{"id":"W2914040916","doi":"10.1109/bibm.2018.8621462","title":"Sample Size and Reproducibility of Gene Set Analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Reproducibility; Sample size determination; False positive paradox; Sample (material); Set (abstract data type); Computer science; Data set; Data mining; Statistics; Artificial intelligence; Mathematics; Chemistry; Chromatography","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":[0.09066434,0.0008808647,0.001696281,0.002324339,0.001417075,0.002486584,0.001909471,0.002022695,0.0009964738],"category_scores_gemma":[0.2598746,0.0006451913,0.001880902,0.002135906,0.002724625,0.001301999,0.00245925,0.001698684,0.0005558157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000846602,"about_ca_system_score_gemma":0.0009997931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006332434,"about_ca_topic_score_gemma":0.000732673,"domain_scores_codex":[0.8668494,0.07414853,0.01507001,0.01578006,0.02671955,0.001432553],"domain_scores_gemma":[0.6940041,0.2197971,0.009573825,0.04778674,0.02797391,0.0008644543],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007529512,0.001088617,0.2603415,0.004178517,0.003542447,0.0009546006,0.00416617,0.0230286,0.3812185,0.01347516,0.006304037,0.2941723],"study_design_scores_gemma":[0.0006072674,0.004653069,0.1988097,0.0007463674,0.003106531,0.00226006,0.0008015322,0.05662909,0.674157,0.02925026,0.02843552,0.0005436107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3147961,0.008138231,0.6648974,0.001464282,0.001789523,0.002034823,0.00184392,0.001664939,0.003370717],"genre_scores_gemma":[0.7226194,0.0009854392,0.267015,0.0008000744,0.000295533,0.00380466,0.002647758,0.0008391836,0.0009929792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9093357,"threshold_uncertainty_score":0.4794846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0117968417584716,"score_gpt":0.2528681228068174,"score_spread":0.2410712810483458,"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."}}