{"id":"W2095859808","doi":"10.1038/ncomms4934","title":"Integrating sequence and array data to create an improved 1000 Genomes Project haplotype reference panel","year":2014,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":457,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; McGill University; McGill University and Génome Québec Innovation Centre","funders":"National Institute on Minority Health and Health Disparities; National Institute of Environmental Health Sciences; National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; National Cancer Institute; Medical Research Council; Wellcome Trust","keywords":"Haplotype; Imputation (statistics); 1000 Genomes Project; Single-nucleotide polymorphism; Indel; Genetics; Genome-wide association study; Haplotype estimation; SNP; Biology; Genome; Reference genome; Genotype; Whole genome sequencing; Computational biology; Tag SNP; Genomics; Computer science; Gene; Missing data","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007297819,0.0009964791,0.002041019,0.008056666,0.0006157832,0.001687613,0.00144906,0.001137058,0.01189003],"category_scores_gemma":[0.02136326,0.001271646,0.001650926,0.008828129,0.0001575798,0.0009705709,0.001670467,0.001899307,0.006858453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005334812,"about_ca_system_score_gemma":0.001917526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01701434,"about_ca_topic_score_gemma":0.04114207,"domain_scores_codex":[0.9955354,0.001202963,0.0005391272,0.001354809,0.001112996,0.0002547202],"domain_scores_gemma":[0.99019,0.002839949,0.0006233205,0.002369137,0.003698936,0.0002786729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001417649,0.0004666818,0.1379054,0.001567084,0.003622008,0.001487785,0.001181487,0.03460569,0.2042984,0.00543803,0.08951832,0.5184914],"study_design_scores_gemma":[0.001269887,0.0005164263,0.4617283,0.0005990678,0.005413311,0.002832054,0.0003951678,0.09275763,0.05785042,0.02024208,0.3557662,0.0006294543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1059825,0.00175669,0.6411264,0.001265868,0.0007459421,0.0009808062,0.2336722,0.007006001,0.007463616],"genre_scores_gemma":[0.09917931,0.0006849427,0.6947905,0.0008189189,0.0002524738,0.0009675272,0.1978063,0.001183786,0.004316155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01701434,"threshold_uncertainty_score":0.03977609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1198381854349152,"score_gpt":0.376645356256871,"score_spread":0.2568071708219558,"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."}}