Integrating genomic and infrared spectral data improves the prediction of milk protein composition in dairy cattle

Table 3 Regression coefficients of predictive values for testing cows on observed phenotypes when fitting multiple kernel learning, multilayer BayesB, and partial least squares (PLS) using repeated random sub-sampling cross-validation

Traits	Kernel							BayesB				PLS
Traits	M1	M2	M3	M4	M5	M6	M7	M1	M2	M3	M4	M1	M2	M3	M4	M7
True protein nitrogen	1.04	0.92	0.91	0.94	0.90	0.93	0.94	0.96	0.92	0.91	0.93	0.87	0.89	0.87	0.92	0.88
Total casein	1.02	1.01	1.01	1.01	1.01	1.00	1.01	0.98	0.97	0.96	0.99	0.98	0.98	0.97	0.97	0.98
Total whey protein	1.01	0.83	0.81	0.87	0.81	0.86	0.86	0.96	0.85	0.82	0.90	0.82	0.77	0.74	0.72	0.75
\(\kappa \text {-}\)casein	1.02	0.76	0.74	0.84	0.85	0.85	0.79	0.92	0.84	0.82	0.92	0.76	0.71	0.71	0.75	0.73
\(\beta \text {-}\)casein	1.12	0.78	0.78	0.92	0.93	0.94	0.86	0.97	0.84	0.82	0.96	0.83	0.83	0.86	0.85	0.84
\(\alpha _{S1}\text {-}\)casein	1.05	0.86	0.86	0.88	0.87	0.88	0.86	1.02	0.87	0.86	0.92	0.84	0.86	0.90	0.82	0.80
\(\alpha _{S2}\text {-}\)casein	1.02	0.84	0.83	0.83	0.80	0.79	0.83	0.99	0.84	0.83	0.85	0.79	0.78	0.78	0.66	0.64
\(\beta \text {-}\)lactoglobulin	0.99	0.84	0.83	0.88	0.83	0.88	0.87	0.99	0.85	0.85	0.90	0.76	0.75	0.78	0.77	0.73
\(\alpha \text {-}\)lactalbumin	1.06	0.92	0.92	0.92	0.89	0.88	0.92	1.02	0.92	0.92	0.92	0.94	0.91	0.91	0.93	0.91

M1: milk Fourier transform infrared spectroscopy (FTIR)
M2: herd + FTIR
M3: herd + days in milk + parity + FTIR
M4: herd + days in milk + parity + FTIR + Genomics
M5: herd + days in milk + parity + FTIR + top three markers with the largest effects
M6: herd + days in milk + parity + FTIR + Genomics + top three markers with the largest effects
M7: herd + days in milk + parity + FTIR + pedigree

ISSN: 1297-9686