{"id":"W4400562029","doi":"10.1093/nargab/lqae079","title":"Optimizing hybrid ensemble feature selection strategies for transcriptomic biomarker discovery in complex diseases","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Feature selection; Robustness (evolution); Computer science; Biomarker discovery; Feature (linguistics); Data mining; Machine learning; Artificial intelligence; Computational biology; Biology; Gene","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":[0.00008140791,0.0001247644,0.000104868,0.00009097573,0.00007312059,0.0002574954,0.00006841688,0.00008005061,0.000002437242],"category_scores_gemma":[0.000005362114,0.0001083656,0.0000655488,0.00008173211,0.00003301516,0.00003287704,0.00002262371,0.00005703908,0.000001027583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003108073,"about_ca_system_score_gemma":0.0001381749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002738499,"about_ca_topic_score_gemma":0.00002109794,"domain_scores_codex":[0.9994144,0.00001068186,0.000188108,0.0001729099,0.00005487983,0.000159006],"domain_scores_gemma":[0.9997817,0.000008514221,0.00003971245,0.0000998473,0.00002569712,0.00004448085],"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":[0.0001845928,0.00003214569,0.0001117319,0.0003703964,0.00005124657,7.813145e-7,0.000430308,0.000456,0.9317458,0.000702358,0.01887657,0.0470381],"study_design_scores_gemma":[0.001481665,0.0003402896,0.00222303,0.0001218873,0.00008746423,0.00005189836,0.002994389,0.4169595,0.06208326,0.001228292,0.5117786,0.0006497126],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8245448,0.009163351,0.163598,0.0005460769,0.0003453537,0.0006103717,0.0003321086,0.00004156251,0.0008183926],"genre_scores_gemma":[0.9902861,0.001845788,0.006723052,0.0001690712,0.00009491441,0.00003617926,0.0005408665,0.00001706601,0.0002869235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8696625,"threshold_uncertainty_score":0.441902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01872548788231583,"score_gpt":0.2641647738759884,"score_spread":0.2454392859936726,"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."}}