{"id":"W2944658903","doi":"10.3389/fgene.2019.00452","title":"Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data","year":2019,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Diamantina Institute, University of Queensland; Université Laval; L'Oreal USA","keywords":"Feature selection; Biomarker discovery; Computer science; Machine learning; Profiling (computer programming); Artificial intelligence; Context (archaeology); Data mining; Software; Biomarker; Categorical variable; Feature (linguistics); Omics; Bioinformatics; Proteomics; Biology","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":[0.0002156103,0.0001329925,0.0001552481,0.0001115,0.00003106974,0.00002783957,0.0002863762,0.000221306,0.000007358987],"category_scores_gemma":[0.00002569504,0.0001331359,0.00003697628,0.0001779877,0.00002233115,0.0000115062,0.0001437279,0.00008933111,0.00000277293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004798487,"about_ca_system_score_gemma":0.0001148691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005837086,"about_ca_topic_score_gemma":0.00009539908,"domain_scores_codex":[0.9989014,0.00004990163,0.0002002637,0.0004847902,0.0001201575,0.0002435056],"domain_scores_gemma":[0.9992938,0.000005560133,0.0000800358,0.0005462334,0.00003594849,0.00003840563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003381661,0.0002469981,0.2837464,0.000103829,0.00005233095,5.201023e-7,0.00009321851,0.00291633,0.4735153,0.0000237487,0.2277151,0.0112481],"study_design_scores_gemma":[0.005131012,0.0002770654,0.2524693,0.00008988573,0.00004103152,0.000006478415,0.0006086385,0.508453,0.0877311,0.0006019911,0.1438954,0.0006951345],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9470765,0.001382475,0.0492996,0.0002365563,0.001287984,0.0004998473,0.0001569897,0.00000905846,0.00005096826],"genre_scores_gemma":[0.9379676,0.000290723,0.05664758,0.0002725115,0.0001378712,0.00005679252,0.00216939,0.00003608827,0.00242143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5055366,"threshold_uncertainty_score":0.5429124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01053283672566128,"score_gpt":0.2558195365858338,"score_spread":0.2452866998601726,"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."}}