{"id":"W2902380111","doi":"10.1002/ajmg.b.32705","title":"Predictive modeling of schizophrenia from genomic data: Comparison of polygenic risk score with kernel support vector machines approach","year":2018,"lang":"en","type":"article","venue":"American Journal of Medical Genetics Part B Neuropsychiatric Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Medical Research Council; Cardiff University; Medical Research Council Canada; Wellcome Trust","keywords":"Support vector machine; Kernel (algebra); Artificial intelligence; Machine learning; Polygenic risk score; Computer science; Pattern recognition (psychology); Schizophrenia (object-oriented programming); Multivariate statistics; Kernel method; Mathematics; Single-nucleotide polymorphism; Biology; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005058703,0.0005089714,0.000754378,0.001019233,0.0001786913,0.0007083475,0.0006544788,0.0004404417,0.0005300393],"category_scores_gemma":[0.008969494,0.0002117605,0.0006161084,0.0005914284,0.0002857927,0.00062235,0.0005877197,0.0007183165,0.0001411687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005163254,"about_ca_system_score_gemma":0.0007261978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006793946,"about_ca_topic_score_gemma":0.003081629,"domain_scores_codex":[0.9989336,0.0007255017,0.00006371833,0.0001160827,0.00009354731,0.00006742974],"domain_scores_gemma":[0.9939163,0.005182787,0.0002704995,0.0002136548,0.0003102582,0.0001064792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006577471,0.0001433697,0.04337328,0.00007607602,0.0003192101,0.0001305695,0.00008298269,0.8541135,0.0009089106,0.002326037,0.000537665,0.0973307],"study_design_scores_gemma":[0.000005194499,0.00001917212,0.001606368,0.000002977825,0.000008669921,0.000007107965,0.000006702261,0.997384,0.00009707819,0.0008320382,0.00002724554,0.000003443152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6812792,0.001197177,0.3149722,0.0009154983,0.00004962701,0.00006539573,0.0003205372,0.0005335368,0.0006669729],"genre_scores_gemma":[0.979136,0.0002012282,0.02009433,0.0000325347,0.00001947132,0.0000282757,0.0002502456,0.00001499796,0.0002228999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006793946,"threshold_uncertainty_score":0.02675331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02505988164933335,"score_gpt":0.2956362895800985,"score_spread":0.2705764079307651,"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."}}