{"id":"W4414306739","doi":"10.1101/2025.09.15.676165","title":"Personalized polygenic risk prediction and assessment with a Mixture-of-Experts framework","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Inference; Predictive modelling; Polygenic risk score; Quality (philosophy); Strengths and weaknesses; Personalized medicine; Representation (politics); Variety (cybernetics); Genetic variants","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006523442,0.001318633,0.001833479,0.001431405,0.0005747826,0.001183233,0.002320339,0.001936156,0.001940136],"category_scores_gemma":[0.009108514,0.0008590156,0.001912142,0.0009721358,0.0008202443,0.001167219,0.001760465,0.002978791,0.0007031058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008033357,"about_ca_system_score_gemma":0.001200817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01082371,"about_ca_topic_score_gemma":0.009577927,"domain_scores_codex":[0.9976883,0.001326392,0.00008456536,0.0004829653,0.0002584632,0.0001593877],"domain_scores_gemma":[0.9961551,0.002738602,0.0002233417,0.0002631772,0.0004281609,0.0001914985],"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":[0.0003023004,0.0001038246,0.005856779,0.0000461798,0.0003601977,0.0001331066,0.000128932,0.9004627,0.001065732,0.006869991,0.002923683,0.08174655],"study_design_scores_gemma":[0.000006396551,0.00001221862,0.0001997649,0.000005981587,0.00001326802,0.00001165323,0.00000372898,0.9958264,0.0001129151,0.003638908,0.0001625687,0.000006212415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03051634,0.0004339487,0.9668118,0.0006141362,0.00005154922,0.00005115874,0.0002084803,0.000634424,0.0006781658],"genre_scores_gemma":[0.6441377,0.0003835913,0.3491868,0.0007584858,0.0003293086,0.0002538086,0.00115089,0.0001624996,0.003636767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01082371,"threshold_uncertainty_score":0.0344997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00898056053010192,"score_gpt":0.2378302793701405,"score_spread":0.2288497188400386,"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."}}