Selection of the most informative wavenumbers to improve prediction accuracy of milk fatty acid profile based on milk mid-infrared spectra data

Abstract

Milk mid-infrared (MIR) spectra have been shown to provide valuable information on a wide range of traits to be used in dairy cattle breeding programs. Selecting the most informative variables from complex data can improve the prediction accuracy and model robustness and, consequently, the interpretability of MIR spectra. Thus, we aimed to investigate the prediction performance of feature selection methods based on MIR spectra data, using the milk fatty acid (FA) profile as an example to illustrate the evaluated procedure. Data of MIR spectra, milk test-day records, and reference FA concentrations of 155 first-parity Holstein cows were used in the analyses. Four models comprising different explanatory variables and three feature selection methods were evaluated. The results indicated that competitive adaptive reweighted sampling (CARS) method can effectively select the most informative variables from the MIR spectra, resulting in higher prediction accuracies than other variable selection approaches. The model including selected MIR spectra and cow information variables yielded the best FA profile predictions based on partial least square regression. C8:0, C10:0, C14:1, C17:0 isomers, C18:1, C18:1 isomer, medium-chain FA, unsaturation FA, monounsaturated FA, and polyunsaturated FA presented accuracies based on the determination coefficient ranging from 0.66 to 0.85 in internal validation and from 0.65 to 0.84 in external validation. The most related wavenumbers to 35 FAs were found within 1003 to 1145 cm⁻¹. Generally, using CARS and cow information improved predictions of FAs based on MIR spectra in Chinese Holstein dairy cows. Additional validation studies should be conducted as larger datasets become available.

Keywords

fatty acids concentration / feature selection / milk mid-infrared spectra / phenotypic prediction

References

[1] Lynch, J., Barbano, D., Schweisthal, M., & Fleming, J. (2006). Precalibration evaluation procedures for mid-infrared milk analyzers. Journal of Dairy Science, 89(7), 2761–2774.

[2] De Marchi, M., Toffanin, V., Cassandro, M., & Penasa, M. (2014). Invited review: Mid-infrared spectroscopy as phenotyping tool for milk traits. Journal of Dairy Science, 97(3), 1171–1186.

[3] De Marchi, M., Penasa, M., Zidi, A., & Manuelian, C. (2018). Invited review: Use of infrared technologies for the assessment of dairy products—Applications and perspectives. Journal of Dairy Science, 101(12), 10589–10604.

[4] Tiplady, K. M., Lopdell, T. J., Littlejohn, M. D., & Garrick, D. J. (2020). The evolving role of Fourier-transform mid-infrared spectroscopy in genetic improvement of dairy cattle. Journal of Animal Science and Biotechnology, 11(1), 1–13.

[5] Toffanin, V., De Marchi, M., Lopez-Villalobos, N., & Cassandro, M. (2015). Effectiveness of mid-infrared spectroscopy for prediction of the contents of calcium and phosphorus, and titratable acidity of milk and their relationship with milk quality and coagulation properties. International Dairy Journal, 41, 68–73.

[6] Vanrobays, M., Bastin, C., Vandenplas, J., Hammami, H., Soyeurt, H., Vanlierde, A., Dehareng, F., Froidmont, E., & Gengler, N. (2016). Changes throughout lactation in phenotypic and genetic correlations between methane emissions and milk fatty acid contents predicted from milk mid-infrared spectra. Journal of Dairy Science, 99(9), 7247–7260.

[7] Grelet, C., Bastin, C., Gelé M., Davière, J., Johan, M., Werner, A., Reding, R., Fernandez Pierna, J., Colinet, F., Dardenne, P., Gengler, N., Soyeurt, H., & Dehareng, F. (2016). Development of Fourier transform mid-infrared calibrations to predict acetone, β-hydroxybutyrate, and citrate contents in bovine milk through a European dairy network. Journal of Dairy Science, 99(6), 4816–4825.

[8] Fleming, A., Schenkel, F., Chen, J., Malchiodi, F., Ali, R., Mallard, B., Sargolzaei, M., Corredig, M., & Miglior, F. (2017). Variation in fat globule size in bovine milk and its prediction using mid-infrared spectroscopy. Journal of Dairy Science, 100(3), 1640–1649.

[9] Soyeurt, H., Dardenne, P., Dehareng, F., Lognay, G., Veselko, D., Marlier, M., Bertozzi, C., Mayeres, P., & Gengler, N. (2006). Estimating fatty acid content in cow milk using mid-infrared spectrometry. Journal of Dairy Science, 89(9), 3690–3695.

[10] Fleming, A., Schenkel, F., Chen, J., Malchiodi, F., Bonfatti, V., Ali, R., Mallard, B., Corredig, M., & Miglior, F. (2017). Prediction of milk fatty acid content with mid-infrared spectroscopy in Canadian dairy cattle using differently distributed model development sets. Journal of Dairy Science, 100(6), 5073–5081.

[11] Pralle, R., Weigel, K., & White, H. (2018). 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. Journal of Dairy Science, 101(5), 4378–4387.

[12] Wallén, S., Prestløkken, E., Meuwissen, T., McParland, S., & Berry, D. (2018). Milk mid-infrared spectral data as a tool to predict feed intake in lactating Norwegian Red dairy cows. Journal of Dairy Science, 101(7), 6232–6243.

[13] Bonfatti, V., Ho, P. N., & Pryce, J. E. (2020). Usefulness of milk mid-infrared spectroscopy for predicting lameness score in dairy cows. Journal of Dairy Science, 103(3), 2534–2544.

[14] Grelet, C., Froidmont, E., Foldager, L., Salavati, M., Hostens, M., Ferris, C., Ingvartsen, K., Crowe, M., Sorensen, M., Fernandez Pierna, J., Vanlierde, A., Gengler, N., & Dehareng, F. (2020). Potential of milk mid-infrared spectra to predict nitrogen use efficiency of individual dairy cows in early lactation. Journal of Dairy Science, 103(5), 4435–4445.

[15] Shi, R., Lou, W., Ducro, B., van der Linden, A., Mulder, H. A., Oosting, S. J., Li, S., & Wang, Y. (2023). Predicting nitrogen use efficiency, nitrogen loss and dry matter intake of individual dairy cows in late lactation by including mid-infrared spectra of milk samples. Journal of Animal Science and Biotechnology, 14(1), 8.

[16] Brand, W., Wells, A., Smith, S., Denholm, S., Wall, E., & Coffey, M. (2021). Predicting pregnancy status from mid-infrared spectroscopy in dairy cow milk using deep learning. Journal of Dairy Science, 104(4), 4980–4990.

[17] Frizzarin, M., Gormley, I. C., Berry, D. P., & McParland, S. (2023). Estimation of body condition score change in dairy cows in a seasonal calving pasture-based system using routinely available milk mid-infrared spectra and machine learning techniques. Journal of Dairy Science, 106(6), 4232–4244.

[18] Frizzarin, M., Visentin, G., Ferragina, A., Hayes, E., Bevilacqua, A., Dhariyal, B., Domijan, K., Khan, H., Ifrim, G., Nguyen, T. L., Meagher, J., Menchetti, L., Singh, A., Whoriskey, S., Williamson, R., Zappaterra, M., & Casa, A. (2023). Classification of cow diet based on milk mid infrared spectra: A data analysis competition at the “international workshop on spectroscopy and chemometrics 2022”. Chemometrics and Intelligent Laboratory Systems, 234, 104755.

[19] Grelet, C., Pierna, J. A. F., Dardenne, P., Soyeurt, H., Vanlierde, A., Colinet, F., Bastin, C., Gengler, N., Baeten, V., & Dehareng, F. (2017). Standardization of milk mid-infrared spectrometers for the transfer and use of multiple models. Journal of Dairy Science, 100(10), 7910–7921.

[20] Grelet, C., Dardenne, P., Soyeurt, H., Fernandez, J., Vanlierde, A., Stevens, F., Gengler, N., & Dehareng, F. (2021). Large-scale phenotyping in dairy sector using milk MIR spectra: Key factors affecting the quality of predictions. Methods, 186, 97–111.

[21] Li-Chan, E., Chalmers, J. M., & Griffiths, P. R. (2010). Applications of vibrational spectroscopy in food science. John Wiley & Sons.

[22] Gottardo, P., De Marchi, M., Cassandro, M., & Penasa, M. (2015). Technical note: Improving the accuracy of mid-infrared prediction models by selecting the most informative wavelengths. Journal of Dairy Science, 98(6), 4168–4173.

[23] Niero, G., Penasa, M., Gottardo, P., Cassandro, M., & De Marchi, M. (2016). Short communication: Selecting the most informative mid-infrared spectra wavenumbers to improve the accuracy of prediction models for detailed milk protein content. Journal of Dairy Science, 99(3), 1853–1858.

[24] Xiao, S., Wang, Q., Li, C., Liu, W., Zhang, J., Fan, Y., Su, J., Wang, H., Luo, X., & Zhang, S. (2022). Rapid identification of A1 and A2 milk based on the combination of mid-infrared spectroscopy and chemometrics. Food Control, 134, 108659.

[25] Zhang, L., Tedde, A., Ho, P., Grelet, C., Dehareng, F., Froidmont, E., Gengler, N., Brostaux, Y., Hailemariam, D., Pryce, J., & Soyeurt, H. (2021). Mining data from milk mid-infrared spectroscopy and animal characteristics to improve the prediction of dairy cow’s liveweight using feature selection algorithms based on partial least squares and Elastic Net regressions. Computers and Electronics in Agriculture, 184, 106106.

[26] Li, H., Liang, Y., Xu, Q., & Cao, D. (2009). Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Analytica Chimica Acta, 648(1), 77–84.

[27] Ji, H., Wang, W., Chong, D., & Zhang, B. (2019). CARS algorithm-based detection of wheat moisture content before harvest. Symmetry, 12(1), 115.

[28] Huppertz, T., & Kelly, A. L. (2008). Properties and constituents of cow’s milk (pp. 23–47).

[29] Stewart, J. E., Feinle-Bisset, C., & Keast, R. S. (2011). Fatty acid detection during food consumption and digestion: Associations with ingestive behavior and obesity. Progress in Lipid Research, 50(3), 225–233.

[30] Ruiz-Núñez, B., Dijck-Brouwer, D. J., & Muskiet, F. A. (2016). The relation of saturated fatty acids with low-grade inflammation and cardiovascular disease. The Journal of Nutritional Biochemistry, 36, 1–20.

[31] Dehghan, M., Mente, A., Rangarajan, S., Sheridan, P., Mohan, V., Iqbal, R., Gupta, R., Lear, S., Wentzel-Viljoen, E., Avezum, A., Lopez-Jaramillo, P., Mony, P., Varma, R. P., Kumar, R., Chifamba, J., Alhabib, K. F., Mohammadifard, N., Oguz, A., Lanas, F., …, & Yusuf, S. (2018). Association of dairy intake with cardiovascular disease and mortality in 21 countries from five continents (pure): A prospective cohort study. The Lancet, 392(10161), 2288–2297.

[32] De Marchi, M., Penasa, M., Cecchinato, A., Mele, M., Secchiari, P., & Bittante, G. (2010). Effectiveness of mid-infrared spectroscopy to predict fatty acid composition of Brown Swiss bovine milk. Animal, 5(10), 1653–1658.

[33] Ferrand-Calmels, M., Palhière, I., Brochard, M., Leray, O., Astruc, J., Aurel, M., Barbey, S., Bouvier, F., Brunschwig, P., Caillat, H., Douguet, M., Faucon-Lahalle, F., Gelé M., Thomas, G., Trommenschlager, J., & Larroque, H. (2013). Prediction of fatty acid profiles in cow, Ewe, and goat milk by mid-infrared spectrometry. Journal of Dairy Science, 97(1), 17–35.

[34] Gottardo, P., Penasa, M., Righi, F., Lopez-Villalobos, N., Cassandro, M., & De Marchi, M. (2017). Fatty acid composition of milk from Holstein-Friesian, Brown Swiss, Simmental and Alpine Grey cows predicted by mid-infrared spectroscopy. Italian Journal of Animal Science, 16(3), 380–389.

[35] Rovere, G., de Los Campos, G., Lock, A. L., Worden, L., Vazquez, A. I., Lee, K., & Tempelman, R. J. (2021). Prediction of fatty acid composition using milk spectral data and its associations with various mid-infrared spectral regions in Michigan Holsteins. Journal of Dairy Science, 104(10), 11242–11258.

[36] Wang, Q., Hulzebosch, A., & Bovenhuis, H. (2016). Genetic and environmental variation in bovine milk infrared spectra. Journal of Dairy Science, 99(8), 6793–6803.

[37] Toledo-Alvarado, H., Vazquez, A. I., De los Campos, G., Tempelman, R. J., Bittante, G., & Cecchinato, A. (2018). Diagnosing pregnancy status using infrared spectra and milk composition in dairy cows. Journal of Dairy Science, 101(3), 2496–2505.

[38] NRC. (2001). Nutrient requirements of dairy cattle (Seventh revised edition). National Academy Press.

[39] Mattarozzi, M., Riboni, N., Maffini, M., Scarpella, S., Bianchi, F., & Careri, M. (2021). Reversed-phase and weak anion-exchange mixed-mode stationary phase for fast separation of medium-long- and very long chain free fatty acids by ultra-high-performance liquid chromatography-high resolution mass spectrometry. Journal of Chromatography A, 1648, 462209.

[40] Hayes, A. F. Truths and Myths about Mean Centering. (2013). Introduction to mediation, moderation, and conditional process analysis (pp. 282–288). The Guiford Press.

[41] Kumar, M., & Shanker Rao, G. (2017). Chapter 12 - analysis of time series. Statistical techniques for transportation engineering (pp. 463–489). Elsevier.

[42] Alseekh, S., Scossa, F., & Fernie, A. R. (2021). Ultra-high-performance liquid chromatography high-resolution mass spectrometry variants for metabolomics research. Nature Methods, 18(7), 733–746.

[43] Collomb, M., Bütikofer, U., Sieber, R., Jeangros, B., & Bosset, J. O. (2002). Correlation between fatty acids in cows’ milk fat produced in the Lowlands, Mountains and Highlands of Switzerland and botanical composition of the fodder. International Dairy Journal, 12(8), 661–666.

[44] Soyeurt, H., Dardenne, P., Gillon, A., Croquet, C., Vanderick, S., Mayerses, P., Bertozzi, C., & Gengler, N. (2006). Variation in fatty acid contents of milk and milk fat within and across breeds. Journal of Dairy Science, 89(12), 4858–4865.

[45] Bainbridge, M. L., Cersosimo, L. M., Wright, A. D. G., & Kraft, J. (2016). Content and composition of branched-chain fatty acids in bovine milk are affected by lactation stage and breed of dairy cow. PLoS One, 11(3), e0150386.

[46] White, S. L., Bertrand, J. A., Wade, M. R., Washburn, S., Green, J., Jr., & Jenkins, T. (2001). Comparison of fatty acid content of milk from Jersey and Holstein cows consuming pasture or a total mixed ration. Journal of Dairy Science, 84(10), 2295–2301.

[47] Fengen, W., Meiqing, C., Runbo, L., Guoxin, H., Xufang, W., Nan, Z., Yangdong, Z., & Jiaqi, W. (2022). Fatty acid profiles of milk from Holstein cows, Jersey cows, buffalos, yaks, humans, goats, camels, and donkeys based on gas chromatography-mass spectrometry. Journal of Dairy Science, 105(2), 1687–1700.

[48] Grummer, R. R. (1991). Effect of feed on the composition of milk fat. Journal of Dairy Science, 74(9), 3244–3257.

[49] Soyeurt, H., Dehareng, F., Gengler, N., Mcparland, S., Wall, E., Berry, D. P., Coffey, M., & Dardenne, P. (2011). Mid-infrared prediction of bovine milk fatty acids across multiple breeds, production systems, and countries. Journal of Dairy Science, 94(4), 1657–1667.

[50] Mele, M., Dal Zotto, R., Cassandro, M., Conte, G., Serra, A., Buccioni, a., Bittante, G., & Secchiari, P. (2009). Genetic parameters for conjugated linoleic acid, selected milk fatty acids, and milk fatty acid unsaturation of Italian Holstein-Friesian cows. Journal of Dairy Science, 92(1), 392–400.

[51] Ferrand, M., Huquet, B., Barbey, S., Barillet, F., Faucon, F., Larroque, H., Leray, O., Trommenschlager, J. M., & Brochard, M. (2011). Determination of fatty acid profile in cow’s milk using mid-infrared spectrometry: Interest of applying a variable selection by genetic algorithms before a PLS regression. Chemometrics and Intelligent Laboratory Systems, 106(2), 183–189.

[52] Caredda, M., Addis, m., Ibba, i., Leardi, R., Scintu, M. F., Piredda, G., & Sanna, G. (2016). Prediction of fatty acid content in sheep milk by Mid-Infrared spectrometry with a selection of wavelengths by Genetic Algorithms. LWT - Food Science and Technology, 65, 503–510.

[53] Tian, Z., Zhang, Y., Zhang, H., Sun, Y., Mao, Y., Yang, Z., & Li, M. (2022). Transcriptional regulation of milk fat synthesis in dairy cattle. Journal of Functional Foods, 96, 105208.

[54] Rutten, M. J. M., Bovenhuis, B., Hettinga, K. A., van Valenberg, H. J. F., & van Arendonk, J. A. M. (2009). Predicting bovine milk fat composition using infrared spectroscopy based on milk samples collected in winter and summer. Journal of Dairy Science, 92(12), 6202–6209.

[55] Ho, P., Bonfatti, V., Luke, T., & Pryce, J. (2019). Classifying the fertility of dairy cows using milk mid-infrared spectroscopy. Journal of Dairy Science, 102(11), 10460–10470.

[56] Luke, T., Rochfort, S., Wales, W., Bonfatti, V., Marett, L., & Pryce, J. (2019). Metabolic profiling of early-lactation dairy cows using milk mid-infrared spectra. Journal of Dairy Science, 102(2), 1747–1760.

[57] Tiplady, K. M., Lopdell, T. J., Sherlock, R. G., Johnson, T. J. J., Spelman, R., Harris, B. L., Davis, S. R., Littlejohn, M. D., & Garrick, D. J. (2022). Comparison of the genetic characteristics of directly measured and Fourier-transform mid-infrared-predicted bovine milk fatty acids and proteins. Journal of Dairy Science, 105(12), 9763–9791.

[58] Wang, F., Chen, M., Luo, R., Huang, G., Wu, X., Zheng, N., Zhang, Y., & Wang, J. (2022). Fatty acid profiles of milk from Holstein cows, Jersey cows, buffalos, yaks, humans, goats, camels, and donkeys based on gas chromatography–mass spectrometry. Journal of Dairy Science, 105(2), 1687–1700.

[59] Wang, J., He, Y., Pang, K., Zeng, Q., Zhang, X., Ren, F., & Guo, H. (2019). Changes in milk yield and composition of colostrum and regular milk from four buffalo breeds in China during lactation. Journal of the Science of Food and Agriculture, 99(13), 5799–5807.

[60] Duffy, & Norman, V. (1972). Interpretation of infrared spectra. Journal of Chemical Education, 49, 30–45.

[61] Soyeurt, H., Misztal, I., & Gengler, N. (2010). Genetic variability of milk components based on mid-infrared spectral data. Journal of Dairy Science, 93(4), 1722–1728.

[62] Rovere, G., de Los Campos, G., Tempelman, R. J., Vazquez, A. I., Miglior, F., Schenkel, F., Cecchinato, A., Bittante, G., Toledo-Alvarado, H., & Fleming, A. (2019). A landscape of the heritability of Fourier-transform infrared spectral wavelengths of milk samples by parity and lactation stage in Holstein cows. Journal of Dairy Science, 102(2), 1354–1363.

[63] Soyeurt, H., Gillon, A., Vanderick, S., Mayeres, P., Bertozzi, C., & Gengler, N. (2007). Estimation of heritability and genetic correlations for the major fatty acids in bovine milk. Journal of Dairy Science, 90(9), 4435–4442.

[64] Narayana, S. G., Schenkel, F. S., Fleming, A., Koeck, A., Malchiodi, F., Jamrozik, J., Johnston, J., Sargolzaei, M., & Miglior, F. (2017). Genetic analysis of groups of mid-infrared predicted fatty acids in milk. Journal of Dairy Science, 100(6), 4731–4744.

[65] Kaylegian, K. E., Lynch, J. M., Fleming, J. R., & Barbano, D. M. (2009). Influence of fatty acid chain length and unsaturation on mid-infrared milk analysis. Journal of Dairy Science, 92(6), 2485–2501.

[66] Sun, D. W. (2009). Infrared spectroscopy for food quality analysis and control: Fourier transform infrared (FT-IR) spectroscopy. Academic/Press/Elsevier.

[67] Macedo, M. L., Bisutti, V., Vanzin, A., Pegolo, S., Toscano, A., Schiavon, S., Tagliapietra, F., Gallo, L., Ajmone Marsan, P., & Cecchinato, A. (2023). Predicting milk protein fractions using infrared spectroscopy and a gradient boosting machine for breeding purposes in Holstein cattle. Journal of Dairy Science, 106(3), 1853–1873.

RIGHTS & PERMISSIONS

2024 The Author(s). Animal Research and One Health published by John Wiley & Sons Australia, Ltd on behalf of Institute of Animal Science, Chinese Academy of Agricultural Sciences.