{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006142573,0.0001207486,0.0001438411,0.00003957187,0.0002504712,0.00003390753,0.001276698,0.0002772976,0.000002458971],"category_scores_gemma":[0.001042478,0.0001065427,0.00001541101,0.0001308462,0.00009325517,0.000009059893,0.0006743619,0.0003523117,0.00000459297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001343011,"about_ca_system_score_gemma":0.00009766617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000195908,"about_ca_topic_score_gemma":0.002877474,"domain_scores_codex":[0.9988915,0.0003073222,0.0001963517,0.0003751974,0.00004829992,0.0001812705],"domain_scores_gemma":[0.9968848,0.0000966504,0.000100398,0.002652925,0.0001893851,0.00007584976],"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":[0.00003001227,0.000110002,0.03651208,0.00001231769,0.00008567348,1.217137e-7,0.0004500786,0.00001554816,0.9208839,0.004134045,0.004228857,0.03353737],"study_design_scores_gemma":[0.0005105366,0.0008136434,0.117636,0.00003656161,0.00009153708,0.0000252909,0.0008490164,0.01080366,0.004054279,0.0005704087,0.8638725,0.0007366223],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9431097,0.01031524,0.01379384,0.0134374,0.000252761,0.00133833,0.0007284839,0.0001397609,0.01688446],"genre_scores_gemma":[0.9087461,0.0009342727,0.08728246,0.0009889365,0.00006641619,0.00003762811,0.001748352,0.00001391504,0.0001819056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9168296,"threshold_uncertainty_score":0.4344687,"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."}}