BACKGROUND: Integrative use of multi-omics data can enhance genomic prediction, yet its application remains challenged by the high cost, temporal specificity, and instability of transcriptomic signals across developmental stages. To address these limitations, it is crucial to utilize small, high-quality multi-omics datasets to efficiently identify stable, major-effect SNPs that can be applied to larger populations with genomic data alone. We propose AbGP (Attention-based Genomic Prediction), a framework designed to extract these robust genomic features. RESULTS: Using a discovery population of Huaxi cattle (HX_A, n = 218) with matched genotype and transcriptome data, AbGP employed a self-attention mechanism to identify a compact, high-value subset of SNPs (top 1.25%). The model’s predictive power was validated in a large, independent population (HX_B, n = 1496), where it significantly outperformed GBLUP and machine learning baselines for economic traits. CONCLUSION: AbGP effectively distills complex multi-omics information into a small subset of key SNPs that capture essential non-linear genetic architectures. This approach improves prediction accuracy and model stability, facilitating practical deployment in Huaxi cattle breeding.

MOTIVATION: Copy number abbreviation (CNA) is one type of genomic aberration that is often induced by genome instability and is associated with diseases such as cancer. Determination of the genome-wide CNA profile is an important step in identifying the underlying mutation mechanisms. Genomic data based on next-generation sequencing technology are particularly suitable for determination of high-quality CNA profile. Now is an important time to reevaluate the use of sequencing techniques for CNA analysis, especially with the rapid growth of the different targeted genome and whole-genome sequencing strategies. RESULTS: In this study, we provide a comparison of resequencing strategies, with regard to their utility, applied to the same hepatocellular carcinoma sample for copy number determination. These strategies include whole-genome, exome and restriction site-associated DNA (RAD) sequencing. The last of these strategies is a targeted sequencing technique that involves cutting the genome with a restriction enzyme and isolating the targeted sequences. Our data demonstrate that RAD sequencing is an efficient and comprehensive strategy that allows the cost-effective determination of CNAs. Further investigation of RAD sequencing data led to the finding that a precise measurement of the allele frequency would be a helpful complement to the read depth for CNA analysis for two reasons. First, knowledge of the allele frequency helps to resolve refined calculations of allele-specific copy numbers, which, in turn, identify the functionally important CNAs that are under natural selection on the parental alleles. Second, this knowledge enables deconvolution of CNA patterns in complex genomic regions.