Cross-Attention Graph Neural Networks for Inferring Gene Regulatory Networks with Skewed Degree Distribution

2024-12-18

AI Summary

In gene regulatory network (GRN) inference, severe degree distribution skew—particularly in in-degree and out-degree—compromises accurate modeling of directed regulatory relationships. To address this, we propose a novel method based on dual complex-valued graph embedding and cross-graph attention. Our approach constructs two separate graphs: a “regulator graph” and a “target graph,” enabling independent modeling of genes’ regulatory capacity and responsiveness within complex-domain graph neural networks. A cross-graph attention mechanism is explicitly incorporated to capture directional regulatory dependencies. The framework is fully differentiable and end-to-end trainable, marking the first systematic mitigation of degree skew interference in directed graph representation learning. Evaluated across multiple human and model organism datasets, our method achieves an average 12.6% improvement in area under the precision–recall curve (AUPR) over state-of-the-art baselines. The implementation is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Social Networks and Social Media: Computational social science

Abstract

Inferencing Gene Regulatory Networks (GRNs) from gene expression data is a pivotal challenge in systems biology, and several innovative computational methods have been introduced. However, most of these studies have not considered the skewed degree distribution of genes. Specifically, some genes may regulate multiple target genes while some genes may be regulated by multiple regulator genes. Such a skewed degree distribution issue significantly complicates the application of directed graph embedding methods. To tackle this issue, we propose the Cross-Attention Complex Dual Graph Embedding Model (XATGRN). Our XATGRN employs a cross-attention mechanism to effectively capture intricate gene interactions from gene expression profiles. Additionally, it uses a Dual Complex Graph Embedding approach to manage the skewed degree distribution, thereby ensuring precise prediction of regulatory relationships and their directionality. Our model consistently outperforms existing state-of-the-art methods across various datasets, underscoring its efficacy in elucidating complex gene regulatory mechanisms. Our codes used in this paper are publicly available at: https://github.com/kikixiong/XATGRN.

Problem

• Gene Regulation
• Network Structure
• Asymmetric Regulation

Innovation

• Cross-Attention Mechanism
• Dual Composite Graph Embedding
• Gene Regulatory Network Prediction