Volatile fatty acids (VFAs) and methane are the main products of rumen fermentation. Quantitative studies of rumen fermentation parameters can be performed using in vitro techniques and machine learning methods. The currently proposed models suffer from poor generalization ability due to the small number of samples. In this study, a prediction model for rumen fermentation parameters (methane, acetic acid (AA), and propionic acid (PA)) of dairy cows is established using the stacking ensemble learning method and in vitro techniques. Four factors related to the nutrient level of total mixed rations (TMRs) are selected as inputs to the model: neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM). The comparison of the prediction results of the stacking model and base learners shows that the stacking ensemble learning method has better prediction results for rumen methane (coefficient of determination ($R^2$) = 0.928, root mean square error (RMSE) = 0.968 mL/g), AA ($R^2$ = 0.888, RMSE = 1.975 mmol/L) and PA ($R^2$ = 0.924, RMSE = 0.74 mmol/L). And the stacking model simulates the variation of methane and VFAs in relation to the dietary fiber content. To demonstrate the robustness of the model in the case of small samples, an independent validation experiment was conducted. The stacking model successfully simulated the transition of rumen fermentation type and the change of methane content under different concentrate-to-forage (C:F) ratios of TMR. These results suggest that the rumen fermentation parameter prediction model can be used as a decision-making basis for the optimization of dairy cow diet compositions, rapid screening of methane emission reduction, feed beneficial to dairy cow health, and improvement of feed utilization.

This study examined branched-chain fatty acids (BCFAs)’ effects on oxidative stress, energy metabolism, inflammation, tight junction disruption, apoptosis, and Toll-like receptor 4/nuclear factor kappa-B (TLR4/NF-κB) signaling in lipopolysaccharide (LPS)-induced calf small intestinal epithelial cells (CSIECs). Eight groups were used: a control group, an LPS-induced group, and six BCFA treatment groups (12-methyltridecanoic acid (iso-C14:0), 13-methyltetradecanoic acid (iso-C15:0), 14-methylpentadecanoic acid (iso-C16:0), 15-methylhexadecanoic acid (iso-C17:0), 12-methyltetradecanoic acid (anteiso-C15:0), and 14-methylhexadecanoic acid (anteiso-C17:0)) with LPS. The BCFA pretreatments significantly increased CSIEC activity compared to the LPS-induced group, with iso-C14:0 showing the highest activity (89.73%). BCFA reduced Reactive Oxygen Species (ROS) generation and malondialdehyde (MDA) levels and improved the superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), and catalase (CAT) activities and glutathione (GSH) levels. Iso-C16:0 optimized total antioxidant capacity (T-AOC). BCFA enhanced the mitochondrial membrane potential, Adenosine Triphosphate (ATP) enzyme activity, and ATP content, with iso-C14:0 increasing ATP by 27.01%. BCFA downregulated interleukin (IL)-1β, IL-8, tumor necrosis factor (TNF)-α, and interferon (INF)-γ gene expression, reduced IL-6 levels, and increased IL-10 expression. Myeloid differentiation factor 88 (MyD88) mRNA levels were reduced. BCFA alleviated Zonula Occludin (ZO-1), Claudin-1, and Claudin-4 decrease and increased Occludin levels. BCFA mitigated LPS-induced increases in Caspase-3 and BCL2-Associated X (BAX) mRNA levels, reduced Caspase-8 and Caspase-9 expression, and increased B-Cell Lymphoma-2 (BCL-2) mRNA levels. The Entropy Weight-TOPSIS method was adopted, and it was discovered that iso-C15:0 has the best effect. In summary, BCFA supplementation mitigated oxidative stress and enhanced mitochondrial function. BCFA inhibited TLR4/NF-κB signaling pathway overactivation, regulated inflammatory cytokine gene expression, reduced cellular apoptosis, preserved tight junction integrity, and supported barrier function.

The gut microbiome plays an important role in the healthy and efficient farming of dairy cows. However, high-dimensional microbial information is difficult to interpret in a simplified manner. We collected fecal samples from 161 cows and performed 16S amplicon sequencing. We developed an interpretable machine learning framework to classify individuals based on their milk urea nitrogen (MUN) concentrations. In this framework, we address the challenge of handling high-dimensional microbial data imbalances and identify 9 microorganisms strongly correlated with MUN. We introduce the Shapley Additive Explanations (SHAP) method to provide insights into the machine learning predictions. The results of the study showed that the performance of the machine learning model improved (accuracy = 72.7%) after feature selection on high-dimensional data. Among the 9 microorganisms, g__Firmicutes_unclassified had the greatest impact in the model. This study provides a reference for precision animal husbandry.