可见-近红外光谱结合模拟退火偏最小二乘分析预测牛初乳中免疫球蛋白 G、A 和 M 浓度的效果。

Effectiveness of visible - Near infrared spectroscopy coupled with simulated annealing partial least squares analysis to predict immunoglobulins G, A, and M concentration in bovine colostrum.

机构信息

Department of Agronomy, Food, Natural resources, Animals and Environment, University of Padova, Viale dell'Università 16, 35020 Legnaro, PD, Italy.

出版信息

Food Chem. 2022 Mar 1;371:131189. doi: 10.1016/j.foodchem.2021.131189. Epub 2021 Sep 20.

DOI:10.1016/j.foodchem.2021.131189

PMID:34600367

Abstract

Visible - near infrared spectroscopy coupled with variable selection using simulated annealing PLS regression was tested to predict immunoglobulin fractions (g/L) of bovine colostrum, namely IgG, IgA and IgM. Immunoglobulins were quantified in 678 samples using the gold standard radial immunodiffusion. Samples were divided in calibration (50%) and validation (50%) datasets. Maximum number of selected variables were limited to 200 and root mean squared error in cross validation (RMSE) was used as loss function. Performance of the final model developed using the calibration dataset was assessed on the validation dataset. Overall, simulated annealing PLS improved validation RMSE compared to ordinary PLS regression by 3% to 17%. The present study demonstrated the effectiveness of the calibration model for accurate quantification of IgG, the most abundant immunoglobulin of bovine colostrum (RMSE = 13.28 g/L; R = 0.83). These outcomes could be useful to assess colostrum quality intended for animal and human usage.

摘要

采用模拟退火偏最小二乘回归结合变量选择的可见-近红外光谱法被用于预测牛乳初乳的免疫球蛋白分数（g/L），即 IgG、IgA 和 IgM。使用金标准放射免疫扩散法在 678 个样本中定量了免疫球蛋白。样本分为校准（50%）和验证（50%）数据集。选择的最大变量数限制为 200，交叉验证均方根误差（RMSE）用作损失函数。使用校准数据集开发的最终模型在验证数据集上进行了评估。总体而言，模拟退火偏最小二乘回归与普通偏最小二乘回归相比，验证 RMSE 提高了 3%至 17%。本研究证明了该校准模型用于准确量化牛乳初乳中最丰富的免疫球蛋白 IgG 的有效性（RMSE=13.28g/L；R=0.83）。这些结果可能有助于评估用于动物和人类使用的初乳质量。