{"id":"W2974319784","doi":"10.1038/s41598-019-50229-6","title":"Model-based clustering for identifying disease-associated SNPs in case-control genome-wide association studies","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"School of Natural Sciences, Mathematics, and Engineering, California State University, Bakersfield; Natural Sciences and Engineering Research Council of Canada; California State University, Bakersfield; Canada Research Chairs; Government of Canada","keywords":"Single-nucleotide polymorphism; Cluster analysis; SNP; Genetic association; Minor allele frequency; Genome-wide association study; False discovery rate; Multiple comparisons problem","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01426494,0.001332691,0.002113131,0.003226751,0.001096847,0.00118276,0.002843019,0.001923661,0.001214856],"category_scores_gemma":[0.03865496,0.0008375428,0.00258958,0.002369098,0.001035454,0.0009106498,0.001718919,0.001995411,0.0005011365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023409,"about_ca_system_score_gemma":0.001457116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005931021,"about_ca_topic_score_gemma":0.005401016,"domain_scores_codex":[0.9896605,0.007119302,0.0004451964,0.001729575,0.0008252508,0.0002201612],"domain_scores_gemma":[0.9878213,0.008238322,0.0009833672,0.001871285,0.0008491234,0.0002365442],"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":[0.0007626971,0.0002608419,0.03640474,0.0006073226,0.003170458,0.0007124472,0.0004849417,0.7381378,0.005716981,0.03953526,0.004821705,0.1693847],"study_design_scores_gemma":[0.0000548872,0.0000736986,0.002897641,0.0000272446,0.0001545394,0.000173614,0.00003507321,0.9716405,0.000733513,0.02303493,0.001128491,0.00004587122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00991439,0.0004000738,0.9886264,0.0001480366,0.00004613069,0.0001328645,0.0001302859,0.0004316598,0.0001702078],"genre_scores_gemma":[0.3445473,0.0004930223,0.6513405,0.0003146817,0.0001318613,0.0009665901,0.001164421,0.0002062369,0.0008353791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01426494,"threshold_uncertainty_score":0.07544112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03211708583416097,"score_gpt":0.3003317447554332,"score_spread":0.2682146589212722,"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."}}