Enhancing genomic prediction accuracy in Huaxi cattle through integration of transcriptomic data and a self-attention-based SNP selection strategy

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. Using a discovery population of Huaxi cattle (HXA, 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 (HXB, n = 1496), where it significantly outperformed GBLUP and machine learning baselines for economic traits. 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.