{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01554676,0.00292703,0.002094609,0.003848241,0.0009210255,0.002888879,0.003500728,0.001550134,0.04314724],"category_scores_gemma":[0.07013723,0.002124499,0.003195619,0.002319663,0.001281988,0.00285926,0.005566038,0.003011659,0.01411692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006018393,"about_ca_system_score_gemma":0.002191053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001299371,"about_ca_topic_score_gemma":0.002388133,"domain_scores_codex":[0.9937025,0.002724711,0.0008424178,0.001149573,0.001320249,0.0002606895],"domain_scores_gemma":[0.9461513,0.04534719,0.002698574,0.003423766,0.001860519,0.0005185759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002516854,0.0003873291,0.02703406,0.003782854,0.00328645,0.001910102,0.002933843,0.01465101,0.01191578,0.02389034,0.3880769,0.5196145],"study_design_scores_gemma":[0.002871695,0.000755897,0.03585722,0.001418239,0.001547957,0.003735073,0.0007322301,0.3420491,0.0573156,0.1425965,0.4101089,0.001011661],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00510107,0.0003368114,0.7068329,0.0003121727,0.000253107,0.0002545085,0.005563996,0.2797956,0.001549747],"genre_scores_gemma":[0.04480966,0.0003295521,0.8742571,0.0008040303,0.0002231103,0.002156788,0.007556959,0.06634289,0.003519868],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04314724,"threshold_uncertainty_score":0.1443419,"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."}}