{"id":"W4415320742","doi":"10.1016/j.jbi.2025.104932","title":"Towards a Biological Evaluation Framework for Oversampling (BEFO) gene expression data","year":2025,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Oversampling; Ranking (information retrieval); Random forest; Biological data; Relevance (law); Synthetic data; Population; Class (philosophy)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001344471,0.00009879268,0.0001686813,0.0001285633,0.00007309988,0.00003668292,0.0005109521,0.0002821593,0.0000260981],"category_scores_gemma":[0.001757238,0.00006885547,0.00008740656,0.0001657657,0.00007613553,0.00001906092,0.0002150216,0.0001502481,0.00000119099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000359072,"about_ca_system_score_gemma":0.0004390148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.876388e-7,"about_ca_topic_score_gemma":1.479061e-7,"domain_scores_codex":[0.9986422,0.00004894166,0.0006929471,0.0001080292,0.0003618629,0.000145991],"domain_scores_gemma":[0.9986553,0.00005313808,0.0004501904,0.0004030447,0.0003348032,0.0001035127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006436586,0.000287275,0.0003717279,0.0001596707,0.0001846487,7.048818e-7,0.0003140562,0.0001488617,0.6880227,0.000919345,0.09496378,0.2139835],"study_design_scores_gemma":[0.003217783,0.0009153802,0.001189606,0.0005529054,0.0001576963,0.0000347321,0.001644505,0.01884486,0.2895712,0.01077963,0.6727887,0.0003030716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06433,0.0006848789,0.9329686,0.0007615715,0.0008070207,0.000208885,0.00004141645,0.000004861564,0.0001927246],"genre_scores_gemma":[0.6299095,0.0008669482,0.3661319,0.001438162,0.0008595297,0.00002362804,0.0007115415,0.00001013165,0.00004866756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5778249,"threshold_uncertainty_score":0.2807845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09341193759917463,"score_gpt":0.4020765994663315,"score_spread":0.3086646618671569,"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."}}