Accurate genomic prediction of complex phenotypes is crucial for accelerating genetic progress in swine breeding. However, conventional methods like Genomic Best Linear Unbiased Prediction (GBLUP) face limitations in capturing complex non-additive effects that contribute significantly to phenotypic variation, restricting the potential accuracy of phenotype prediction. To address this challenge, we introduce a novel framework based on a self-supervised, pre-trained encoder-only Transformer model. Its core novelty lies in tokenizing SNP sequences into non-overlapping 6-mers (sequences of 6 SNPs), enabling the model to directly learn local haplotype patterns instead of treating SNPs as independent markers. The model first undergoes self-supervised pre-training on the unlabeled version of the same SNP dataset used for subsequent fine-tuning, learning intrinsic genomic representations through a masked 6-mer prediction task. Subsequently, the pre-trained model is fine-tuned on labeled data to predict phenotypic values for specific economic traits. Experimental validation demonstrates that our proposed model consistently outperforms baseline methods, including GBLUP and a Transformer of the same architecture trained from scratch (without pre-training), in prediction accuracy across key economic traits. This outperformance suggests the model’s capacity to capture non-linear genetic signals missed by linear models. This research contributes not only a new, more accurate methodology for genomic phenotype prediction but also validates the potential of self-supervised learning to decipher complex genomic patterns for direct application in breeding programs. Ultimately, this approach offers a powerful new tool to enhance the rate of genetic gain in swine production by enabling more precise selection based on predicted phenotypes.

Deep learning-based morphometric analysis of zebrafish is widely utilized for non-destructively identifying abnormalities and diagnosing diseases. However, obtaining discriminative and continuous organ category decision boundaries poses a significant challenge by directly observing zebrafish larvae from the outside. To address this issue, this study simplifies the organ areas to polygons and focuses solely on the endpoint positioning. Specifically, we introduce a deep learning-based feature endpoint detection method for quantitatively determining zebrafish larvae’s essential phenotype and organ features. We propose the cross-shaped heat tensor network (CSHT-Net), a feature point detection framework consisting of a novel keypoint training method named cross-shaped heat tensor and a feature extractor called combinatorial convolutional block. Our model alleviates the problem of the heatmap-based method that restricts attention to local regions around key points while enhancing the model’s ability to learn continuous, strip-like features. Moreover, we compiled a dataset of 4389 bright-field micrographs of zebrafish larvae at 120 h post-fertilization for the model training and algorithm evaluation of zebrafish phenotypic traits. The proposed framework achieves an average precision (AP) of 83.2% and an average recall (AR) of 85.8%, outperforming multiple widely adopted keypoint detection techniques. This approach enables robust phenotype extraction and reliable morphometric analysis for zebrafish larvae, fostering efficient hazard identification for chemicals and medical products.

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.