{"id":"W4414255624","doi":"10.1101/2025.09.09.675248","title":"Experimenting with Two Recent Feature Selection Methods for High-Dimensional Biological Data","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Prompt (Canada)","funders":"","keywords":"Feature selection; Replicate; Biological data; Feature (linguistics); Selection (genetic algorithm); Scalability; Noisy data","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01014504,0.001050582,0.0008993358,0.001353567,0.0006325467,0.001165422,0.001808251,0.001298351,0.001212625],"category_scores_gemma":[0.01931564,0.0003330898,0.001094117,0.001564293,0.0007907278,0.001544168,0.0008655298,0.00130619,0.0005210911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006768639,"about_ca_system_score_gemma":0.001136215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003012355,"about_ca_topic_score_gemma":0.003079848,"domain_scores_codex":[0.9970197,0.001606921,0.0001755483,0.0004977727,0.0005646448,0.0001354055],"domain_scores_gemma":[0.9859648,0.01055617,0.0004513711,0.001240732,0.001530903,0.0002560843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003700463,0.001155353,0.04141004,0.0008574456,0.001531848,0.0002892114,0.0002252181,0.4131263,0.02891395,0.006466789,0.01109527,0.4912281],"study_design_scores_gemma":[0.0002858227,0.0007301414,0.00531979,0.00002534588,0.00009065057,0.000187743,0.00005747305,0.9701729,0.01697415,0.003143505,0.002956253,0.00005618947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3602084,0.003170914,0.6275657,0.001711154,0.0003668244,0.0003165145,0.00129506,0.004478067,0.0008872294],"genre_scores_gemma":[0.6727993,0.0006048353,0.3211533,0.0003824374,0.0001124763,0.0004870377,0.003271264,0.0002252371,0.0009641774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01014504,"threshold_uncertainty_score":0.0536527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03998647398184139,"score_gpt":0.3331264907589367,"score_spread":0.2931400167770953,"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."}}