Metabolic disturbances adversely impact productive and reproductive performance of dairy cattle due to changes in endocrine status and immune function, which increase the risk of disease. This may occur in the post-partum phase, but also throughout lactation, with sub-clinical symptoms. Recently, increased attention has been directed towards improved health and resilience in dairy cattle, and genomic selection (GS) could be a helpful tool for selecting animals that are more resilient to metabolic disturbances throughout lactation. Hence, we evaluated the genomic prediction of serum biomarkers levels for metabolic distress in 1353 Holsteins genotyped with the 100K single nucleotide polymorphism (SNP) chip assay. The GS was evaluated using parametric models best linear unbiased prediction (GBLUP), Bayesian B (BayesB), elastic net (ENET), and nonparametric models, gradient boosting machine (GBM) and stacking ensemble (Stack), which combines ENET and GBM approaches. The results show that the Stack approach outperformed other methods with a relative difference (RD), calculated as an increment in prediction accuracy, of approximately 18.0% compared to GBLUP, 12.6% compared to BayesB, 8.7% compared to ENET, and 4.4% compared to GBM. The highest RD in prediction accuracy between other models with respect to GBLUP was observed for haptoglobin (hapto) from 17.7% for BayesB to 41.2% for Stack; for Zn from 9.8% (BayesB) to 29.3% (Stack); for ceruloplasmin (CuCp) from 9.3% (BayesB) to 27.9% (Stack); for ferric reducing antioxidant power (FRAP) from 8.0% (BayesB) to 40.0% (Stack); and for total protein (PROTt) from 5.7% (BayesB) to 22.9% (Stack). Using a subset of top SNPs (1.5k) selected from the GBM approach improved the accuracy for GBLUP from 1.8 to 76.5%. However, for the other models reductions in prediction accuracy of 4.8% for ENET (average of 10 traits), 5.9% for GBM (average of 21 traits), and 6.6% for Stack (average of 16 traits) were observed. Our results indicate that the Stack approach was more accurate in predicting metabolic disturbances than GBLUP, BayesB, ENET, and GBM and seemed to be competitive for predicting complex phenotypes with various degrees of mode of inheritance, i.e. additive and non-additive effects. Selecting markers based on GBM improved accuracy of GBLUP.

中文翻译：

---

使用参数和非参数模型对荷斯坦牛代谢紊乱的血液生物标志物进行基因组预测


由于内分泌状态和免疫功能的变化，代谢紊乱会对奶牛的生产和繁殖性能产生不利影响，从而增加患病风险。这可能发生在产后阶段，但也可能发生在整个哺乳期，并伴有亚临床症状。最近，人们越来越关注改善奶牛的健康和恢复能力，而基因组选择（GS）可能是一个有用的工具，用于选择在整个哺乳期对代谢紊乱更具恢复能力的动物。因此，我们评估了通过 100K 单核苷酸多态性 (SNP) 芯片测定进行基因分型的 1353 头荷斯坦牛代谢窘迫的血清生物标志物水平的基因组预测。使用参数模型最佳线性无偏预测（GBLUP）、贝叶斯 B（BayesB）、弹性网络（ENET）和非参数模型、梯度增强机（GBM）和堆叠集成（Stack）（结合了 ENET 和 GBM 方法）对 GS 进行评估。结果表明，Stack 方法优于其他方法，其相对差异 (RD)（以预测精度的增量计算）与 GBLUP 相比约为 18.0%，与 BayesB 相比约为 12.6%，与 ENET 相比约为 8.7%，与 ENET 相比约为 4.4%到 GBM。触珠蛋白 (hapto) 的 GBLUP 预测精度在其他模型中最高 RD，从 BayesB 的 17.7% 到 Stack 的 41.2%； Zn 从 9.8% (BayesB) 到 29.3% (Stack)；铜蓝蛋白 (CuCp) 从 9.3% (BayesB) 到 27.9% (Stack)；铁的抗氧化能力 (FRAP) 从 8.0% (BayesB) 降低至 40.0% (Stack)；总蛋白 (PROTt) 从 5.7% (BayesB) 到 22.9% (Stack)。使用从 GBM 方法中选择的顶级 SNP 子集 (1.5k) 将 GBLUP 的准确性从 1.8% 提高到 76.5%。 然而，对于其他模型，ENET（10 个性状的平均值）的预测准确度降低了 4.8%，GBM（21 个性状的平均值）降低了 5.9%，Stack（16 个性状的平均值）降低了 6.6%。我们的结果表明，Stack 方法在预测代谢紊乱方面比 GBLUP、BayesB、ENET 和 GBM 更准确，并且在预测具有不同程度的遗传模式（即加性和非加性效应）的复杂表型方面似乎具有竞争力。基于 GBM 选择标记提高了 GBLUP 的准确性。