[en] Lactoferrin (LF) is a glycoprotein naturally present in milk. Its content varies throughout lactation, but also with mastitis; therefore it is a potential additional indicator of udder health beyond somatic cell count. Condequently, there is an interest in quantifying this biomolecule routinely. First prediction equations proposed in the literature to predict the content in milk using milk mid-infrared spectrometry were built using partial least square regression (PLSR) due to the limited size of the data set. Thanks to a large data set, the current study aimed to test 4 different machine learning algorithms using a large data set comprising 6,619 records collected across different herds, breeds, and countries. The first algorithm was a PLSR, as used in past investigations. The second and third algorithms used partial least square (PLS) factors combined with a linear and polynomial support vector regression (PLS + SVR). The fourth algorithm also used PLS factors, but included in an artificial neural network with 1 hidden layer (PLS + ANN). The training and validation sets comprised 5,541 and 836 records, respectively. Even if the calibration prediction performances were the best for PLS + polynomial SVR, their validation prediction performances were the worst. The 3 other algorithms had similar validation performances. Indeed, the validation root mean squared error (RMSE) ranged between 162.17 and 166.75 mg/L of milk. However, the lower standard deviation of cross-validation RMSE and the better normality of the residual distribution observed for PLS + ANN suggest that this modeling was more suitable to predict the LF content in milk from milk mid-infrared spectra (R2v = 0.60 and validation RMSE = 162.17 mg/L of milk). This PLS +ANN model was then applied to almost 6 million spectral records. The predicted LF showed the expected relationships with milk yield, somatic cell score, somatic cell count, and stage of lactation. The model tended to underestimate high LF values (higher than 600 mg/L of milk). However, if the prediction threshold was set to 500 mg/L, 82% of samples from the validation having a content of LF higher than 600 mg/L were detected. Future research should aim to increase the number of those extremely high LF records in the calibration set.
Disciplines :
Animal production & animal husbandry Food science
Author, co-author :
Soyeurt, Hélène ; Université de Liège - ULiège > Département GxABT > Modélisation et développement
Beck, M.W., NeuralNetTools: Visualization and analysis tools for neural networks. J. Stat. Softw. 85 (2018), 1–20 https://doi.org/10.18637/jss.v085.i11 30505247.
Chaneton, L., Bontá, M., Pol, M., Tirante, L., Bussmann, L.E., Milk lactoferrin in heifers: Influence of health status and stage of lactation. J. Dairy Sci. 96 (2013), 4977–4982 https://doi.org/10.3168/jds.2012-6028 23769364.
Chaneton, L., Tirante, L., Maito, J., Chaves, J., Bussmann, L.E., Relationship between milk lactoferrin and etiological agent in the mastitic bovine mammary gland. J. Dairy Sci. 91 (2008), 1865–1873 https://doi.org/10.3168/jds.2007-0732 18420617.
Chen, P.W., Mao, F.C., Detection of lactoferrin in bovine and goat milk by enzyme-linked immunosorbent assay. Yao Wu Shi Pin Fen Xi 12 (2004), 133–139.
Cheng, J.B., Wang, J.Q., Bu, D.P., Liu, G.L., Zhang, C.G., Wei, H.Y., Zhou, L.Y., Wang, J.Z., Factors Affecting the Lactoferrin Concentration in Bovine Milk. J. Dairy Sci. 91 (2008), 970–976 https://doi.org/10.3168/jds.2007-0689 18292252.
De Marchi, M., Fagan, C.C., O'Donnell, C.P., Cecchinato, A., Dal Zotto, R., Cassandro, M., Penasa, M., Bittante, G., Prediction of coagulation properties, titratable acidity, and pH of bovine milk using mid-infrared spectroscopy. J. Dairy Sci. 92 (2009), 423–432 https://doi.org/10.3168/jds.2008-1163 19109300.
Delhez, P., Ho, P.N., Gengler, N., Soyeurt, H., Pryce, J.E., Diagnosing the pregnancy status of dairy cows: How useful is milk mid-infrared spectroscopy?. J. Dairy Sci. 103 (2020), 3264–3274 https://doi.org/10.3168/jds.2019-17473 32037165.
Despagne, F., Luc Massart, D., Chabot, P., Development of a robust calibration model for nonlinear in-line process data. Anal. Chem. 72 (2000), 1657–1665 https://doi.org/10.1021/ac991076k 10763266.
Dórea, J.R.R., Rosa, G.J.M., Weld, K.A., Armentano, L.E., Mining data from milk infrared spectroscopy to improve feed intake predictions in lactating dairy cows. J. Dairy Sci. 101 (2018), 5878–5889 https://doi.org/10.3168/jds.2017-13997 29680644.
Finn, G.D., Lister, R., Szabo, T., Simonetta, D., Mulder, H., Young, R., Neural networks applied to a large biological database to analyse dairy breeding patterns. Neural Comput. Appl. 4 (1996), 237–253 https://doi.org/10.1007/BF01413822.
Gaunt, S.N., Raffio, N., Kingsbury, E.T., Damon, R.A. Jr., Johnson, W.H., Mitchell, B.A., Variation of lactoferrin and mastitis and their heritabilities. J. Dairy Sci. 63 (1980), 1874–1880 https://doi.org/10.3168/jds.S0022-0302(80)83154-7 7192293.
Grelet, C., Bastin, C., Gelé, M., Davière, J.B., Johan, M., Werner, A., Reding, R., Fernandez Pierna, J.A., Colinet, F.G., Dardenne, P., Gengler, N., Soyeurt, H., Dehareng, F., Development of Fourier transform mid-infrared calibrations to predict acetone, β-hydroxybutyrate, and citrate contents in bovine milk through a European dairy network. J. Dairy Sci. 99 (2016), 4816–4825 https://doi.org/10.3168/jds.2015-10477 27016835.
Grelet, C., Pierna, J.A.F., Dardenne, P., Soyeurt, H., Vanlierde, A., Colinet, F., Bastin, C., Gengler, N., Baeten, V., Dehareng, F., Standardization of milk mid-infrared spectrometers for the transfer and use of multiple models. J. Dairy Sci. 100 (2017), 7910–7921 https://doi.org/10.3168/jds.2017-12720 28755945.
Grzesiak, W., Blaszczyk, P., Lacroix, R., Methods of predicting milk yield in dairy cows—Predictive capabilities of Wood's lactation curve and artificial neural networks (ANNs). Comput. Electron. Agric. 54 (2006), 69–83 https://doi.org/10.1016/j.compag.2006.08.004.
Hagiwara, S-I., Kawai, K., Anri, A., Nagahata, H., Lactoferrin concentrations in milk from normal and subclinical mastitic cows. J. Vet. Med. Sci. 65 (2003), 319–323 https://doi.org/10.1292/jvms.65.319 12679560.
Hempstalk, K., McParland, S., Berry, D.P., Machine learning algorithms for the prediction of conception success to a given insemination in lactating dairy cows. J. Dairy Sci. 98 (2015), 5262–5273 https://doi.org/10.3168/jds.2014-8984 26074247.
Kawai, K., Hagiwara, S., Anri, A., Nagahata, H., Lactoferrin concentration in milk of bovine clinical mastitis. Vet. Res. Commun. 23 (1999), 391–398 https://doi.org/10.1023/A:1006347423426 10598071.
Król, J., Litwińczuk, Z., Brodziak, A., Barłowska, J., Lactoferrin, lysozyme and immunoglobulin G content in milk of four breeds of cows managed under intensive production system. Pol. J. Vet. Sci. 13 (2010), 357–361 20731193.
Kuhn, M., caret Package. J. Stat. Softw. 28 (2008), 1–26.
Lê, S., Josse, J., Husson, F., FactoMineR: An R package for multivariate analysis. J. Stat. Softw. 25 (2008), 1–18 https://doi.org/10.18637/jss.v025.i01.
McCulloch, W.S., Pitts, W., A logical calculus of the ideas imminent in nervous activity. Bull. Math. Biophys. 5 (1943), 115–133 https://doi.org/10.1007/BF02478259.
Molenaar, A.J., Kuys, Y.M., Davis, S.R., Wilkins, R.J., Mead, P.E., Tweedie, J.W., Elevation of lactoferrin gene expression in developing, ductal, resting regressing parenchymal epithelium of the ruminant mammary gland. J. Dairy Sci. 79 (1996), 1198–1208 https://doi.org/10.3168/jds.S0022-0302(96)76473-1 8872714.
Pralle, R.S., Weigel, K.W., White, H.M., Predicting blood β-hydroxybutyrate using milk Fourier transform infrared spectrum, milk composition, and producer-reported variables with multiple linear regression, partial least squares regression, and artificial neural network. J. Dairy Sci. 101 (2018), 4378–4387 https://doi.org/10.3168/jds.2017-14076 29477523.
Prekopcsak, Z., Henk, T., Gaspar-Papanek, C., Cross-validation: The illusion of reliable performance estimation. RCOMM RapidMiner Community Meeting and Conference, 2010, 1N6 http://prekopcsak.hu/papers/preko-2010-rcomm.pdf.
Soyeurt, H., Bastin, C., Colinet, F.G., Arnould, V.M.R., Berry, D.P., Wall, E., Dehareng, F., Nguyen, H.N., Dardenne, P., Schefers, J., Vandenplas, J., Weigel, K., Coffey, M., Thé Ron, L., Detilleux, J., Reding, E., Gengler, N., McParland, S., Mid-infrared prediction of lactoferrin content in bovine milk: Potential indicator of mastitis. Animal 6 (2012), 1830–1838 https://doi.org/10.1017/S1751731112000791 22717388.
Soyeurt, H., Colinet, F.G., Arnould, V.M.R., Dardenne, P., Bertozzi, C., Renaville, R., Portetelle, D., Gengler, N., Genetic variability of lactoferrin content estimated by mid-infrared spectrometry in bovine milk. J. Dairy Sci. 90 (2007), 4443–4450 https://doi.org/10.3168/jds.2006-827 17699065.
Soyeurt, H., Dehareng, F., Gengler, N., McParland, S., Wall, E., Berry, D.P., Coffey, M., Dardenne, P., Mid-infrared prediction of bovine milk fatty acids across multiple breeds, production systems, and countries. J. Dairy Sci. 94 (2011), 1657–1667 https://doi.org/10.3168/jds.2010-3408 21426953.
Soyeurt, H., Froidmont, E., Dufrasne, I., Hailemariam, D., Wang, Z., Bertozzi, C., Colinet, F.G., Dehareng, F., Gengler, N., Contribution of milk mid-infrared spectrum to improve the accuracy of test-day body weight predicted from stage, lactation number, month of test and milk yield. Livest. Sci. 227 (2019), 82–89 https://doi.org/10.1016/j.livsci.2019.07.007.
Thissen, U., Pepers, M., Üstün, B., Melssen, W.J., Buydens, L.M.C., Comparing support vector machines to PLS for spectral regression applications. Chemom. Intell. Lab. Syst. 73 (2004), 169–179 https://doi.org/10.1016/j.chemolab.2004.01.002.
Vanlierde, A., Vanrobays, M.L., Gengler, N., Dardenne, P., Froidmont, E., Soyeurt, H., McParland, S., Lewis, E., Deighton, M.H., Mathot, M., Dehareng, F., Milk mid-infrared spectra enable prediction of lactation-stage-dependent methane emissions of dairy cattle within routine population-scale milk recording schemes. Anim. Prod. Sci. 56 (2016), 258–264 https://doi.org/10.1071/AN15590.
Wakabayashi, H., Yamauchi, K., Takase, M., Lactoferrin research, technology and applications. Int. Dairy J. 16 (2006), 1241–1251 https://doi.org/10.1016/j.idairyj.2006.06.013.
Wang, Q., Bovenhuis, H., Validation strategy can result in an overoptimistic view of the ability of milk infrared spectra to predict methane emission of dairy cattle. J. Dairy Sci. 102 (2019), 6288–6295 https://doi.org/10.3168/jds.2018-15684 31056328.
Yang, X.Z., Lacroix, R., Wade, K.M., Investigation into the production and conformation traits associated with clinical mastitis using artificial neural networks. Can. J. Anim. Sci. 80 (2000), 415–426 https://doi.org/10.4141/A98-100.