{"id":"W4311679150","doi":"10.1038/s41437-022-00582-6","title":"Weighted kernels improve multi-environment genomic prediction","year":2022,"lang":"en","type":"article","venue":"Heredity","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Oklahoma State University; Oklahoma Center for the Advancement of Science and Technology; U.S. Department of Agriculture; National Science Foundation","keywords":"Biology; Genome-wide association study; Leverage (statistics); Computational biology; Predictability; Phenome; Bayesian probability; Genome; Population; Genetics; Genotype; Computer science; Machine learning; Gene; Artificial intelligence; Statistics; Single-nucleotide polymorphism; Mathematics","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":[0.0001147784,0.0001143464,0.00008635492,0.00001453289,0.0001885258,0.000007280248,0.0001732527,0.00006701789,0.0005279852],"category_scores_gemma":[0.000004360946,0.0001220653,0.00006068086,0.00002619935,0.00005103814,0.000001480629,0.0002549193,0.0001351699,0.00002948365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004061775,"about_ca_system_score_gemma":0.00004229548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001616647,"about_ca_topic_score_gemma":0.000002614386,"domain_scores_codex":[0.9991255,0.00007205587,0.0001469204,0.0003346552,0.0001363722,0.0001844498],"domain_scores_gemma":[0.9995462,0.000004217101,0.00005673353,0.0003128808,0.00001027767,0.00006968633],"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":[0.0002384744,0.0008158183,0.01797911,0.00002637551,0.0001766375,0.000002648962,0.0004236141,0.006764823,0.9445428,0.0004464268,0.01853266,0.01005058],"study_design_scores_gemma":[0.002152539,0.001595671,0.5588523,0.000002396258,0.000060511,0.00003688395,0.0003813804,0.0008646352,0.04294335,0.001027041,0.3916055,0.0004777975],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870871,0.0005145647,0.009989319,0.00004350832,0.0009665775,0.0002588981,0.0002953286,0.00002241818,0.0008222953],"genre_scores_gemma":[0.986863,0.00002231795,0.009448598,0.0001212101,0.0005266809,0.0001009272,0.0002222743,0.00001737767,0.002677686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9015995,"threshold_uncertainty_score":0.5781067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01107085988556966,"score_gpt":0.2099484123272675,"score_spread":0.1988775524416979,"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."}}