{"id":"W2987322729","doi":"10.1371/journal.pgen.1008432","title":"UMAP reveals cryptic population structure and phenotype heterogeneity in large genomic cohorts","year":2019,"lang":"en","type":"article","venue":"PLoS Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":258,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research; Canada Excellence Research Chairs, Government of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Biology; Population; Evolutionary biology; Dimension (graph theory); Scale (ratio); Variation (astronomy); Computational biology; Phenotype; Population size; Genome; Projection (relational algebra); Genetics; Cartography; Computer science; Geography; Mathematics; Algorithm; Demography; Gene","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":[0.00350859,0.000342077,0.0004893204,0.001163706,0.0007367697,0.001075453,0.0004791725,0.0004166533,0.001055609],"category_scores_gemma":[0.0104876,0.0002405912,0.0007323152,0.001160261,0.0007175492,0.0006938609,0.002228622,0.001246886,0.0002645835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003043697,"about_ca_system_score_gemma":0.0006227327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002265821,"about_ca_topic_score_gemma":0.003300194,"domain_scores_codex":[0.9987544,0.0007283801,0.00005414588,0.0003087852,0.000092661,0.00006168669],"domain_scores_gemma":[0.9954693,0.002284719,0.0004388129,0.001436912,0.0001572563,0.0002129835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008407937,0.0001925655,0.6915829,0.0002791859,0.001770791,0.0008265365,0.002241669,0.04326252,0.02258753,0.02378749,0.009185676,0.2034424],"study_design_scores_gemma":[0.0001351734,0.0003711384,0.5364597,0.00009551022,0.0003459829,0.001011374,0.001732361,0.3222079,0.006542782,0.1209977,0.009996541,0.0001037118],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8770337,0.0004872975,0.1176914,0.0009528775,0.00004091999,0.00004309767,0.001922217,0.0007261436,0.001102429],"genre_scores_gemma":[0.9640296,0.0001555696,0.03360026,0.000129028,0.00003311779,0.00004586116,0.001690055,0.00008089208,0.0002356548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00350859,"threshold_uncertainty_score":0.0185554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01010903290458093,"score_gpt":0.2486461602683072,"score_spread":0.2385371273637262,"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."}}