{"id":"W4380870059","doi":"10.1093/gigascience/giad043","title":"EraSOR: a software tool to eliminate inflation caused by sample overlap in polygenic score analyses","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; Medical Research Council; National Institutes of Health; King's College London; National Institute for Health and Care Research; Medical Research Council Canada; South London and Maudsley NHS Foundation Trust","keywords":"Sample size determination; Sample (material); Genome-wide association study; Computer science; Statistics; Large sample; Polygenic risk score; Software; Inflation (cosmology); Scale (ratio); Computational biology; Biology; Mathematics; Genetics; Single-nucleotide polymorphism; Cartography; Physics; Genotype","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004900342,0.00009901568,0.0001291152,0.0000858924,0.0002127217,0.00001647429,0.0002732448,0.00005149157,0.00006144045],"category_scores_gemma":[0.0008363005,0.0001047902,0.00005265739,0.0004546193,0.00004136535,0.000005116015,0.0002526361,0.00008457701,0.000007051316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006833088,"about_ca_system_score_gemma":0.0001177935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003064633,"about_ca_topic_score_gemma":0.0002128867,"domain_scores_codex":[0.998776,0.000115576,0.0002266965,0.0003904637,0.0001779159,0.0003133152],"domain_scores_gemma":[0.999501,0.00004684919,0.0000833583,0.0002665545,0.00004005933,0.00006214633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002362266,0.00005801916,0.4751814,0.000003415169,0.00001331124,0.000001483322,0.0001967615,0.01418781,0.5003058,0.00002705913,0.005414805,0.004586566],"study_design_scores_gemma":[0.0004287644,0.0004502435,0.9649103,0.000004176958,0.00001246392,0.000004918302,0.000315659,0.001231705,0.01066754,0.0003249845,0.0213227,0.0003265325],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917631,0.0002198015,0.00721267,0.0003847214,0.000100283,0.0001637451,0.0001089276,0.000009399268,0.00003736978],"genre_scores_gemma":[0.9948352,0.00002244239,0.003406588,0.001193055,0.00002772736,0.00008380794,0.0001552374,0.00000812179,0.0002678257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.489729,"threshold_uncertainty_score":0.4273221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02752959332814869,"score_gpt":0.3079644849386726,"score_spread":0.2804348916105239,"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."}}