{"id":"W4414339439","doi":"10.1101/2025.09.15.676316","title":"Challenges to case-only analysis for gene-environment interaction detection using polygenic risk scores: model assumptions and biases in large biobanks","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Division of Graduate Education; University of Wisconsin-Madison","keywords":"Biobank; False positive paradox; Population; Collider; Spurious relationship; Disease; Regression analysis; False positives and false negatives; Regression","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":[0.3670293,0.001169725,0.002809096,0.002215193,0.002553083,0.006132321,0.006454258,0.00241999,0.003530224],"category_scores_gemma":[0.6422675,0.00162233,0.002267332,0.003984937,0.004744508,0.003933316,0.005906806,0.005598902,0.001259484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00195919,"about_ca_system_score_gemma":0.004208114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009082659,"about_ca_topic_score_gemma":0.006979106,"domain_scores_codex":[0.6563073,0.3063125,0.01044497,0.01412042,0.01156148,0.00125328],"domain_scores_gemma":[0.2123173,0.6985019,0.02476553,0.05153178,0.0116012,0.001282329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002154017,0.0006445998,0.514675,0.002553856,0.006293319,0.004150496,0.008633803,0.07059887,0.003312607,0.1293394,0.04683391,0.2108101],"study_design_scores_gemma":[0.0007575249,0.0006540185,0.08521361,0.001669395,0.001124833,0.003410291,0.002464076,0.3664207,0.005378753,0.4888751,0.04372672,0.0003050534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0793342,0.001798479,0.8980699,0.0118285,0.0006440958,0.001278275,0.002716159,0.001092919,0.003237439],"genre_scores_gemma":[0.5280826,0.000610206,0.4580279,0.005199477,0.0005237766,0.00384427,0.002149876,0.0004210428,0.001140792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3670293,"threshold_uncertainty_score":0.7805656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04462764582333377,"score_gpt":0.2900034014385843,"score_spread":0.2453757556152505,"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."}}