{"id":"W4405221092","doi":"10.1093/bioinformatics/btae719","title":"PheWAS analysis on large-scale biobank data with PheTK","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Biobank; Computer science; Scale (ratio); Data science; Bioinformatics; Biology; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003848661,0.0001413883,0.0001861951,0.0001057952,0.000078896,0.00005155376,0.0003083108,0.0001376954,0.00004826757],"category_scores_gemma":[0.00006089412,0.000102952,0.00008258618,0.0003838174,0.00004184048,0.000007753111,0.0001709142,0.00008348917,0.0001264611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001031167,"about_ca_system_score_gemma":0.00007757002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009698892,"about_ca_topic_score_gemma":0.0001387387,"domain_scores_codex":[0.9990487,0.00002920749,0.0002735904,0.0002524722,0.0001269453,0.0002691552],"domain_scores_gemma":[0.9989509,0.00002742445,0.00007182043,0.0008395075,0.00004148692,0.00006886592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003364129,0.0008187646,0.1421638,0.0006689382,0.01402666,0.00003513581,0.003032689,0.01695341,0.003800569,0.003998599,0.7420889,0.0720761],"study_design_scores_gemma":[0.0004826602,0.0005138408,0.01504896,0.00003317338,0.0007972427,0.00001485253,0.0008290463,0.3147897,0.0007989964,0.00004969379,0.6661792,0.0004626816],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5623994,0.002181554,0.3957829,0.001852237,0.0007046754,0.0005217705,0.002268303,0.0001785808,0.03411063],"genre_scores_gemma":[0.9521703,0.0003567671,0.03986096,0.001047543,0.0002622401,0.00001310423,0.00463627,0.00002427028,0.001628624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3897708,"threshold_uncertainty_score":0.4198259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01748673113263469,"score_gpt":0.2820495558834093,"score_spread":0.2645628247507746,"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."}}