Bo Gao

Background: The enhancer–promoter interaction (EPI) is a critical component of gene regulatory networks, playing a significant role in understanding the complexity of gene expression. Traditional EPI prediction methods focus on one-to-one interactions, neglecting more complex one-to-many and many-to-many patterns. To address this gap, we utilize graph neural networks to comprehensively explore all interaction patterns between enhancers and promoters, capturing complex regulatory relationships for more accurate predictions. Methods: In this study, we introduce a novel EPI prediction framework, GATv2EPI, based on dynamic graph attention neural networks. GATv2EPI leverages epigenetic information from enhancers, promoters, and their surrounding regions and organizes interactions into a network to comprehensively explore complex EPI regulatory patterns, including one-to-one, one-to-many, and many-to-many relationships. To avoid overfitting and ensure diverse data representation, we implemented a connectivity-based sampling method for dataset partitioning, which constructs graphs for each chromosome and assigns entire connected subgraphs to training or test sets, thereby preventing information leakage and ensuring comprehensive chromosomal representation. Results: In experiments conducted on four cell lines—NHEK, IMR90, HMEC, and K562—GATv2EPI demonstrated superior EPI recognition accuracy compared to existing similar methods, with a training time improvement of 95.29% over TransEPI. Conclusions: GATv2EPI enhances EPI prediction accuracy by capturing complex topological structure information from gene regulatory networks through graph neural networks. Additionally, our results emphasize the importance of epigenetic features surrounding enhancers and promoters in EPI prediction.

The rapid advancement of spatial transcriptomics (ST) sequencing technology has made it possible to capture gene expression with spatial coordinate information at the cellular level. Although many methods in ST data analysis can detect spatially variable genes (SVGs), these methods often fail to identify genes with explicit spatial expression patterns due to the lack of consideration for spatial domains. Considering spatial domains is crucial for identifying SVGs as it focuses the analysis of gene expression changes on biologically relevant regions, aiding in the more accurate identification of SVGs associated with specific cell types. Existing methods for identifying SVGs based on spatial domains predefine spot similarity before training, which prevents adaptive learning and limits generalizability across different tissues or samples. This limitation may also lead to inaccurate identification of specific genes at boundary regions. To address these issues, we present GAADE, an unsupervised neural network architecture based on graph-structured data representation learning. GAADE stacks encoder/decoder layers and integrates a self-attention mechanism to reconstruct node attributes and graph structure, effectively capturing spatial domain structures of different sections. Consequently, we confine the identification of SVGs within spatial domains. By performing differential expression analysis on spots within the target spatial domain and their multi-order neighbors, GAADE detects genes with enriched expression patterns within defined domains. Comparative evaluations with five other popular methods on ST datasets across four different species, regions and tissues demonstrate that GAADE exhibits superior performance in detecting SVGs and capturing the extent of spatial gene expression variation.

Structural variation (SV) is an important form of genomic variation that influences gene function and expression by altering the structure of the genome. Although long-read data have been proven to better characterize SVs, SVs detected from noisy long-read data still include a considerable portion of false-positive calls. To accurately detect SVs in long-read data, we present SVDF, a method that employs a learning-based noise filtering strategy and an SV signature-adaptive clustering algorithm, for effectively reducing the likelihood of false-positive events. Benchmarking results from multiple orthogonal experiments demonstrate that, across different sequencing platforms and depths, SVDF achieves higher calling accuracy for each sample compared to several existing general SV calling tools. We believe that, with its meticulous and sensitive SV detection capability, SVDF can bring new opportunities and advancements to cutting-edge genomic research.

The heterogeneity of tumors poses a challenge for understanding cell interactions and constructing complex ecosystems within cancer tissues. Current research strategies integrate spatial transcriptomics (ST) and single-cell sequencing (scRNA-seq) data to thoroughly analyze this intricate system. However, traditional deep learning methods using scRNA-seq data tend to filter differentially expressed genes through statistical methods. In the context of cancer tissues, where cancer cells exhibit significant differences in gene expression compared to normal cells, this heterogeneity renders traditional analysis methods incapable of accurately capturing differences between cell types. Therefore, we propose a graph-based deep learning method, GTADC, which utilizes Silhouette scores to precisely capture genes with significant expression differences within each cell type, enhancing the accuracy of gene selection. Compared to traditional methods, GTADC not only considers the expression similarity of genes within their respective clusters but also comprehensively leverages information from the overall clustering structure. The introduction of graph structure effectively captures spatial relationships and topological structures between the two types of data, enabling GTADC to more accurately and comprehensively resolve the spatial composition of different cell types within tissues. This refinement allows GTADC to intricately reconstruct the cellular spatial composition, offering a precise solution for inferring cell spatial composition. This method allows for early detection of potential cancer cell regions within tissues, assessing their quantity and spatial information in cell populations. We aim to achieve a preliminary estimation of cancer occurrence and development, contributing to a deeper understanding of early-stage cancer and providing potential support for early cancer diagnosis.