{"id":"W3159144092","doi":"10.1093/bib/bbab132","title":"KCRR: a nonlinear machine learning with a modified genomic similarity matrix improved the genomic prediction efficiency","year":2021,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Beef Cattle Research Council; National Natural Science Foundation of China","keywords":"Cosine similarity; Best linear unbiased prediction; Similarity (geometry); Support vector machine; Heritability; Kernel (algebra); Computer science; Machine learning; Artificial intelligence; Mathematics; Biology; Pattern recognition (psychology); Genetics; Selection (genetic algorithm); Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001615521,0.0007905648,0.000743862,0.000665604,0.0003395646,0.0007009061,0.0008420894,0.0006908597,0.00136245],"category_scores_gemma":[0.003567959,0.0002409392,0.0008619949,0.0006647263,0.0003979765,0.001089446,0.0008636889,0.001082212,0.0006305243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004609263,"about_ca_system_score_gemma":0.0009732716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006480338,"about_ca_topic_score_gemma":0.004716835,"domain_scores_codex":[0.9986952,0.0004030629,0.0001062056,0.0003878322,0.0003180679,0.00008966924],"domain_scores_gemma":[0.9985372,0.0005138281,0.000143229,0.0001859846,0.0005566355,0.00006325093],"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":[0.0006051735,0.0004465812,0.01420132,0.0003423876,0.0004142099,0.0001918624,0.0001522468,0.2608629,0.0573097,0.006167212,0.005443965,0.6538624],"study_design_scores_gemma":[0.00002355221,0.0001086405,0.002069918,0.000006609635,0.00003717341,0.00006706468,0.00001482977,0.9887097,0.007276233,0.0007560112,0.0009014395,0.00002873398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1257212,0.0005569059,0.8691112,0.0003144149,0.00009867798,0.00008371146,0.0002294073,0.002382166,0.00150242],"genre_scores_gemma":[0.694059,0.0002974482,0.3015633,0.0001871459,0.00005921429,0.0001288379,0.0007900395,0.0002304881,0.002684477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006480338,"threshold_uncertainty_score":0.01288521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007201868497908619,"score_gpt":0.2133350644116704,"score_spread":0.2061331959137617,"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."}}