{"id":"W3190403341","doi":"10.1101/2021.07.30.21260578","title":"Design and quality control of large-scale two-sample Mendelian randomisation studies","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK; Harvard T.H. Chan School of Public Health; Brigham and Women's Hospital; Centre International de Recherche sur le Cancer; World Health Organization","keywords":"Mendelian randomization; Genome-wide association study; Pipeline (software); Computer science; Summary statistics; Data set; Statistics; Sample size determination; Genetic association; Data mining; Data quality; Computational biology; Biology; Genetics; Mathematics; Genetic variants; Single-nucleotide polymorphism; Artificial intelligence; Engineering","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4164354,0.003187231,0.005265251,0.006642491,0.002617542,0.005733203,0.006470859,0.005296139,0.01821519],"category_scores_gemma":[0.6270888,0.004012101,0.008550096,0.00878279,0.005258221,0.003189656,0.00512308,0.005728413,0.005445111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004202613,"about_ca_system_score_gemma":0.01691317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002322832,"about_ca_topic_score_gemma":0.002565938,"domain_scores_codex":[0.3635612,0.5289935,0.05683388,0.02568894,0.02126132,0.003661117],"domain_scores_gemma":[0.4043013,0.2759641,0.06162335,0.1926466,0.06075849,0.004706173],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.07959209,0.00204251,0.04362507,0.05955131,0.0286413,0.001683542,0.01124659,0.03090645,0.00851551,0.1598124,0.114153,0.4602303],"study_design_scores_gemma":[0.1010028,0.01645751,0.0560744,0.02342609,0.02242345,0.001128189,0.001440129,0.09611227,0.03111592,0.2484721,0.4005948,0.001752342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01229825,0.002119655,0.6071755,0.002581667,0.00223463,0.3570363,0.008304873,0.003409112,0.004839942],"genre_scores_gemma":[0.04821724,0.0003775038,0.3109108,0.001411986,0.0002690442,0.635998,0.001494288,0.0004157152,0.0009054568],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5835646,"threshold_uncertainty_score":0.7196391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05327181572753027,"score_gpt":0.3476401064785222,"score_spread":0.294368290750992,"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."}}