{"id":"W4391445695","doi":"10.1101/2024.01.30.24302021","title":"A novel and efficient machine learning Mendelian randomization estimator applied to predict the safety and efficacy of sclerostin inhibition","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University; Institut universitaire de cardiologie et de pneumologie de Québec; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Mendelian randomization; Sclerostin; Estimator; Quantile; Instrumental variable; Causal inference; Confounding; Econometrics; Osteoporosis; Statistics; Computer science; Medicine; Internal medicine; Mathematics; Biology; Genotype; Genetics; Genetic variants","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":[0.0141775,0.000601052,0.001404371,0.001028155,0.0002793233,0.0008341268,0.001436077,0.001079885,0.002554737],"category_scores_gemma":[0.05547662,0.0003995836,0.001042884,0.0009052119,0.001065241,0.0007162692,0.001235061,0.001492012,0.0003844632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000553882,"about_ca_system_score_gemma":0.001528171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001566429,"about_ca_topic_score_gemma":0.0009748869,"domain_scores_codex":[0.9933299,0.005327685,0.0001880862,0.0005673792,0.0004130664,0.000173919],"domain_scores_gemma":[0.9652191,0.02892991,0.002454128,0.00209994,0.001026431,0.0002704536],"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":[0.001361441,0.0003022854,0.05940257,0.0004629639,0.001164509,0.0004954556,0.0001629337,0.4995826,0.005877644,0.1537293,0.007235209,0.270223],"study_design_scores_gemma":[0.0001343926,0.0001806049,0.003229562,0.00004577544,0.0000917537,0.0001460434,0.00001597923,0.9537966,0.001451083,0.03894936,0.001930983,0.00002778805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01316355,0.0002134207,0.9854418,0.0002265395,0.0000406739,0.00009132482,0.0001844812,0.0003138107,0.0003244175],"genre_scores_gemma":[0.5285162,0.0004591699,0.4668519,0.0004984059,0.0002063602,0.0005925519,0.0009875583,0.0001658069,0.001721973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0141775,"threshold_uncertainty_score":0.07497871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01132586971717154,"score_gpt":0.2468711282930947,"score_spread":0.2355452585759232,"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."}}