Signed graphs are powerful models for representing complex relations with both positive and negative connections. Recently, Signed Graph Neural Networks (SGNNs) have emerged as potent tools for analyzing such graphs. To our knowledge, no prior research has been conducted on devising a training plan specifically for SGNNs. The prevailing training approach feeds samples (edges) to models in a random order, resulting in equal contributionsfrom each sample during the training process, but fails to account for varying learning difficulties based on the graph's structure. We contend that SGNNs can benefit from a curriculum that progresses from easy to difficult, similar to human learning. The main challenge is evaluating the difficulty of edges in a signed graph. Weaddress this by theoretically analyzing the difficulty of SGNNs in learning adequate representations for edges in unbalanced cycles and propose a lightweight difficulty measurer. This forms the basis for our innovative Curriculum representation learning framework for Signed Graphs, referred to as CSG. The process involves using the measurer to assign difficulty scores to training samples, adjusting their order using a scheduler and training the SGNN model accordingly. We empirically our approach on six real-world signed graph datasets. Our method demonstrates remarkable results, enhancing the accuracy of popular SGNN models by up to 23.7 % and showing a reduction of 8.4 % in standard deviation, enhancing model stability. Our implementation is available in PyTorch (https://github.com/Alex-Zeyu/CSG).

Signed Graph Neural Networks (SGNNs) have been shown to be effective in analyzing complex patterns in real-world situations where positive and negative links coexist. However, SGNN models suffer from poor explainability, which limit their adoptions in critical scenarios that require understanding the rationale behind predictions. To the best of our knowledge, there is currently no research work on the explainability of the SGNN models. Our goal is to address the explainability of decision-making for the downstream task of link sign prediction specific to signed graph neural networks. Since post-hoc explanations are not derived directly from the models, they may be biased and misrepresent the true explanations. Therefore, in this paper we introduce a Self-Explainable Signed Graph transformer (SE-SGformer) framework, which can not only outputs explainable information while ensuring high prediction accuracy. Specifically, we propose a new Transformer architecture for signed graphs and theoretically demonstrate that using positional encoding based on signed random walks has greater expressive power than current SGNN methods and other positional encoding graph Transformer-based approaches. We construct a novel explainable decision process by discovering the K-nearest (farthest) positive (negative) neighbors of a node to replace the neural network-based decoder for predicting edge signs. These K positive (negative) neighbors represent crucial information about the formation of positive (negative) edges between nodes and thus can serve as important explanatory information in the decision-making process. We conducted experiments on several real-world datasets to validate the effectiveness of SE-SGformer, which outperforms the state-of-the-art methods by improving 2.2% prediction accuracy and 73.1% explainablity accuracy in the best-case scenario.

Addressing global food security demands more efficient crop breeding. While Genomic Selection (GS) accelerates breeding by predicting phenotypes from genomic data, its accuracy is limited by complex trait architectures and environmental dependencies. To overcome these challenges, we propose DPCformer, a deep learning model integrating convolutional neural networks with self-attention to capture nonlinear genotype-phenotype relationships. Evaluated on 13 traits across five crops (maize, cotton, tomato, rice, chickpea) using chromosomally-ordered SNP data processed with 8-dimensional encoding and PMF feature selection, DPCformer demonstrated superior performance. It achieved accuracy improvements of$0.74-2.92 \%$in maize, up to 8.37% in cotton, and remarkable PCC enhancements of 57.35% in tomato and 16.62% in chickpea compared to baselines. These results establish DPCformer as a robust framework for genomic prediction, excelling in accuracy, small-sample performance, and polyploid data processing.

Deep learning-based AI models have been extensively applied in genomics, achieving remarkable success across diverse applications. As these models gain prominence, there exists an urgent need for interpretability methods to establish trustworthiness in model-driven decisions. For genetic researchers, interpretable insights derived from these models hold significant value in providing novel perspectives for understanding biological processes. Current interpretability analyses in genomics predominantly rely on intuition and experience rather than rigorous theoretical foundations. In this review, we categorize interpretability methods into input-based and model-based approaches, while critically evaluating their limitations through concrete biological application scenarios. Furthermore, we establish theoretical underpinnings to elucidate the origins of these constraints through formal mathematical demonstrations, aiming to assist genetic researchers in better understanding and designing models in the future. Finally, we provide feasible suggestions for future research on interpretability in the field of genetics.

Positive and negative association prediction between gene and phenotype helps to illustrate the underlying mechanism of complex traits in organisms. The transcription and regulation activity of specific genes will be adjusted accordingly in different cell types, developmental timepoints, and physiological states. There are the following two problems in obtaining the positive/negative associations between gene and phenotype: (1) high-throughput DNA/RNA sequencing and phenotyping are expensive and time-consuming due to the need to process large sample sizes; (2) experiments introduce both random and systematic errors, and, meanwhile, calculations or predictions using software or models may produce noise. To address these two issues, we propose a Contrastive Signed Graph Diffusion Network, CSGDN, to learn robust node representations with fewer training samples to achieve higher link prediction accuracy. CSGDN uses a signed graph diffusion method to uncover the underlying regulatory associations between genes and phenotypes. Then, stochastic perturbation strategies are used to create two views for both original and diffusive graphs. Lastly, a multiview contrastive learning paradigm loss is designed to unify the node presentations learned from the two views to resist interference and reduce noise. We perform experiments to validate the performance of CSGDN in three crop datasets: Gossypium hirsutum, Brassica napus, and Triticum turgidum. The results show that the proposed model outperforms state-of-the-art methods by up to 9. 28% AUC for the prediction of link sign in the G. hirsutum dataset. The source code of our model is available at https://github.com/Erican-Ji/CSGDN.

SUMMARY: TAD boundaries are essential for organizing the chromatin spatial structure and regulating gene expression in eukaryotes. However, for large-scale pan-3D genome research, identifying conserved and specific TAD boundaries across different species or individuals is computationally challenging. Here, we present Tcbf, a rapid and powerful Python/R tool that integrates gene synteny blocks and homologous sequences to automatically detect conserved and specific TAD boundaries among multiple species, which can efficiently analyze huge genome datasets, greatly reduce the computational burden and enable pan-3D genome research. AVAILABILITY AND IMPLEMENTATION: Tcbf is implemented by Python/R and is available at https://github.com/TcbfGroup/Tcbf under the MIT license.