{"id":"W2799867601","doi":"10.1101/319145","title":"Gene Set Overlap: An Impediment to Achieving High Specificity in Over-representation Analysis","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Set (abstract data type); Gene; Data set; Statistical analysis; Gene interaction","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":[0.01484431,0.0008459875,0.001613975,0.002945944,0.001118314,0.003189386,0.001694265,0.0008979462,0.0009101349],"category_scores_gemma":[0.0424668,0.0005981731,0.0009993764,0.00373651,0.003377625,0.002771111,0.003936428,0.001863805,0.0005750054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001092125,"about_ca_system_score_gemma":0.001124187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008223456,"about_ca_topic_score_gemma":0.001150488,"domain_scores_codex":[0.9789596,0.009418064,0.001300354,0.003142756,0.006150811,0.001028362],"domain_scores_gemma":[0.9331061,0.04372535,0.00481874,0.01253262,0.004987669,0.0008296229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001011507,0.0002707743,0.152314,0.001636551,0.000938795,0.001144743,0.002378346,0.03476468,0.4453894,0.05614971,0.003307008,0.3006945],"study_design_scores_gemma":[0.00005472795,0.0003555537,0.1061857,0.0003616438,0.000394588,0.004152958,0.001343483,0.3051139,0.3911116,0.1739927,0.01672791,0.00020526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3075399,0.00172383,0.6843073,0.0009452787,0.00007336064,0.0001221295,0.0003051321,0.001842752,0.003140435],"genre_scores_gemma":[0.8252952,0.000331066,0.1723838,0.0004638742,0.00004110883,0.0001390783,0.0003908631,0.0003912939,0.0005637797],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01484431,"threshold_uncertainty_score":0.07850516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01265832008404523,"score_gpt":0.2480680046949929,"score_spread":0.2354096846109477,"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."}}