{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003327092,0.0003527642,0.0003574494,0.0001286437,0.0001341459,0.00008957227,0.0003259823,0.0006868142,0.00004065961],"category_scores_gemma":[0.00008603295,0.0003825572,0.0001026636,0.0001265545,0.00004467467,0.000004973418,0.0004761522,0.0003149414,0.00001200828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004446699,"about_ca_system_score_gemma":0.0001162596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001149977,"about_ca_topic_score_gemma":0.00005682198,"domain_scores_codex":[0.9981209,0.00008872031,0.000342877,0.0008184434,0.0001899169,0.0004391093],"domain_scores_gemma":[0.9987785,0.000005784199,0.0002278134,0.0006666071,0.000182477,0.0001387911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002755782,0.00008075735,0.3007722,0.0001463131,0.00004822899,0.0000125494,0.000008708092,0.000137291,0.6981229,0.000009220405,0.0006335534,7.441171e-7],"study_design_scores_gemma":[0.0007854887,0.00006902091,0.7526002,0.0003100803,0.00005630913,4.009367e-8,0.00000644036,0.0004944556,0.2391578,0.000002112817,0.005770569,0.0007474638],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964964,0.0006351583,0.0009930041,0.00003076892,0.0007066936,0.0003272583,0.0007558931,0.00004687085,0.000007985128],"genre_scores_gemma":[0.9931826,0.0001816861,0.005819032,0.0001696158,0.0005600397,0.00001339972,0.00001428834,0.00004304745,0.00001626447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4589651,"threshold_uncertainty_score":0.9998626,"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."}}