Optimizing the path of livestock manure used for farmland is a hugely significant issue, which not only improves the utilization efficiency of manure but also reduces the cost of the transportation of manure. However, some factors such as different terrains and the density of surrounding farmland may lead to more difficulty in further improving the resource utilization rate. Therefore, this paper aims to establish a transport network optimization model for a complex livestock manure distribution scheme. Using basic information from livestock and poultry farms, cultivated land, water areas and forestland in Xinzhou District, Wuhan City, Hubei Province, the relationship between farmland and livestock farms is divided into farm-intensive and water-intensive farmland areas by using the Voronoi diagram subdivision method. Then, according to the supply–demand balance of manure and crop demand, an optimization model is proposed to discuss the manure return scheme for these two types of terrain. The results show that our model can help significantly improve manure utilization efficiency under different terrain situations, which is proposed comprehensively, considering the economic and environmental benefits.

Genomic prediction has been established as a powerful tool in pig breeding, which typically entails the analysis of large-scale genomic datasets. Neural network models, renowned for their robust pattern recognition capabilities, have been successfully applied to extract complex genetic patterns from such high-dimensional genomic data. Because growth traits are critical economic indicators in pig breeding, their accurate prediction is essential for genetic improvement. However, the underlying genetic architecture of these traits is highly complex, regulated by numerous genetic loci. Given that not all loci exert significant effects on growth traits and traditional neural networks face challenges in capturing genome-wide genetic interactions, there is an urgent need for a more efficient and accurate prediction framework. To address this challenge, we propose a novel model, TKOA-GPNN, which comprises two components: a two-stage genomic feature selection module and a genomic prediction neural network. First, symmetric uncertainty correlation analysis is employed to reduce the feature space. Subsequently, a kepler optimization algorithm integrated with tent mapping is applied to select trait-associated loci. The selected features are then fed into the neural network (GPNN) to conduct genomic prediction. Experimental results demonstrate that TKOA-GPNN outperforms 14 existing models with superior accuracy and efficiency. Tests based on offspring data shows favorable performance with genotyping array data, while further validation using whole-genome sequencing data confirmed the robustness of the proposed model. These results suggest that TKOA-GPNN is applicable to genomic data of different types and quality levels. Overall, TKOA-GPNN improves both prediction accuracy and computational efficiency, providing an effective solution for intelligent breeding and genetic improvement in pigs breeding.

Identifying causal genetic variants and candidate genes underlying complex traits remains a central challenge in animal breeding and genetics. Genome-wide association studies (GWAS) are widely used for this purpose. However, their reliance on marginal variant effects and sensitivity to linkage disequilibrium (LD) can lead to redundant and less accurate identification of variants or genes of biological relevance. Here, we propose SNP prioritization (GWAS-based and fine-mapping-based) strategies within a unified framework, designed to improve the selection of more informative variants and candidate genes by explicitly modeling LD structure and genetic architectures of three pig teat-related traits (total teat number, teat symmetry, and teat adequacy). While GWAS prioritization favored variants with strong marginal effects, fine-mapping substantially improved joint explanatory performance and prediction accuracy. For total teat number, the best-performing fine-mapping-derived SNP subset achieved a mean PCC of 0.6599 across 10-fold cross-validation, compared with 0.3755 for GWAS-based prioritization. Similarly, for teat adequacy, the highest mean AUC increased from 0.7012 (GWAS) to 0.8547 (fine-mapping). Moreover, fine-mapping-derived SNP sets identified more coherent and trait-specific biological pathways and functionally relevant candidate genes. Taken together, our findings demonstrate that fine-mapping provides a more accurate and biologically meaningful framework for SNP and candidate gene prioritization, supporting its integration into genetic analysis and breeding applications.