{"id":"W2943009138","doi":"10.1101/624908","title":"Legacy Data Confounds Genomics Studies","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Population stratification; Imputation (statistics); Spurious relationship; 1000 Genomes Project; Genomics; Genome-wide association study; Population; Biology; Data quality; Statistical genetics; Genetic data; Computational biology; Genome; Computer science; Genetics; Missing data; Demography; Gene; Single-nucleotide polymorphism; Engineering; Machine learning","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":[],"category_scores_codex":[0.1839467,0.0007053199,0.0014462,0.004865764,0.002522641,0.005187126,0.00362467,0.002208014,0.008037961],"category_scores_gemma":[0.4268391,0.0008056317,0.001027741,0.009913946,0.004780008,0.004003562,0.00597228,0.004191495,0.001197178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887664,"about_ca_system_score_gemma":0.002377132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005759933,"about_ca_topic_score_gemma":0.004815898,"domain_scores_codex":[0.8325664,0.1232139,0.01019278,0.01805962,0.01433245,0.001634954],"domain_scores_gemma":[0.4474852,0.4060985,0.03184676,0.09046143,0.01997076,0.004137361],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001148129,0.0002111428,0.5948258,0.002079476,0.003567717,0.001533046,0.01094344,0.001457573,0.001109251,0.1011265,0.09691123,0.1850867],"study_design_scores_gemma":[0.0003253614,0.0002965926,0.3665521,0.004053736,0.002751768,0.003495339,0.003975396,0.005843005,0.003959924,0.2684135,0.3400611,0.0002722531],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3707529,0.03828431,0.3184657,0.1725994,0.0103625,0.0009979153,0.03903411,0.001483651,0.04801954],"genre_scores_gemma":[0.8438787,0.004595103,0.07619746,0.05023564,0.006945204,0.001127164,0.01120608,0.001197935,0.00461671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8160533,"threshold_uncertainty_score":0.9728149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04394886926549438,"score_gpt":0.2878497976135977,"score_spread":0.2439009283481034,"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."}}