Prediction of milk fatty acid content with mid-infrared spectroscopy in Canadian dairy cattle using differently distributed model development sets

Abstract

The fatty acid profile of milk is a prevailing issue due to the potential negative or positive effects of different fatty acids to human health and nutrition. Mid-infrared spectroscopy can be used to obtain predictions of otherwise costly fatty acid phenotypes in a widespread and rapid manner. The objective of this study was to evaluate the prediction of fatty acid content for the Canadian dairy cattle population from mid-infrared spectral data and to compare the results produced by altering the partial least squares (PLS) model development set used. The PLS model development sets used to develop the predictions were reference fatty acids expressed as (1) grams per 100 g of fatty acid, (2) grams per 100 g of milk, (3) the natural logarithmic transform of grams per 100 g of milk, and (4) subsets of samples randomly selected by removing excess records around the mean to present a more uniform distribution, repeated 10 times. Gas chromatography measured fatty acid concentration and spectral data for 2,023 milk samples of 373 cows from 4 breeds and 44 herds were used in the model development. The coefficient of determination of cross-validation (R) increased when fatty acids were expressed on a per 100 g of milk basis compared with on a per 100 g of fat basis for all examined fatty acids. The logarithmic transformation used to create a more Gaussian distribution in the development set had little effect on the prediction accuracy. The individual fatty acids C12:0, C14:0, C16:0, C18:0, C18:1n-9 cis, and saturated, monounsaturated, unsaturated, short-chain, medium-chain, and long-chain fatty acid groups had (R) greater than 0.70. When model development was performed with subsets of the original samples, slight increases in (R) values were observed for the majority of fatty acids. The difference in (R) between the top- and bottom-performing prediction equation across the different subsets for a single predicted fatty acid was on average 0.055 depending on which samples were randomly selected to be used in the PLS model development set. Predictions for fatty acids with high accuracies can be used to monitor fatty acid contents for cows in milk recording programs and possibly for genetic evaluation.

Milk Fat Globule in Ruminant: Major and Minor Compounds, Nutritional Regulation and Differences Among Species

“…For these groups of FA, the cross‐validation coefficient of determination ( r 2 ) was greater than 0.95 . Therefore, prediction of groups of FA from MIR spectra has increased interest across different countries using model development sample sets from large dairy cow populations . The MIR method has been extended to milks from ewe and goat species, and the predictions there were better for individual SFA and MUFA with medium and high milk concentrations ( r 2 > 0.95) .…”

Genome-wide association study on Fourier transform infrared milk spectra for two Danish dairy cattle breeds

“…The major milk components fat, protein, and lactose have been successfully predicted with FT-IR milk spectra [3]. In addition, minor milk components have been predicted with FT-IR milk spectra, such as fatty acids [4][5][6], protein fractions [7,8], and ketone bodies [9][10][11]. Concentration of ketone bodies in milk can be used as an indicator for subclinical ketosis [9][10][11], or energy balance [12,13].…”

A landscape of the heritability of Fourier-transform infrared spectral wavelengths of milk samples by parity and lactation stage in Holstein cows

“…Most research and industry applications using milk FTIR data focus on developing prediction equations for economically important phenotypes such as fine milk composition (Rutten et al, 2010(Rutten et al, , 2011Fleming et al, 2017aFleming et al, ,b, 2018 and technological properties of milk (Cecchinato et al, 2009. In addition, FTIR data have been shown to be a potentially valuable tool for predicting health and reproductive phenotypes (Heuer et al, 2001;Belay et al, 2017;Toledo-Alvarado et al, 2018) and for predicting residual feed intake, DMI, and methane emissions (Shetty et al, 2017a,b;Bittante and Cipolat-Gotet, 2018;Dórea et al, 2018).…”