{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006074179,0.0009649617,0.00194217,0.0009789836,0.0005485788,0.0009754499,0.001443698,0.001139533,0.001371274],"category_scores_gemma":[0.01949812,0.0007420417,0.00122237,0.001633874,0.0004483767,0.001209567,0.002001808,0.002961843,0.0008683425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005073737,"about_ca_system_score_gemma":0.0009016838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003317514,"about_ca_topic_score_gemma":0.004326662,"domain_scores_codex":[0.997794,0.001276008,0.0001103297,0.0003004904,0.0004320981,0.0000869552],"domain_scores_gemma":[0.9883874,0.008677856,0.0003378244,0.0008785953,0.001488781,0.0002294734],"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":[0.0002462555,0.0001786662,0.00395111,0.0001144184,0.0003192663,0.00009720036,0.00009593565,0.6940308,0.002481186,0.009210921,0.005581143,0.2836932],"study_design_scores_gemma":[0.000006431828,0.00001168617,0.000182009,0.000005842267,0.00001109451,0.000009505055,0.000003932451,0.9934741,0.0003873272,0.005468916,0.0004329537,0.000006238212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0157878,0.000925765,0.9807741,0.000428741,0.0001270882,0.00003313901,0.0002626169,0.001207839,0.0004529265],"genre_scores_gemma":[0.4526488,0.001229443,0.5394014,0.0004300185,0.0005364518,0.0003303893,0.001733635,0.0004433919,0.003246481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006074179,"threshold_uncertainty_score":0.03212368,"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."}}