{"id":"W4388731451","doi":"10.1002/widm.1523","title":"The use of gene expression datasets in feature selection research: 20 years of inherent bias?","year":2023,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Global Affairs Canada; Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Feature selection; Preprocessor; Computer science; Selection (genetic algorithm); Feature (linguistics); Machine learning; Data mining; DNA microarray; Data pre-processing; Artificial intelligence; Biological data; Data science; Bioinformatics; Gene; Gene expression; Biology; Genetics","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":[0.001336559,0.0001173004,0.0002168655,0.0001422049,0.0001203804,0.00005104235,0.0004535962,0.00009781282,0.000002455617],"category_scores_gemma":[0.0003994683,0.0000834282,0.00004832864,0.0004842014,0.0001555369,0.00005410333,0.001757028,0.0001384913,0.000004274564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001280809,"about_ca_system_score_gemma":0.00008247451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005056307,"about_ca_topic_score_gemma":0.00019692,"domain_scores_codex":[0.9983686,0.0004594455,0.0003951495,0.0004450744,0.0001391075,0.0001926217],"domain_scores_gemma":[0.9986681,0.0001230265,0.0001825731,0.000924426,0.00005713538,0.00004472989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001886813,0.0000877054,0.002443109,0.000144496,0.00001816274,0.000001202341,0.0005391685,0.000007984364,0.3614075,0.000005864047,0.5223827,0.1127734],"study_design_scores_gemma":[0.000562388,0.00036458,0.01291108,0.002919542,0.00002834216,0.00001059161,0.001981296,0.001051483,0.08097009,0.00002720662,0.8989123,0.0002611292],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9475148,0.04963511,0.000226962,0.0002326139,0.0003753078,0.0006076861,0.001281335,0.00001025161,0.0001158811],"genre_scores_gemma":[0.8715091,0.1063757,0.001522785,0.00002512081,0.0004016368,0.0002252464,0.01623472,0.00005496078,0.003650727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3765295,"threshold_uncertainty_score":0.3402103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2838351985218934,"score_gpt":0.4274522595190564,"score_spread":0.1436170609971629,"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."}}