{"id":"W146732357","doi":"10.1007/978-3-319-16706-0_20","title":"Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Feature selection; Linear model; Artificial neural network; Regularization (linguistics); Feature (linguistics); Pattern recognition (psychology); Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003901047,0.0001960296,0.0001456786,0.0001021893,0.00008957083,0.00009743204,0.0002486537,0.0002345105,0.000002014605],"category_scores_gemma":[0.00003049317,0.0001866064,0.00002191833,0.00007804705,0.000226975,0.000005316583,0.0003026156,0.0001684579,0.000001960665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005699014,"about_ca_system_score_gemma":0.0001070742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003191776,"about_ca_topic_score_gemma":0.00009718251,"domain_scores_codex":[0.9988869,0.00001466075,0.0001157872,0.0006541883,0.0001503242,0.000178181],"domain_scores_gemma":[0.9994367,0.00001783401,0.00007382999,0.0002623251,0.0001032033,0.0001061032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007810003,0.00001770156,0.0001941814,0.00009657279,0.00004172582,0.000004618577,0.0007865687,0.01999312,0.1833143,0.00272743,0.0001280166,0.7926176],"study_design_scores_gemma":[0.002166388,0.003104177,0.004654968,0.0006521898,0.0001680938,0.0009463949,0.0000127661,0.3938566,0.1035589,0.4421928,0.04402354,0.004663149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01470268,0.001073417,0.9832073,0.0001862907,0.0001698457,0.0003054768,0.000003837024,0.000009130415,0.0003420038],"genre_scores_gemma":[0.9230872,0.0001914508,0.07459292,0.0008568166,0.000485043,0.0000202901,0.00004339329,0.00004115649,0.0006816826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9086144,"threshold_uncertainty_score":0.7609587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00514727866085998,"score_gpt":0.2466586401508765,"score_spread":0.2415113614900165,"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."}}