{"id":"W2794553059","doi":"","title":"CREAM: new feature selection approach for epigenomic profiles of cells","year":2018,"lang":"en","type":"article","venue":"Research in Computational Molecular Biology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Epigenomics; Computer science; Feature selection; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Chemistry; DNA methylation","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":[0.00102241,0.0008491506,0.001272246,0.00199818,0.0003985288,0.0007953176,0.0009450695,0.0006981748,0.002840277],"category_scores_gemma":[0.001601785,0.00020862,0.001358594,0.001594037,0.0001752558,0.0005983719,0.001015363,0.0007249342,0.001211599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002411537,"about_ca_system_score_gemma":0.000529798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001943602,"about_ca_topic_score_gemma":0.00301285,"domain_scores_codex":[0.9996246,0.00006362428,0.00002753877,0.0001117781,0.0001072006,0.00006520313],"domain_scores_gemma":[0.9995597,0.0001691056,0.00002877622,0.00005869554,0.0001423481,0.00004132915],"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":[0.001317826,0.0004506189,0.01602648,0.0003714737,0.0005830171,0.0003046607,0.0001163135,0.01949417,0.09767858,0.001403648,0.0341424,0.8281108],"study_design_scores_gemma":[0.0002788883,0.0006191498,0.03715932,0.00004652897,0.0004106015,0.0006860282,0.0001902386,0.8777796,0.04903493,0.00935642,0.02431577,0.0001224496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1036698,0.00110314,0.8745755,0.0003101201,0.0002457091,0.00025839,0.009236732,0.009248763,0.001351858],"genre_scores_gemma":[0.4791484,0.0005467226,0.4796762,0.0004285919,0.0003486015,0.0007724663,0.03109606,0.0008444507,0.007138489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002840277,"threshold_uncertainty_score":0.009501696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06525411104604177,"score_gpt":0.4057354812409324,"score_spread":0.3404813701948907,"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."}}