{"id":"W4416664067","doi":"10.1007/s11634-025-00659-0","title":"Data-driven logistic regression ensembles with applications in genomics","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Mitacs; KU Leuven","keywords":"Genomics; Regularization (linguistics); Ranking (information retrieval); Big data; Logistic regression; Computational genomics; Predictive modelling; Binary number","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":[0.0002213954,0.0001178131,0.0001741981,0.0002729305,0.00006909957,0.00003545015,0.0006455354,0.00008204431,0.000003895722],"category_scores_gemma":[0.00005402833,0.00009373429,0.0000159186,0.0009316706,0.00009131808,0.00004487159,0.0002862845,0.0000769231,9.63899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002730294,"about_ca_system_score_gemma":0.00007634482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002160052,"about_ca_topic_score_gemma":0.003675209,"domain_scores_codex":[0.9986485,0.00006560219,0.0002814081,0.0007913672,0.00009146596,0.0001216588],"domain_scores_gemma":[0.9978922,0.00002812368,0.0001454732,0.001861143,0.00004212317,0.00003091769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003161228,0.0004614903,0.6008784,0.0001322506,0.0003101368,0.000001696665,0.00007322144,0.005047634,0.2056777,0.007598767,0.002209791,0.1772928],"study_design_scores_gemma":[0.0009195814,0.00004222035,0.406303,0.00009418023,0.0004599224,0.00000118679,0.001364272,0.07820422,0.003498315,0.0007776644,0.507939,0.000396442],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1560013,0.01811891,0.8202986,0.001254952,0.00008051469,0.0007814444,0.0008383157,0.00002796483,0.002597986],"genre_scores_gemma":[0.9700208,0.01214206,0.004079203,0.00006594024,0.00002607975,0.00008406489,0.01337106,0.00000673392,0.000204068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8162194,"threshold_uncertainty_score":0.3822373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04371606132484556,"score_gpt":0.3582000692644834,"score_spread":0.3144840079396379,"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."}}