{"id":"W4409461002","doi":"10.21203/rs.3.rs-6322956/v1","title":"Selecting variant masks to improve power and replicability of gene-level burden tests","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Human Genome Research Institute","keywords":"Masking (illustration); Biobank; Association test; Association (psychology); Genetic association; Coding (social sciences); Computer science; Statistical power; Computational biology; Biology; Genetics; Statistics; Single-nucleotide polymorphism; Gene; Psychology; Mathematics; Genotype","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":[0.1326275,0.002681553,0.004254456,0.003127568,0.002459733,0.004757443,0.00524899,0.006321379,0.008290497],"category_scores_gemma":[0.4791144,0.002380536,0.003553767,0.003251825,0.004146281,0.006098117,0.005156572,0.004868286,0.00155993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007686184,"about_ca_system_score_gemma":0.003700531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003232239,"about_ca_topic_score_gemma":0.002689261,"domain_scores_codex":[0.9266579,0.05478254,0.004504573,0.008862352,0.003553345,0.001639187],"domain_scores_gemma":[0.3674195,0.5608214,0.008442507,0.05357824,0.007220213,0.002518078],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01596107,0.001041904,0.2313029,0.002106814,0.009332188,0.003657204,0.003538749,0.1249079,0.04206049,0.08783346,0.01664072,0.4616166],"study_design_scores_gemma":[0.00360709,0.002168873,0.05192227,0.0004041799,0.005274924,0.002363999,0.0004420595,0.6496336,0.0303476,0.240806,0.01265377,0.00037559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1412869,0.001372708,0.8484139,0.001710911,0.0006613586,0.0005823951,0.001163216,0.002923416,0.001885289],"genre_scores_gemma":[0.5788876,0.0003010748,0.4145022,0.0008371483,0.0005208388,0.0007469698,0.001306163,0.001046194,0.001851916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8673725,"threshold_uncertainty_score":0.7014097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05032994656358145,"score_gpt":0.3994971219782061,"score_spread":0.3491671754146247,"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."}}