{"id":"W2989440251","doi":"10.1093/bib/bbz108","title":"Genotype imputation and reference panel: a systematic evaluation on haplotype size and diversity","year":2019,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Imputation (statistics); Minor allele frequency; Population; Sample size determination; Haplotype; Statistics; 1000 Genomes Project; Genetics; Allele frequency; Biology; Missing data; Allele; Genotype; Mathematics; Single-nucleotide polymorphism; Medicine; Environmental health","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":[0.0007272171,0.00009587013,0.0001718473,0.00003942757,0.00007516523,0.00001947599,0.00006206551,0.0001374163,0.000006427145],"category_scores_gemma":[0.0006873407,0.00008766915,0.00001597251,0.00005733955,0.00003024538,0.000008420781,0.0001537009,0.00006373219,0.00001719621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002587673,"about_ca_system_score_gemma":0.00003099955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007218686,"about_ca_topic_score_gemma":0.0000276128,"domain_scores_codex":[0.9992498,0.00007526272,0.0002688496,0.0001421796,0.0001270027,0.0001368996],"domain_scores_gemma":[0.9994667,0.0001005997,0.0001713217,0.0001481551,0.00007889064,0.00003431709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005612447,0.0003034488,0.9008179,0.0165237,0.0004741405,0.000003425049,0.01387693,0.006556861,0.01880312,0.005206667,0.003111855,0.03376075],"study_design_scores_gemma":[0.00155552,0.0005697916,0.9348887,0.0003992014,0.00007657382,0.0000216384,0.0007547213,0.05947747,0.0001709378,0.001483725,0.0002649381,0.0003367816],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979414,0.0001843196,0.0003153161,0.0001521856,0.00004425956,0.0004486236,0.00000561774,0.000006902366,0.0009013934],"genre_scores_gemma":[0.9960334,0.000176924,0.002906531,0.0007351033,0.00001038351,0.00001046844,0.00003700814,0.000005589353,0.00008463577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05292061,"threshold_uncertainty_score":0.3575044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02665397938933341,"score_gpt":0.2602573282323055,"score_spread":0.2336033488429721,"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."}}