The development of omics techniques has increased the number of functional genomic annotations, making it possible to leverage this information in statistical models to improve genomic prediction performance. However, it remains challenging to effectively use the variety of functional annotations available. Here, we develop an adaptive model we call IFAM, which extends the linear mixed model with multiple random effects to accommodate a greater number of types of functional annotations to improve prediction accuracy for complex traits. The IFAM yields improvements in prediction accuracy across diverse datasets compared to the GBLUP model, achieving an average improvement of 9.46%, 6.15%, 4.59%, 4.09%, and 10.83% in the WTCCC1, UK Biobank, Duroc pig, Yorkshire pig and rice datasets, respectively. Notably, excluding trait-specific GWAS-derived annotations, functional annotations alone yielded a 1.40% predictive gain for the UK Biobank dataset but only marginal improvements in livestock and crop datasets. This suggests that the effectiveness of multi-omics information is constrained by species-specific annotation quality, tissue and trait relevance, and the limited resolution of existing functional datasets. As functional genomics resources continue to expand, their integration is expected to provide increasing benefits for genomic prediction.

Genomic selection has become a widely adopted and effective breeding technology for modern genetic improvements in pigs. However, the core model currently used in genetic evaluation is primarily based on a linear mixed model, which accounts for only additive genetic effects. Non-additive effects and complex nonlinear interactions among genes or loci are often neglected, leaving substantial potential for improving the predictive ability of traits. To address this limitation, we here propose a Multi-omics Annotation and Residual Split strategy-based deep learning model (MARS). Through comprehensive comparisons and evaluations against various linear and nonlinear models across multiple pig traits, we demonstrate that the residual split indirect strategy effectively mitigates overfitting and underfitting issues commonly observed in deep learning models, thereby enhancing predictive accuracy for complex traits. Moreover, by incorporating multi-omics annotation information within a hierarchical feature selection procedure, our results show that it improves computational efficiency without significant sacrifices in prediction performance. It is foreseeable that our developed MARS would facilitate the application of artificial intelligence technology and the publicly available big omics data in the coming future of pig breeding.

Image retrieval system (IRS) is commonly used in E-Commerce platforms for a wide range of applications such as price comparison and commodity recommendation. However, customers may experience inconsistent retrieval problems. Although the retrieved image contains the query object, the main product of the retrieved image is not associated with the query product. This is caused by the wrong product instance location when building the product image retrieval library. We can easily determine which product is on sale through the hint of the title, so we propose Text-Guided MuliModal Product Location (TMML) to use additional product titles to assist in locating the actual selling product instance. We design a weakly-aligned region-text data collection method to generate region-text pseudo-label by utilizing the IRS and user behavior from the E-commerce platform. To mitigate the impact of data noise, we propose a Mutual-Aware Contrastive Loss. Our results show that the proposed TMML outperforms the state-of-the-art method GLIP [11] by 3.95% in top-1 precision on our multi-objects test set, and 2.53% error located images in AliExpress has been corrected, which greatly alleviates the retrieval inconsistencies in IRS.

The genotype-phenotype gap is a persistent barrier to complex trait genetic dissection, worsened by the explosive growth of genomic data (1.5 billion variants identified in the UK Biobank WGS study) alongside persistently scarce and subjective human-defined phenotypes. Digital phenotyping offers a potential solution, yet existing tools fail to balance scalable non-manual phenotype generation and biological interpretability of these quantitative traits. Here we report AIPheno, the first generative AI-driven "phenotype sequencer" that bridges this gap. It enables high-throughput, unsupervised extraction of digital phenotypes from imaging data and unlocks their biological meaning via generative network analysis. AIPheno transforms imaging modalities into a rich source of quantitative traits, dramatically enhancing cross-species genetic discovery, including novel loci such as CCBE1 (humans), KITLG-TMTC3 (domestic pigeons), and SOD2-IGF2R (swine). Critically, its generative module decodes AI-derived phenotypes by synthesizing variant-specific images to yield actionable biological insights. For example, it clarifies how the OCA2-HERC2 locus pleiotropically links pigmentation to retinal vascular traits via vascular visibility modulation. Integrating scalable non-manual phenotyping, enhanced genetic discovery power, and generative mechanistic decoding, AIPheno establishes a transformative closed-loop paradigm. This work addresses the longstanding genotype-phenotype imbalance, redefines digital phenotype utility, and accelerates translation of genetic associations into actionable understanding with profound implications for human health and agriculture.