Blood metabolic profiles can be used to assess metabolic disorders and to evaluate the health status of dairy cows. Given that these analyses are time-consuming, expensive, and stressful for the cows, there has been increased interest in Fourier transform infrared (FTIR) spectroscopy of milk samples as a rapid, cost-effective alternative for predicting metabolic disturbances. The integration of FTIR data with other layers of information such as genomic and on-farm data (days in milk (DIM) and parity) has been proposed to further enhance the predictive ability of statistical methods. Here, we developed a phenotype prediction approach for a panel of blood metabolites based on a combination of milk FTIR data, on-farm data, and genomic information recorded on 1150 Holstein cows, using BayesB and gradient boosting machine (GBM) models, with tenfold, batch-out and herd-out cross-validation (CV) scenarios. The predictive ability of these approaches was measured by the coefficient of determination (R2). The results show that, compared to the model that includes only FTIR data, integration of both on-farm (DIM and parity) and genomic information with FTIR data improves the R2 for blood metabolites across the three CV scenarios, especially with the herd-out CV: R2 values ranged from 5.9 to 17.8% for BayesB, from 8.2 to 16.9% for GBM with the tenfold random CV, from 3.8 to 13.5% for BayesB and from 8.6 to 17.5% for GBM with the batch-out CV, and from 8.4 to 23.0% for BayesB and from 8.1 to 23.8% for GBM with the herd-out CV. Overall, with the model that includes the three sources of data, GBM was more accurate than BayesB with accuracies across the CV scenarios increasing by 7.1% for energy-related metabolites, 10.7% for liver function/hepatic damage, 9.6% for oxidative stress, 6.1% for inflammation/innate immunity, and 11.4% for mineral indicators. Our results show that, compared to using only milk FTIR data, a model integrating milk FTIR spectra with on-farm and genomic information improves the prediction of blood metabolic traits in Holstein cattle and that GBM is more accurate in predicting blood metabolites than BayesB, especially for the batch-out CV and herd-out CV scenarios.

中文翻译：

---

整合农场和基因组信息提高了牛奶红外预测奶牛代谢紊乱血液指标的预测能力

血液代谢概况可用于评估代谢紊乱和评估奶牛的健康状况。鉴于这些分析耗时、昂贵且对奶牛造成压力，人们越来越关注牛奶样品的傅里叶变换红外 (FTIR) 光谱，将其作为预测代谢紊乱的快速、经济高效的替代方法。已提议将 FTIR 数据与其他信息层（例如基因组和农场数据（产奶天数 (DIM) 和胎次）相结合）以进一步增强统计方法的预测能力。在这里，我们基于 1150 头荷斯坦奶牛的牛奶 FTIR 数据、农场数据和基因组信息的组合，开发了一组血液代谢物的表型预测方法，使用 BayesB 和梯度增强机 (GBM) 模型，十倍, batch-out 和 herd-out 交叉验证 (CV) 场景。这些方法的预测能力通过决定系数 (R2) 来衡量。结果表明，与仅包含 FTIR 数据的模型相比，农场（DIM 和胎次）和基因组信息与 FTIR 数据的整合提高了三种 CV 场景中血液代谢物的 R2，尤其是在牛群外出的情况下CV：BayesB 的 R2 值范围为 5.9 至 17.8%，具有十倍随机 CV 的 GBM 为 8.2 至 16.9%，BayesB 为 3.8 至 13.5%，具有批量 CV 的 GBM 为 8.6 至 17.5%，以及从BayesB 为 8.4% 至 23.0%，GBM 为 8.1% 至 23.8%，具有 herd-out CV。总体而言，使用包含三个数据源的模型，GBM 比 BayesB 更准确，CV 场景中的准确度提高了 7。能量相关代谢物 1%，肝功能/肝损伤 10.7%，氧化应激 9.6%，炎症/先天免疫 6.1%，矿物质指标 11.4%。我们的结果表明，与仅使用牛奶 FTIR 数据相比，将牛奶 FTIR 光谱与农场和基因组信息相结合的模型改进了对荷斯坦牛血液代谢性状的预测，并且 GBM 在预测血液代谢物方面比 BayesB 更准确，尤其是对于 batch-out CV 和 herd-out CV 场景。