{"id":"W2890993253","doi":"10.1101/423632","title":"Revealing multi-scale population structure in large cohorts","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Population; Principal component analysis; Scale (ratio); Sampling (signal processing); Population genetics; Computer science; Data mining; Geography; Artificial intelligence; Cartography; Demography","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":[0.002088442,0.0002946558,0.0003200342,0.001580171,0.000489437,0.0009553113,0.0003540698,0.0003565763,0.001320072],"category_scores_gemma":[0.004764938,0.0001994543,0.0006705218,0.001304105,0.0003562795,0.0004668396,0.001110782,0.00082129,0.0002067451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003290492,"about_ca_system_score_gemma":0.0004471445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003682391,"about_ca_topic_score_gemma":0.004596852,"domain_scores_codex":[0.9995413,0.0002160191,0.00002288183,0.0001010149,0.00007774092,0.00004119303],"domain_scores_gemma":[0.9971455,0.001686343,0.0002871889,0.0004100376,0.000301929,0.0001689769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008759525,0.0002825691,0.4948739,0.0003713761,0.001082422,0.001751518,0.003183522,0.1495606,0.05999788,0.01934157,0.02269667,0.2459822],"study_design_scores_gemma":[0.00008884545,0.000153069,0.4053962,0.00007238647,0.0001284713,0.0005407947,0.001597832,0.532854,0.01098521,0.03841658,0.009636719,0.0001299332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8619557,0.0003052027,0.1324209,0.0008155774,0.00004938355,0.00006836444,0.002096997,0.001109968,0.001177828],"genre_scores_gemma":[0.9177482,0.0001370322,0.07962504,0.0001074605,0.00002985817,0.00007126846,0.001783299,0.0001067705,0.0003910338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003682391,"threshold_uncertainty_score":0.01104486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01104248635408904,"score_gpt":0.2239578334063384,"score_spread":0.2129153470522494,"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."}}