{"id":"W4383499258","doi":"10.1101/2023.07.06.548007","title":"Topological stratification of continuous genetic variation in large biobanks","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Biobank; Population stratification; Stratification (seeds); Visualization; Population; Data mining; Computer science; Geography; Biology; Genotype; Bioinformatics; Single-nucleotide polymorphism; Genetics; Gene; 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":[0.002359419,0.0002225424,0.0004750698,0.003800105,0.001068029,0.002035881,0.0004769901,0.0005362884,0.001101277],"category_scores_gemma":[0.01059919,0.0002823195,0.0004549836,0.005062025,0.001571779,0.00126776,0.00147518,0.0006460691,0.0002259696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001230009,"about_ca_system_score_gemma":0.0006463025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003838171,"about_ca_topic_score_gemma":0.004197201,"domain_scores_codex":[0.998647,0.0005767724,0.00008788805,0.0002918361,0.0002725473,0.000123993],"domain_scores_gemma":[0.9932539,0.003402395,0.001517504,0.0007875325,0.0006530276,0.0003857614],"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":[0.00095105,0.0003187736,0.6286534,0.0004606079,0.0004633403,0.001316873,0.004490495,0.1335236,0.05456597,0.07005798,0.0086719,0.09652606],"study_design_scores_gemma":[0.00008230883,0.0001735665,0.6356691,0.00009409237,0.000112872,0.0006594551,0.002680827,0.2469859,0.008773219,0.09748732,0.007127218,0.0001540908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.971143,0.0002365083,0.02574872,0.0003443194,0.00001105139,0.00003035545,0.001084308,0.0003699953,0.001031835],"genre_scores_gemma":[0.9775023,0.0001093871,0.02002328,0.00005487506,0.00001376822,0.00005035364,0.001943646,0.00005864428,0.0002437879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003838171,"threshold_uncertainty_score":0.01247793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01644006935192836,"score_gpt":0.2312277708999806,"score_spread":0.2147877015480522,"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."}}