{"id":"W4386019111","doi":"10.1111/1755-0998.13854","title":"Best practices for genotype imputation from low‐coverage sequencing data in natural populations","year":2023,"lang":"en","type":"article","venue":"Molecular Ecology Resources","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Institute of Mental Health; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Imputation (statistics); Biology; Genotyping; Genotype; Inference; Whole genome sequencing; Computational biology; Genetics; Statistics; Genome; Missing data; Evolutionary biology; Computer science; Gene; Artificial intelligence","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":[0.0002421107,0.0001513077,0.0001551981,0.0000920234,0.0001157577,0.0000349083,0.0004290129,0.0002067853,0.00001258677],"category_scores_gemma":[0.0006603224,0.0001602836,0.00004783546,0.0001736284,0.00006169613,0.00001128243,0.0002674377,0.0001231749,0.00002732071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002183501,"about_ca_system_score_gemma":0.00009355141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002900749,"about_ca_topic_score_gemma":0.001721609,"domain_scores_codex":[0.9986586,0.0001226281,0.0002498775,0.000562477,0.0001022011,0.0003042091],"domain_scores_gemma":[0.9990615,0.00009470103,0.0002037838,0.0005408979,0.00005125593,0.00004786523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000560345,0.0002569798,0.08918674,0.0001218632,0.0004083601,0.00005374358,0.001651444,0.07851099,0.8051767,0.002471541,0.002755293,0.01884599],"study_design_scores_gemma":[0.003737462,0.001205018,0.8747193,0.00007097553,0.0002858797,0.00003487007,0.001501276,0.0152246,0.02655029,0.02727414,0.04813153,0.001264666],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992399,0.0008453564,0.005247907,0.0003210158,0.0003557198,0.0003795673,0.0001618352,0.0000271883,0.0002624576],"genre_scores_gemma":[0.9805238,0.00002275886,0.01494275,0.0003061009,0.0002061232,0.00005582214,0.003384117,0.00003009054,0.0005284846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7855325,"threshold_uncertainty_score":0.6536177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04382550939880728,"score_gpt":0.3201149087259336,"score_spread":0.2762893993271263,"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."}}