{"id":"W2921446414","doi":"10.5220/0007376901820193","title":"Gene Set Overlap: An Impediment to Achieving High Specificity in Over-representation Analysis","year":2019,"lang":"en","type":"article","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Set (abstract data type); Representation (politics); Computer science; Data set; Gene; Computational biology; Data mining; Artificial intelligence; Biology; Genetics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01845362,0.000943572,0.001773034,0.00345303,0.001117657,0.002868041,0.001468129,0.0008593242,0.0008420652],"category_scores_gemma":[0.04300619,0.0005970855,0.001178549,0.003854038,0.003373078,0.002396914,0.003814124,0.001735971,0.0006624369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001046724,"about_ca_system_score_gemma":0.001188415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008320501,"about_ca_topic_score_gemma":0.001500056,"domain_scores_codex":[0.9748589,0.01149769,0.001679548,0.003567434,0.007171136,0.00122536],"domain_scores_gemma":[0.9283941,0.04931172,0.004415222,0.01257306,0.004664627,0.0006412235],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0010655,0.0002369206,0.1391471,0.00203122,0.0009888153,0.001046119,0.002897688,0.02368959,0.3668322,0.03996103,0.002570562,0.4195332],"study_design_scores_gemma":[0.00006966136,0.0006828972,0.161756,0.000520014,0.0005820299,0.006539787,0.001991094,0.2193747,0.3976808,0.1817606,0.02875841,0.0002840759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2439449,0.002244339,0.7470113,0.000747608,0.00007183498,0.0002077734,0.0003220167,0.001683097,0.003767121],"genre_scores_gemma":[0.7614574,0.0005267285,0.2353049,0.0005491592,0.00004757604,0.0002687418,0.0005197675,0.0004333465,0.00089242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9815464,"threshold_uncertainty_score":0.09759319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01536468960941936,"score_gpt":0.3062355042943524,"score_spread":0.2908708146849331,"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."}}