{"id":"W3162447044","doi":"10.1101/2021.05.15.21257266","title":"Two-phase sample selection strategies for design and analysis in post-genome wide association fine-mapping studies","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; Terveyden ja hyvinvoinnin laitos; Oulun Yliopisto; Government of Ontario; Broad Institute; Compute Canada; University of Toronto; Ontario Institute for Cancer Research","keywords":"Genome-wide association study; Computer science; Context (archaeology); Inference; Sampling (signal processing); Genetic association; Sample size determination; Statistical power; Data mining; Computational biology; Statistics; Mathematics; Biology; Genetics; Artificial intelligence; Single-nucleotide polymorphism; Filter (signal processing)","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01240119,0.0003569053,0.001189778,0.0012875,0.0001959419,0.0009800609,0.0004391362,0.0002415918,0.00008236353],"category_scores_gemma":[0.02668782,0.000321922,0.0003314576,0.002228637,0.00006532722,0.0004531822,0.0004444692,0.0003689813,0.000003527787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005337467,"about_ca_system_score_gemma":0.0003537312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002267974,"about_ca_topic_score_gemma":0.0005602589,"domain_scores_codex":[0.9943137,0.00196995,0.001140905,0.001210048,0.0009699763,0.0003954156],"domain_scores_gemma":[0.9808615,0.01659026,0.0008306112,0.0004520703,0.001173931,0.0000916057],"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":[0.0005411986,0.0007046724,0.4898761,0.0001936926,0.005684413,0.00003907799,0.02512103,0.3146456,0.1497909,0.0003972286,0.0002738087,0.01273231],"study_design_scores_gemma":[0.005820372,0.001316202,0.3343288,0.000269931,0.00239895,0.000006504843,0.08213714,0.4116987,0.0237189,0.1348656,0.0007029467,0.002735995],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4975245,0.001465374,0.4999149,0.0002283187,0.0002188368,0.0005454211,0.00004210647,0.000029939,0.00003062098],"genre_scores_gemma":[0.5543388,0.00009595665,0.4449326,0.00009294778,0.00006248165,0.0002587633,0.00006764942,0.00001985009,0.0001309545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1555474,"threshold_uncertainty_score":0.9999233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2294715080347703,"score_gpt":0.4784005448773211,"score_spread":0.2489290368425508,"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."}}