Dapeng Li

This study addresses the inefficiencies, subjectivity, and poor adaptability to lighting variations inherent in traditional candling methods used in large-scale egg incubation. We developed a high-throughput transmissive imaging system capable of capturing 30 eggs simultaneously. Based on this system, we propose PDA-YOLO, an enhanced YOLOv8-based object detection model featuring a position-decoupled attention strategy. Specifically, a lightweight C2f-SE module is integrated into the backbone to amplify subtle feature responses in low-contrast regions, while a CBAM is deployed prior to the detection head to mitigate background clutter through precise spatial attention. Experimental results on a self-constructed Hailan White egg dataset show that at the critical 60 h incubation stage, PDA-YOLO achieves a Recall of 91.5% and an mAP@0.5 of 97.4%, outperforming the YOLOv8 baseline while maintaining a real-time inference speed of 62.1 FPS. Grad-CAM visualizations confirm the model’s ability to focus on vascular textures and suppress noise. Furthermore, the model demonstrates robust performance under varying illumination (180–540 lumens), effectively mitigating missed detections in low light and recognition degradation from overexposure. This work provides a scalable, real-time solution for non-destructive, early-stage detection of poultry health and fertilization status in commercial hatcheries.

Controlling low ambient temperatures and ammonia levels is critical for effective environmental management in poultry houses during winter, as both represent persistent stressors affecting bird health and productivity. However, evidence regarding their combined long-term effects on the physiological responses of laying hens remains limited. In this study, 576 eighteen-week-old Hy-Line Brown hens were randomly assigned to six treatments (8 replicates with 12 birds per replicate each treatment) and housed in environmentally controlled chambers for 20 weeks: T1 (8 °C, ≤5 ppm ammonia), T2 (8 °C, 20 ppm ammonia), T3 (8 °C, 45 ppm ammonia), T4 (20 °C, ≤5 ppm ammonia; control), T5 (20 °C, 20 ppm ammonia), and T6 (20 °C, 45 ppm ammonia). Plasma samples were collected at 22, 26, 30, 34, and 38 weeks to evaluate physiological stress biomarkers (corticosterone, CORT; total antioxidant capacity, T-AOC), immunoglobulins (IgG, IgM, and IgA), and reproductive hormones (luteinizing hormone, LH; follicle-stimulating hormone, FSH; estradiol, E2). At 38 weeks, hypothalamus, pituitary, and spleen tissues were collected to assess the relative mRNA expression of gonadotropin-releasing hormone (GnRH), FSH, tumor necrosis factor-α (TNF-α), and interleukins (IL-1β, IL-6, and IL-10). Results showed that both cold and ammonia stress reduced antioxidant capacity, disrupted immune homeostasis, and altered reproductive hormone profiles. Cold exposure induced acute immunoendocrine alterations with partial physiological adaptation over time, whereas ammonia exerted progressive and cumulative damage, including elevated immunoglobulins (IgG and IgM) and downregulation of GnRH and FSH expression. Combined exposure significantly upregulated TNF-α and IL-1β expression, suggesting a synergistic inflammatory response. These results highlight complex, parameter-specific interactions between cold and ammonia stressors, emphasizing the need for targeted environmental strategies. Stage-specific interventions—thermal regulation in early laying and ammonia control in later phases—are recommended to safeguard hen health and optimize productivity under winter conditions.

Background: Suaeda glauca and Suaeda salsa have obvious morphological features and strongly tolerate saline–alkali environments. However, the mechanisms that lead to the differences in saline–alkali tolerance between them remain unclear. Methods: In this study, we employed comparative transcriptome analysis to investigate S. glauca and S. salsa under saline–alkali stress. Results: Our sequencing efforts resulted in the identification of 99,868 unigenes. We obtained 12,021 and 6227 differentially expressed genes (DEGs) from the S. glauca and S. salsa under salt stress compared with plants in the control. Notably, 1189 and 1864 were specifically upregulated DEGs in the roots and leaves of S. salsa under saline–alkali conditions, respectively. These genes were enriched in pathways such as “Plant hormone signal transduction”, “Carbon metabolism” and “Starch and sucrose metabolism”. Further analysis of stress-related pathways and gene expression levels revealed that key genes involved in abscisic acid (ABA) and jasmonic acid (JA) biosynthesis, ABA signal transduction, and their downstream transcription factors were upregulated in the roots of S. salsa under saline–alkali conditions. Additionally, 24 DEGs associated with stress response were identified in the roots and leaves of both species. The expression levels of these pathways and related genes were higher in S. salsa than in S. glauca, suggesting that S. salsa enhances its saline–alkali tolerance by elevating the expression of these genes. Conclusions: This study provides a new research perspective for revealing the differences in saline–alkali tolerance mechanisms between S. glauca and S. salsa, bringing forth important candidate genes for studying their saline–alkali tolerance.

Heat stress poses a significant challenge to livestock farming, particularly affecting the health and productivity of high-yield dairy cows. This study develops a machine learning framework aimed at predicting the core body temperature (CBT) of dairy cows to enable more effective heat stress management and enhance animal welfare. The dataset includes 3005 records of physiological data from real-world production environments, encompassing environmental parameters, individual animal characteristics, and infrared temperature measurements. Employed machine learning algorithms include elastic net (EN), artificial neural networks (ANN), random forests (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and CatBoost, alongside several optimization algorithms such as Bayesian optimization (BO) and grey wolf optimizer (GWO) to refine model performance through hyperparameter tuning. Comparative analysis of various feature sets reveals that the feature set incorporating the average infrared temperature of the trunk (IRTave_TK) excels in CBT prediction, achieving a coefficient of determination (R²) value of 0.516, mean absolute error (MAE) of 0.239 °C, and root mean square error (RMSE) of 0.302 °C. Further analysis shows that the GWO–XGBoost model surpasses others in predictive accuracy with an R² value of 0.540, RMSE as low as 0.294 °C, and MAE of just 0.232 °C, and leads in computational efficiency with an optimization time of merely 2.41 s—approximately 4500 times faster than the highest accuracy model. Through SHAP (SHapley Additive exPlanations) analysis, IRTave_TK, time zone (TZ), days in lactation (DOL), and body posture (BP) are identified as the four most critical factors in predicting CBT, and the interaction effects of IRTave_TK with other features such as body posture and time periods are unveiled. This study provides technological support for livestock management, facilitating the development and optimization of predictive models to implement timely and effective interventions, thereby maintaining the health and productivity of dairy cows.

Producing translucent eggs has been found to reduce the quality and safety of the eggs, as well as the demand from consumers. However, the intestinal function and the molecular mechanism for the production of translucent eggs remain uncertain. A total of 120 eggs from 276-day-old Jining Bairi were divided into two groups based on eggshell translucence: the translucent egg group (group T) and the normal group (group C). Group T exhibited thicker eggshells and a lower egg yolk color. Subsequently, we divided the chickens into translucent and normal groups based on their egg quality. We then assessed the plasma biochemical index, intestinal morphology and structure, enzyme activity, and antioxidant capacity of the hens producing translucent eggs compared to those producing normal eggs. The results showed that the ratio of duodenal villus length to crypt depth, succinate dehydrogenase (SDH) activity, chymotrypsin, total ATPase (T-ATPase), alkaline phosphatase (AKP), and glutathione peroxidase (GSH-Px) activities were decreased in the hens produced translucent eggs (p < 0.05), but malondialdehyde (MDA) content was increased (p < 0.05); jejunal lipase activity, Na⁺K⁺-ATPase activity, total antioxidant capacity (T-AOC), and GSH-Px activities were decreased (p < 0.05) in group T; ileal amylase and Ca²⁺Mg²⁺-ATPase activities were also decreased (p < 0.05) in group T. In addition, we identified a total of 471 differentially expressed genes (DEGs) in duodenal tissue, with 327 up-regulated genes and 144 down-regulated genes (|log₂FC| ≥ 1 and p < 0.05). Enrichment analysis showed that the up-regulated genes, such as GSTT1, GSTO2, and GSTA3, were mostly enriched in metabolism of xenobiotics by cytochrome P450, drug metabolism-cytochrome P450, and oxidative phosphorylation pathways. The results of our study indicate that plasma lipid metabolism disorder, decreased intestinal antioxidant capacity, and altered intestinal metabolism capabilities may influence the formation of translucent eggs.

Producing translucent eggs has been found to reduce the quality and safety of the eggs produced., as well as the demand from consumers. However, the intestinal function and the molecular mechanism for the production of translucent eggs remain uncertain. A total of 120 eggs were allocated into two groups, one for the translucent egg group (group T) and one for the normal group (group C), according to the degree of eggshell translucence. Translucent eggs showed thicker eggshell and lower egg yolk color. We also detected the plasma biochemical index, intestinal morphology and structure, enzyme activity, and antioxidant capacity of the hens’ producing translucent eggs and normal eggs. The results showed that the ratio of duodenal villus length to crypt depth, succinate dehydrogenase (SDH) activity, chymotrypsin, total ATPase (T-ATPase), alkaline phosphatase (AKP) and glutathione peroxidase (GSH-Px) activities were decreased in the hens produced translucent eggs (P < 0.05), but malondialdehyde (MDA) content was increased (P < 0.05); jejunal lipase activity, Na+K+-ATPase activity, total antioxidant capacity (T-AOC), GSH-Px activities were decreased (P < 0.05) in group T; ileal amylase and Ca2+Mg2+-ATPase activities were also decreased (P < 0.05) in group T. In addition, we identified a total of 471 differentially expressed genes (DEGs) in duodenal tissue, with 327 up-regulated genes and 144 down-regulated genes (|log2FC| ≥ 1 and P < 0.05). Enrichment analysis showed that the up-regulated genes, such as GSTT1, GSTO2, GSTA3, were mostly enriched in metabolism of xenobiotics by cytochrome P450, drug metabolism-cytochrome P450 and oxidative phosphorylation pathways. The results of our study indicate that plasma lipid metabolism disorder, decreased intestinal antioxidant capacity, and altered intestinal metabolism capabilities may influence the formation of translucent eggs.