011185,0.0000306262,0.00001271547,0.000115986,0.0001203912,0.00002137029],"category_scores_gemma":[0.00002015615,0.00008902623,0.00008464332,0.00004914185,0.00001573868,0.000007712244,0.00004730248,0.00003290412,0.000008735912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001273208,"about_ca_system_score_gemma":0.00009883894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.082793e-7,"about_ca_topic_score_gemma":0.000001414311,"domain_scores_codex":[0.9993718,0.000007806502,0.0002696598,0.0001095206,0.0001149426,0.0001262964],"domain_scores_gemma":[0.9994689,0.000008919453,0.0001211188,0.0002539973,0.0001050207,0.00004205814],"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":[0.0001391716,0.00002880138,0.000286954,0.0002467518,0.00003835914,1.736833e-8,0.0004049609,0.1321473,0.8609399,0.00008692256,0.00427517,0.00140574],"study_design_scores_gemma":[0.0005215453,0.00009629295,0.00006117282,0.00001976587,0.000007820508,0.000002295538,0.00004736871,0.853486,0.1367414,0.00004156689,0.008863585,0.0001112046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.221539,0.0001578428,0.7750451,0.0001604027,0.000345213,0.0006483899,0.0001340113,0.00001836395,0.001951736],"genre_scores_gemma":[0.9498625,0.00004573956,0.0483891,0.0005386682,0.00006661694,0.00003887271,0.0002819559,0.00001414167,0.0007624069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7283235,"threshold_uncertainty_score":0.3630384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01551478166122175,"score_gpt":0.2525756993871091,"score_spread":0.2370609177258874,"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."}}