Enhancing the accuracy of genomic prediction is a key goal in genomic selection (GS) research. Integrating prior biological information into GS methods using appropriate models can improve prediction accuracy for complex traits. Genome-wide association study (GWAS) is widely utilized to identify potential candidate loci associated with complex traits in livestock and poultry, offering essential genomic insights. In this study, a GWAS was conducted on 685 Duroc × Landrace × Yorkshire (DLY) pigs to extract significant single-nucleotide polymorphisms (SNPs) as genomic features. We compared two GS models, genomic best linear unbiased prediction (GBLUP) and genomic feature BLUP (GFBLUP), by using imputed whole-genome sequencing (WGS) data on 651 Yorkshire pigs. The results revealed that the GBLUP model achieved prediction accuracies of 0.499 for backfat thickness (BFT) and 0.423 for loin muscle area (LMA). By applying the GFBLUP model with GWAS-based SNP preselection, the average prediction accuracies for BFT and LMA traits reached 0.491 and 0.440, respectively. Specifically, the GFBLUP model displayed a 4.8% enhancement in predicting LMA compared to the GBLUP model. These findings suggest that, in certain scenarios, the GFBLUP model may offer superior genomic prediction accuracy when compared to the GBLUP model, underscoring the potential value of incorporating genomic features to refine GS models.

Genomic prediction (GP), which uses genome-wide markers to estimate breeding values, is a crucial tool for accelerating genetic progress in livestock and plant breeding. The accuracy of GP depends on several factors, including the statistical model, marker density, and cross-validation strategy. This study evaluated these factors to optimize GP accuracy for eight economically important carcass and body traits in a Duroc × (Landrace × Yorkshire) (DLY) pig population. This study used 50 K SNP chip data from 1494 DLY pigs, which were imputed to the whole genome sequence (WGS) level. Seven different models were compared, including GBLUP, ssGBLUP, and five Bayesian models. The ssGBLUP model consistently outperformed other models across all traits, with prediction accuracies ranging from 0.371 to 0.502. Further analyses showed that prediction accuracy improved with increasing cross-validation folds and marker density, particularly in the low-density panel. However, the improvement plateaued in medium-to-high-density scenarios. These findings underscore the importance of carefully selecting the model, marker density, and cross-validation strategy to optimize GP accuracy for carcass and body traits in commercial pigs. The insights from this study can guide breeders and researchers in maximizing genetic progress in pig breeding programs.