An Enhanced Genomic Transformer for Multi-Dataset Forward-Validation Benchmarking in Pig Genomic Prediction

Genomic prediction models in pig breeding should forecast the performance of future selection candidates, yet random cross-validation does not accurately reflect this sequential setting. Here, we introduce an enhanced genomic transformer (EGT) that compresses genome-wide SNP profiles into compact tokens and incorporates a differentiable scoring term alongside mean squared error (MSE) during training. We constructed 70%/10%/20% forward-validation datasets for three pig datasets and evaluated single-trait and multi-task EGT variants against GBLUP, support-vector regression, random forest, XGBoost, CNN, and RNN across 12 prediction tasks. The better-performing EGT variant achieved a higher test-set Pearson correlation coefficient (PCC) than the baseline for 10 of the 12 prediction tasks, with the largest improvement on LDL-C (+0.057). In BloodLipid ablations, autoencoder-only representation yielded the highest mean PCC (0.285), while Pearson-MSE objective reached 0.293 versus 0.291 for MSE-only training. Integrated-gradient analysis revealed a recurrent candidate region on Sus scrofa chromosome 13 across three lipid traits, and masking the top-attributed features reduced predictive performance more than a marker-count-matched random control for HDL-C, LDL-C and TG, whereas masking increased test-set PCC for TCHOL. This work establishes forward-validation benchmarks across three pig datasets and reports results to inform model selection and region prioritization in pig breeding.