{"id":"W4391325391","doi":"10.1002/cpz1.972","title":"Recovering Misidentified Samples Through Genetic Discordance Clustering","year":2024,"lang":"en","type":"article","venue":"Current Protocols","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Multiple Sclerosis Society; Multiple Sclerosis Society of Canada; European Genomic Institute for Diabetes","keywords":"Genotyping; Sample (material); Protocol (science); Computer science; Quality assurance; Guideline; Data science; Medicine; Biology; Pathology; Genetics; Genotype; External quality assessment; Alternative medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044148,0.0001695124,0.0001691998,0.00002915075,0.00009465309,0.0001007573,0.0002087898,0.00009249597,0.00005422276],"category_scores_gemma":[0.0001350399,0.0001574138,0.0001233888,0.000100837,0.00004776046,0.000008050724,0.0001707511,0.000121604,0.00005687922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002880725,"about_ca_system_score_gemma":0.00007906996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001542203,"about_ca_topic_score_gemma":0.00003217105,"domain_scores_codex":[0.9986877,0.00008194293,0.0003297464,0.000486953,0.00009657636,0.0003171078],"domain_scores_gemma":[0.999464,0.00002785295,0.0000708368,0.0003475948,0.00003771581,0.00005201067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001601961,0.0003134255,0.07867276,0.002331502,0.0003973312,0.00001935341,0.0006779022,0.005115152,0.4911452,0.001159691,0.07569814,0.3443094],"study_design_scores_gemma":[0.0004459958,0.0001763657,0.03993802,0.0005534745,0.00002889897,0.00002835618,0.00004809889,0.002073249,0.01250367,0.003225373,0.940473,0.0005055001],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.422377,0.00844698,0.5293873,0.0005367674,0.002339537,0.03526511,0.0001053749,0.0001695393,0.0013724],"genre_scores_gemma":[0.8907208,0.0006132121,0.02266387,0.0001537408,0.002028802,0.08165345,0.0002492338,0.0001023928,0.001814526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8647749,"threshold_uncertainty_score":0.6419148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07448014551770323,"score_gpt":0.3835014261622324,"score_spread":0.3090212806445292,"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."}}