{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001799416,0.000160864,0.0002558757,0.00005003672,0.00004033206,0.00001449883,0.0001115112,0.0002584828,0.00003485914],"category_scores_gemma":[0.00007205415,0.0001645122,0.00004143517,0.00006613793,0.00002181403,0.000002328899,0.0001302076,0.00009931409,0.00001361745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002990452,"about_ca_system_score_gemma":0.00002508309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001263064,"about_ca_topic_score_gemma":0.0001981124,"domain_scores_codex":[0.9987687,0.0001225034,0.0003019448,0.0003949915,0.00008983558,0.0003220379],"domain_scores_gemma":[0.9993995,0.00001855258,0.0001204498,0.0003441661,0.00004752423,0.00006973575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001137028,0.00002718078,0.7872041,0.00001966807,0.00002986738,4.553125e-7,0.0000269012,0.0004982556,0.2119515,0.00002088472,0.00005948673,0.0001503681],"study_design_scores_gemma":[0.0005009444,0.0001305788,0.9890643,0.000008862968,0.00002457568,0.00000386982,0.00001812069,0.002003906,0.006865835,0.0006775094,0.0005010557,0.0002004075],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978325,0.001468539,0.00004942657,0.00005329866,0.0001308527,0.0003419105,0.00004051299,0.00001179556,0.00007109952],"genre_scores_gemma":[0.9975361,0.000244324,0.001446529,0.0003088259,0.0001168282,0.000008506816,0.0002296716,0.00003429081,0.00007498284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2050857,"threshold_uncertainty_score":0.6708612,"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."}}