{"id":"W4396927899","doi":"10.1101/2024.05.13.593724","title":"Dimension Reduction using Local Principal Components for Regression-based Multi-SNP Analysis in 1000 Genomes and the Canadian Longitudinal Study on Aging (CLSA)","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Collinearity; Statistics; Regression; SNP; Single-nucleotide polymorphism; Principal component analysis; Imputation (statistics); Linear regression; Regression analysis; Mathematics; Biology; Genetics; Gene; Genotype; Missing data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01581633,0.001113946,0.001331182,0.002363233,0.0009678505,0.00103746,0.001404125,0.0008213866,0.001824305],"category_scores_gemma":[0.04806568,0.0004421906,0.00258294,0.003103991,0.001086882,0.0009003678,0.001336948,0.002392557,0.0003519511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001450673,"about_ca_system_score_gemma":0.003623863,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04386014,"about_ca_topic_score_gemma":0.03697319,"domain_scores_codex":[0.9911286,0.006567836,0.0003158065,0.0008290954,0.0008738811,0.0002848023],"domain_scores_gemma":[0.9723821,0.02010072,0.001391344,0.003151279,0.002527769,0.000446773],"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":[0.001001834,0.000280347,0.08771279,0.0006268636,0.003170666,0.000427099,0.0005534469,0.5225342,0.006015455,0.02476764,0.01066227,0.3422474],"study_design_scores_gemma":[0.0001080177,0.0001304577,0.02062066,0.00005693279,0.0001649046,0.00008082449,0.00007528048,0.9609762,0.002702554,0.01233271,0.002654335,0.00009711758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1087691,0.00126725,0.8844888,0.0008240772,0.0001866381,0.0004362591,0.001374449,0.001978761,0.0006746328],"genre_scores_gemma":[0.3818412,0.000352612,0.6141478,0.0001830704,0.00006988415,0.0007780046,0.00181168,0.000274792,0.000540969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9561399,"threshold_uncertainty_score":0.0872097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05344568067900334,"score_gpt":0.3102661313679576,"score_spread":0.2568204506889543,"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."}}