Skip to main content
Fig. 1 | Genetics Selection Evolution

Fig. 1

From: Integrating on-farm and genomic information improves the predictive ability of milk infrared prediction of blood indicators of metabolic disorders in dairy cows

Fig. 1

Average of the relative difference (%) in predictive ability across tenfold random, batch-out and herd-out cross-validation scenarios for Model 2 (milk FTIR data and on-farm data), Model 3 (milk FTIR data and genomic information) and Model 4 (milk FTIR data, on-farm data, and genomic information) for BayesB (a, c, e) and gradient boosting machine (GBM) (b, d, f) against the Model 1 considering only the FTIR data. Data are shown as mean ± SD (dark red error bar line) [for more details, see Additional file 1: Table S2 to S4]. GLU: Glucose; BHBA: β-hydroxybutyric acid; AST: aspartate aminotransferase; GGT: γ-glutamyl transferase; PON: paraoxonase; ROMt: total reactive oxygen metabolites; AOPP: advanced oxidation protein products; FRAP: ferric reducing antioxidant power; CuCp: Ceruloplasmin; PROTt: total proteins; GLOB: Globulin; Ca: Calcium; k: Potassium; Zn: Zinc

Back to article page

Genetics Selection Evolution

ISSN: 1297-9686