{"id":"W2981736362","doi":"10.1186/s40246-019-0226-2","title":"Size matters: how sample size affects the reproducibility and specificity of gene set analysis","year":2019,"lang":"en","type":"article","venue":"Human Genomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Reproducibility; False positive paradox; Sample (material); Set (abstract data type); Data set; Computer science; Statistics; Computational biology; False discovery rate; Data mining; Biology; Gene; Genetics; Artificial intelligence; Mathematics; Chemistry; Chromatography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004649675,0.0001026611,0.0001647804,0.00002217903,0.00006921616,0.0000306304,0.0001775394,0.00007076865,0.0001027967],"category_scores_gemma":[0.0001458116,0.00008058827,0.00009170133,0.0001067737,0.00008131201,0.000002650404,0.00009194881,0.00005409392,0.000002657034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001710585,"about_ca_system_score_gemma":0.00002447045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002748685,"about_ca_topic_score_gemma":0.00003963608,"domain_scores_codex":[0.9989634,0.0000853954,0.000136822,0.0006118863,0.00008385156,0.00011867],"domain_scores_gemma":[0.9982825,0.00006792135,0.000145136,0.001415854,0.00005048807,0.00003812485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003223022,0.00002107507,0.02047683,0.00001852368,0.0001043304,7.616685e-8,0.0001286193,0.00006738536,0.9769325,0.00002876754,0.001940441,0.0002492717],"study_design_scores_gemma":[0.000349731,0.0001085758,0.2844255,0.000002974407,0.0001256553,0.00000150916,0.0004218318,0.00005867498,0.6842253,0.0001780429,0.02993136,0.000170895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998261,0.000286257,0.0003625035,0.0005958475,0.00006166306,0.0002153768,0.00005986726,0.000005268202,0.0001522656],"genre_scores_gemma":[0.9979944,0.0001077119,0.0007570027,0.0002985683,0.000103812,0.000008082116,0.00006569506,0.00001087009,0.0006538767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2927072,"threshold_uncertainty_score":0.3286294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02048667910047409,"score_gpt":0.2585244882334746,"score_spread":0.2380378091330005,"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."}}