{"id":"W4390722087","doi":"10.1101/2024.01.03.24300779","title":"Valid inference for machine learning-assisted GWAS","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Jewish General Hospital; University of Toronto","funders":"National Institute on Aging; National Institutes of Health; Division of Graduate Education; University of Wisconsin-Madison; Wisconsin Alumni Research Foundation","keywords":"Genome-wide association study; Imputation (statistics); Inference; Computer science; Computational biology; Statistical inference; Data mining; Statistics; Machine learning; Artificial intelligence; Biology; Single-nucleotide polymorphism; Genetics; Missing data; Mathematics; Gene; 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":[],"consensus_categories":[],"category_scores_codex":[0.08332887,0.001227253,0.002017413,0.002200595,0.001129822,0.003394321,0.003426353,0.001724751,0.00331823],"category_scores_gemma":[0.2666716,0.001216376,0.001903384,0.002871913,0.004537632,0.002029281,0.003721321,0.004134121,0.0009141654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001372246,"about_ca_system_score_gemma":0.004118573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173119,"about_ca_topic_score_gemma":0.003198431,"domain_scores_codex":[0.9429591,0.04855502,0.001517337,0.003676443,0.002748769,0.0005433484],"domain_scores_gemma":[0.6869909,0.268306,0.007864506,0.03008143,0.005702078,0.001055096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001167841,0.0002029645,0.07080291,0.0009937908,0.002879699,0.00133005,0.0005211326,0.3966382,0.002330431,0.3311467,0.01513558,0.1768506],"study_design_scores_gemma":[0.0001753468,0.00007604621,0.002470673,0.0001166893,0.000140433,0.0001934415,0.00003733654,0.5597541,0.001508593,0.4310116,0.004473277,0.00004244533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005791019,0.0003422596,0.9908019,0.001044173,0.0001137615,0.00005766654,0.0004953272,0.0008296498,0.00052427],"genre_scores_gemma":[0.367092,0.0004612125,0.6254562,0.002208643,0.0006546486,0.0004666382,0.001954379,0.0005081642,0.001198122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08332887,"threshold_uncertainty_score":0.4406905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358669316496831,"score_gpt":0.3270543988208504,"score_spread":0.2911874671711673,"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."}}