基于中红外光谱的牛奶中三种氨基酸含量预测模型的建立及应用

doi:10.11843/j.issn.0366-6964.2023.08.016

畜牧兽医学报 ›› 2023, Vol. 54 ›› Issue (8): 3299-3312.doi: 10.11843/j.issn.0366-6964.2023.08.016

基于中红外光谱的牛奶中三种氨基酸含量预测模型的建立及应用

褚楚¹, 张静静¹, 丁磊¹, 樊懿楷¹, 包向男², 向世馨¹, 刘锐¹, 罗雪路¹, 任小丽¹, 李春芳¹, 刘文举¹, 王亮¹, 刘莉¹, 李永青¹, 江汉¹, 李委奇³, 孙伟², 李喜和², 温万³, 周佳敏³, 张淑君^1*

1. 华中农业大学动物科学技术学院、动物医学院, 动物遗传育种与繁殖教育部实验室, 武汉 430070;
2. 内蒙古国家乳业技术创新中心有限责任公司, 呼和浩特 011517;
3. 宁夏回族自治区畜牧工作站, 银川 750000

收稿日期:2022-11-25 出版日期:2023-08-23 发布日期:2023-08-22
通讯作者: 张淑君,主要从事动物抗病分子遗传育种、牛奶MIR指纹及奶牛生物标记的研究,E-mail:sjxiaozhang@mail.hzau.edu.cn
作者简介:褚楚(1999-),女,山东枣庄人,硕士,主要从事动物遗传育种与繁殖研究,E-mail:1346409454@qq.com;张静静(1996-),女,山东烟台人,硕士,主要从事动物遗传育种与繁殖研究,E-mail:1462210902@qq.com。
基金资助:
国家重点研发计划政府间国际科技创新合作（2021YFE0115500）；国家乳业技术创新中心项目（2022-科研攻关-3）；湖北省国际合作项目（2022EHB043）

Establishment and Application of Prediction Model of Three Amino Acids in Milk Based on Mid-infrared Spectroscopy

CHU Chu¹, ZHANG Jingjing¹, DING Lei¹, FAN Yikai¹, BAO Xiangnan², XIANG Shixin¹, LIU Rui¹, LUO Xuelu¹, REN Xiaoli¹, LI Chunfang¹, LIU Wenju¹, WANG Liang¹, LIU Li¹, LI Yongqing¹, JIANG Han¹, LI Weiqi³, SUN Wei², LI Xihe², WEN Wan³, ZHOU Jiamin³, ZHANG Shujun^1*

1. Laboratory of Animal Genetics, Breeding and Reproduction of Ministry of Education, College of Animal Science and Technology/College of Animal Medicine, Huazhong Agricultural University, Wuhan 430070, China;
2. Inner Mongolia National Center of Technology Innovation for Dairy Industry, Hohhot 011517, China;
3. Ningxia Hui Autonomous Region Animal Husbandry Workstation, Yinchuan 750000, China

Received:2022-11-25 Online:2023-08-23 Published:2023-08-22

摘要/Abstract

摘要： 旨在建立牛奶中游离精氨酸、组氨酸和异亮氨酸含量的中红外光谱快速批量检测的方法，并进行大量外部验证。本研究以来自华北、华中和西北3个地区4个省份的217份健康中国荷斯坦牛牛奶样本为研究对象，利用4种光谱预处理算法（SG平滑、差分、多元散射校正、标准正态变换）、4种特征选择算法（已知信息区域、适应重加权算法、遗传算法及最小角回归算法）及两种建模算法（偏最小二乘回归和岭回归），分别建立了牛奶中游离的精氨酸、组氨酸和异亮氨酸含量的MIR光谱定量预测模型，将建立的最优模型应用于另外9个不同奶牛场的4 690头牛采集的32 559个牛奶样本的MIR光谱进行预测分析，以探讨泌乳阶段、牧场、胎次及季节对MIR预测的精氨酸、组氨酸及异亮氨酸含量的影响。结果表明：1）基于CARS特征选择算法、无光谱预处理和PLSR建模算法开发的精氨酸含量预测模型效果最好，该模型R_P²=0.58，RMSEp=6.89 nmol·mL^-1；基于CARS特征选择算法、SG平滑（窗口长度为11，2阶多项式）预处理及PLSR建模算法开发的组氨酸含量预测模型效果最好，该模型R_P²=0.56，RMSEp=0.88 nmol·mL^-1；基于274个特征信息波点、SG平滑（窗口长度为29，3阶多项式）预处理及PLSR建模算法开发的异亮氨酸含量预测模型效果最好，该模型R_P²=0.49，RMSEp=1.75 nmol·mL^-1；2）将最优模型进行跨地区外部验证时，预测准确性有所降低；3）将建立的模型应用于E省（未参与模型建立）大规模光谱数据库，以预测牛奶中游离精氨酸、组氨酸和异亮氨酸含量，发现泌乳阶段、牧场、季节对牛奶中游离精氨酸、组氨酸及异亮氨酸含量均有极显著影响（P<0.001），而胎次对精氨酸含量无显著影响，对组氨酸和异亮氨酸有极显著影响（P<0.001）。结果表明，利用MIR预测牛奶中游离氨基酸含量是可行的，特别是在牛奶氨基酸含量高低趋势分析方面具有一定预测能力，而该预测模型还需要更多的有代表性样本进行优化，提高模型的准确性和通用性。

关键词: 中红外光谱(MIR), 牛乳氨基酸, 预测模型, 牛奶, 机器学习

Abstract: The purpose of this study was to establish a rapid batch determination method for free arginine, histidine and isoleucine in milk by mid-infrared spectroscopy, and to carry out a large number of external verifications. A total of 217 Chinese Holstein milk samples from 4 provinces in North China, Central China and Northwest China were taken as the research objects, using 4 spectral preprocessing algorithms (SG smoothing, difference, multivariate scattering correction, standard normal transformation), 4 feature selection algorithms (known information region, adaptive heavy weighting algorithm, genetic algorithm and minimum angle regression algorithm) and 2 modeling algorithms (partial least squares regression and ridge regression), the MIR spectral quantitative prediction models of free arginine, histidine and isoleucine contents in milk were established. The optimal model was applied to the MIR spectra of 32 559 milk samples collected from 4 690 cows in 9 different dairy farms to explore the effects of lactation stage, pasture, parity and season on the predicted arginine, histidine and isoleucine contents by MIR. The results show that:1) The prediction model of arginine content based on CARS feature selection algorithm, non-spectral pretreatment algorithm and PLSR modeling algorithm was the best, R_P²=0.58, RMSEp=6.89 nmol·mL^-1; The prediction model of histidine content based on CARS feature selection algorithm, SG smoothing (window length is 11, 2-order polynomial) pretreatment and PLSR modeling algorithm was the best, R_P²=0.56, RMSEp=0.88 nmol·mL^-1; Based on 274 characteristic information wave points, SG smoothing (window length is 29, 3-order polynomial) pretreatment and PLSR modeling algorithm, the prediction model of isoleucine content was the best, R_P²=0.49, RMSEp=1.75 nmol·mL^-1; 2) When the optimal model was verified externally across regions, the prediction accuracy was reduced; 3) Applying the established model to the large-scale spectral database of E province (not participating in the establishment of the model), the contents of free arginine, histidine and isoleucine in milk was predicted, it was found that lactation stage, pasture and season had significant effects on the contents of free arginine, histidine and isoleucine in milk (P<0.001), while parity had no significant effect on arginine content, but had significant effect on histidine and isoleucine (P<0.001). The results show that it is feasible to predict the content of free amino acids in milk by MIR, especially, it has certain predictive ability in the trend analysis of milk amino acid content, and the prediction model needs more representative samples to optimize, so as to improve the accuracy and universality of the model.

Key words: mid-infrared spectroscopy(MIR), milk amino acid, prediction model, milk, machine learning

中图分类号:

S823.91

褚楚, 张静静, 丁磊, 樊懿楷, 包向男, 向世馨, 刘锐, 罗雪路, 任小丽, 李春芳, 刘文举, 王亮, 刘莉, 李永青, 江汉, 李委奇, 孙伟, 李喜和, 温万, 周佳敏, 张淑君. 基于中红外光谱的牛奶中三种氨基酸含量预测模型的建立及应用[J]. 畜牧兽医学报, 2023, 54(8): 3299-3312.

CHU Chu, ZHANG Jingjing, DING Lei, FAN Yikai, BAO Xiangnan, XIANG Shixin, LIU Rui, LUO Xuelu, REN Xiaoli, LI Chunfang, LIU Wenju, WANG Liang, LIU Li, LI Yongqing, JIANG Han, LI Weiqi, SUN Wei, LI Xihe, WEN Wan, ZHOU Jiamin, ZHANG Shujun. Establishment and Application of Prediction Model of Three Amino Acids in Milk Based on Mid-infrared Spectroscopy[J]. Acta Veterinaria et Zootechnica Sinica, 2023, 54(8): 3299-3312.

参考文献 36

[1]	WEI M, DENG Z Y, LIU B, et al.Investigation of amino acids and minerals in Chinese breast milk[J].J Sci Food Agric, 2020, 100(10):3920-3931.
[2]	KHAN I T, NADEEM M, IMRAN M, et al.Antioxidant properties of Milk and dairy products:a comprehensive review of the current knowledge[J].Lipids Health Dis, 2019, 18(1):41.
[3]	MAO X B, GU C S, REN M, et al.L-isoleucine administration alleviates rotavirus infection and immune response in the weaned piglet model[J].Front Immunol, 2018, 9:1654.
[4]	RICHERT B T, GOODBAND R D, TOKACH M D, et al.Increasing valine, isoleucine, and total branched-chain amino acids for lactating sows[J].J Anim Sci, 1997, 75(8):2117-2128.
[5]	ZHAO Y, YAN M Y, JIANG Q, et al.Isoleucine improved growth performance, and intestinal immunological and physical barrier function of hybrid catfish Pelteobagrus vachelli×Leiocassis longirostris[J].Fish Shellfish Immunol, 2021, 109:20-33.
[6]	ACKROYD H, HOPKINS F G.Feeding experiments with deficiencies in the amino-acid supply:arginine and histidine as possible precursors of purines[J].Biochem J, 1916, 10(4):551-576.
[7]	HOLE AČG EK M.Histidine in health and disease:metabolism, physiological importance, and use as a supplement[J].Nutrients, 2020, 12(3):848.
[8]	BROSNAN M E, BROSNAN J T.Histidine metabolism and function[J].J Nutr, 2020, 150(S1):2570S-2575S.
[9]	张爱琳, 段筱筠, 任斐, 等.牛乳中主要过敏原的分离及其氨基酸成分分析[J].中国乳品工业, 2016, 44(12):4-6, 10.ZHANG A L, DUAN X J, REN F, et al.Study the separation on the main allergens in milk and its amino acid composition analysis[J]. China Dairy Industry, 2016, 44(12):4-6, 10.(in Chinese)
[10]	MARTÍ I LÍNDEZ A A, REITH W.Arginine-dependent immune responses[J].Cell Mol Life Sci, 2021, 78(13):5303-5324.
[11]	RASHID J, KUMAR S S, JOB K M, et al.Therapeutic potential of citrulline as an arginine supplement:a clinical pharmacology review[J].Paediatr Drugs, 2020, 22(3):279-293.
[12]	关博元, 张正翰, 石佳鑫, 等.人常乳与牛常乳中全谱游离氨基酸和水解氨基酸的对比[J].食品科学, 2019, 40(10):193-198.GUAN B Y, ZHANG Z H, SHI J X, et al.Comparison of full-spectrum free and hydrolyzed amino acids in human and bovine milks[J].Food Science, 2019, 40(10):193-198.(in Chinese)
[13]	PIRI-MOGHADAM H, MILLER A, PRONGER D, et al.Quantification of branched-chain amino acids in plasma by high-performance liquid chromatography-tandem mass spectrometry (LC-MS/MS)[M]//GARG U.Clinical Applications of Mass Spectrometry in Biomolecular Analysis.New York:Springer, 2022:65-81.
[14]	XU W H, ZHONG C C, ZOU C P, et al.Analytical methods for amino acid determination in organisms[J].Amino Acids, 2020, 52(8):1071-1088.
[15]	FERRÉ S, GONZÁLEZ-RUIZ V, GUILLARME D, et al.Analytical strategies for the determination of amino acids:past, present and future trends[J].J Chromatogr B Analyt Technol Biomed Life Sci, 2019, 1132:121819.
[16]	LI G, WU D, XIE W Y, et al.Analysis of amino acids in tobacco by derivatization and dispersive liquid-liquid microextraction based on solidification of floating organic droplet method[J].J Chromatogr A, 2013, 1296:243-247.
[17]	WEBER P.Determination of amino acids in food and feed by microwave hydrolysis and UHPLC-MS/MS[J].J Chromatogr B Analyt Technol Biomed Life Sci, 2022, 1209:123429.
[18]	ZHAO X X, SONG Y T, ZHANG Y P, et al.Predictions of milk fatty acid contents by mid-infrared spectroscopy in Chinese Holstein cows[J].Molecules, 2023, 28(2):666
[19]	YAO Z Q, NIE P, ZHANG X X, et al.Establishment and validation of Fourier transform infrared spectroscopy (FT-MIR) methodology for the detection of linoleic acid in buffalo milk[J].Foods, 2023, 12(6):1199.
[20]	SALLEH S M, DANIELSSON R, KRONQVIST C.Using machine learning methods to predict dry matter intake from milk mid-infrared spectroscopy data on Swedish dairy cattle[J].J Dairy Res, 2023, 90(1):5-8.
[21]	GRUBER S, RIENESL L, KÖCK A, et al.Importance of mid-infrared spectra regions for the prediction of mastitis and ketosis in dairy cows[J].Animals (Basel), 2023, 13(7):1193.
[22]	MCDERMOTT A, DE MARCHI M, BERRY D P, et al.Cow and environmental factors associated with protein fractions and free amino acids predicted using mid-infrared spectroscopy in bovine milk[J].J Dairy Sci, 2017, 100(8):6272-6284.
[23]	SHADPOUR S, CHUD T C S, HAILEMARIAM D, et al.Predicting dry matter intake in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks[J].J Dairy Sci, 2022, 105(10):8257-8271.
[24]	SOYEURT H, DEHARENG F, GENGLER N, et al.Mid-infrared prediction of bovine milk fatty acids across multiple breeds, production systems, and countries[J].J Dairy Sci, 2011, 94(4):1657-1667.
[25]	BITTANTE G, CECCHINATO A.Genetic analysis of the Fourier-transform infrared spectra of bovine milk with emphasis on individual wavelengths related to specific chemical bonds[J].J Dairy Sci, 2013, 96(9):5991-6006.
[26]	KAYLEGIAN K E, HOUGHTON G E, LYNCH J M, et al.Calibration of infrared milk analyzers:modified milk versus producer milk[J]. J Dairy Sci, 2006, 89(8):2817-2832.
[27]	TOLEDO-ALVARADO H, PÉREZ-CABAL M A, TEMPELMAN R J, et al.Association between days open and milk spectral data in dairy cows[J].J Dairy Sci, 2021, 104(3):3665-3675.
[28]	WANG Q Y, 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].J Dairy Sci, 2019, 102(7):6288-6295.
[29]	SHETTY N, DIFFORD G, LASSEN J, et al.Predicting methane emissions of lactating Danish Holstein cows using Fourier transform mid-infrared spectroscopy of milk[J].J Dairy Sci, 2017, 100(11):9052-9060.
[30]	GOTTARDO P, PENASA M, LOPEZ-VILLALOBOS N, et al.Variable selection procedures before partial least squares regression enhance the accuracy of milk fatty acid composition predicted by mid-infrared spectroscopy[J].J Dairy Sci, 2016, 99(10):7782-7790.
[31]	MCPARLAND S, BANOS G, WALL E, et al.The use of mid-infrared spectrometry to predict body energy status of Holstein cows[J]. J Dairy Sci, 2011, 94(7):3651-3661.
[32]	MCPARLAND S, BANOS G, MCCARTHY B, et al.Validation of mid-infrared spectrometry in milk for predicting body energy status in Holstein-Friesian cows[J].J Dairy Sci, 2012, 95(12):7225-7235.
[33]	WEINERT-NELSON J R, MEYER W A, WILLIAMS C A.Diurnal variation in forage nutrient composition of mixed cool-season grass, crabgrass, and bermudagrass pastures[J].J Equine Vet Sci, 2022, 110:103836.
[34]	李爽, 孙悦, 李铁柱, 等.西门塔尔牛乳成分及氨基酸组成分析[J].中国乳品工业, 2013, 41(1):15-18.LI S, SUN Y, LI T Z, et al.Analysis of Simmental milk and amino acid composition[J].China Dairy Industry, 2013, 41(1):15-18.(in Chinese)
[35]	双金, 敖力格日玛, 侯先志, 等.研究通辽地区荷斯坦牛乳中氨基酸含量的季节变化特点[J].中国奶牛, 2011(13):52-54.SHUANG J, AO L R M, HOU X Z et al.To study the seasonal variation characteristics of amino acid content in Holstein milk in Tongliao area[J].China Dairy Cattle, 2011(13):52-54.(in Chinese)
[36]	张幸开, 袁耀明.影响奶牛乳蛋白生产的因素及应对措施[J].中国奶牛, 2006(12):17-21.ZHANG X K, YUAN Y M.Factors affecting milk protein and countermeasures in dairy cows[J].China Dairy Cattle, 2006(12):17-21.(in Chinese)

基于中红外光谱的牛奶中三种氨基酸含量预测模型的建立及应用

Establishment and Application of Prediction Model of Three Amino Acids in Milk Based on Mid-infrared Spectroscopy

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 36

相关文章 8

编辑推荐

Metrics

本文评价

[1]	张元旭, 李竟, 王泽昭, 陈燕, 徐凌洋, 张路培, 高雪, 高会江, 李俊雅, 朱波, 郭鹏. 动物遗传评估软件研究进展[J]. 畜牧兽医学报, 2024, 55(5): 1827-1841.
[2]	徐小静, 董瑞玲, 魏立民, 赵少猛, 赵桂苹, 张敏红, 冯京海. 文昌鸡母鸡生长模型的研究[J]. 畜牧兽医学报, 2023, 54(12): 4952-4961.
[3]	丁纪强, 李庆贺, 张高猛, 李森, 郑麦青, 文杰, 赵桂苹. 比较机器学习等算法对肉鸡产蛋性状育种值估计的准确性[J]. 畜牧兽医学报, 2022, 53(5): 1364-1372.
[4]	娄文琦, 李想, 罗汉鹏, 刘林, 邹杨, 王雅春. 牛奶的中红外光谱相关变量遗传参数估计[J]. 畜牧兽医学报, 2019, 50(5): 947-956.
[5]	杜保华, 陈思, 张相德, 何宁, 杨欣, 呙于明, 姚军虎, 杨小军. 肉鸡皮大麦表观代谢能预测模型研究[J]. 畜牧兽医学报, 2018, 49(10): 2180-2190.
[6]	赵江波,魏时来,赵明明，马涛,肖怡,丁静美,李岚捷,冯文晓,贾鹏,刁其玉. 精料来源对肉羊营养物质消化率的影响及代谢能预测模型的建立[J]. 畜牧兽医学报, 2016, 47(11): 2257-2265.
[7]	许贵善，纪守坤，姜成钢，邓凯东，屠焰，刁其玉. 杜寒杂交公羔羊能量与蛋白质的组织分布及机体组成的预测模型研究[J]. 畜牧兽医学报, 2013, 44(5): 727-736.
[8]	龚都强;高利;肖建华;刘云;孙昕;孙喜娟;王洪斌. BP神经网络在新城疫预测研究中的应用[J]. 畜牧兽医学报, 2007, 38(11): 1211-1216.