{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004062114,0.001025594,0.001191259,0.0008272302,0.0003522183,0.0006517311,0.0009240853,0.0006406787,0.0006274377],"category_scores_gemma":[0.005392809,0.0002679967,0.001062375,0.0006812396,0.0003271324,0.0009506326,0.0006806731,0.0007893366,0.0002283473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004944149,"about_ca_system_score_gemma":0.0007354257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003526653,"about_ca_topic_score_gemma":0.005161383,"domain_scores_codex":[0.9990005,0.000538011,0.00004844607,0.0001682598,0.0001473705,0.00009750937],"domain_scores_gemma":[0.998007,0.001336072,0.00009683416,0.0001849861,0.0003058517,0.00006927722],"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":[0.0003373849,0.0001892885,0.008094857,0.00005578319,0.000434203,0.0001198759,0.0000706888,0.8202017,0.009328529,0.001429647,0.001068249,0.1586698],"study_design_scores_gemma":[0.000008172438,0.00006194203,0.0007720752,0.000003436945,0.00002348793,0.00001707327,0.00001051622,0.9961123,0.001461361,0.001363194,0.000160249,0.00000627933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1174683,0.0005664103,0.8804254,0.0002291328,0.00003173326,0.00006862496,0.0001329049,0.000616456,0.0004610336],"genre_scores_gemma":[0.8121673,0.0002112556,0.1858978,0.0001723008,0.00005034441,0.0001664508,0.0005851173,0.00006226318,0.0006871865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004062114,"threshold_uncertainty_score":0.02148277,"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."}}