Skip to main content
Fig. 3 | Genetics Selection Evolution

Fig. 3

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. 3

Wavelength regions variable importance (VI) greater than 0.8% for the GBM approach using Model 4 (M4) that includes milk FTIR data, on-farm (DIM and parity), and genomic information for blood metabolites. a Overlap of FTIR wavelength considered as significant (VI > 0.8%) indicating specific and shared regions, b total of FTIR wavelengths with a relative VI greater than 0.8% of the phenotypic variability and c heatmap for relative VI scores for each FTIR wavelength absorbance considered as significant (VI > 0.8%)

Back to article page

Genetics Selection Evolution

ISSN: 1297-9686