GATv2EPI: Predicting Enhancer-Promoter Interactions with a Dynamic Graph Attention Network.
Tianjiao Zhang1, Xingjie Zhao1, Hao Sun1
1College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
Genes
|January 8, 2025
Summary
This study introduces GATv2EPI, a novel graph neural network framework that accurately predicts enhancer-promoter interactions (EPIs), including complex one-to-many and many-to-many patterns, significantly improving gene regulatory network analysis.
Area of Science:
- Genomics
- Computational Biology
- Molecular Biology
Background:
- Enhancer-promoter interactions (EPIs) are crucial for gene regulation and understanding gene expression complexity.
- Traditional EPI prediction methods often overlook complex one-to-many and many-to-many interactions.
- Graph neural networks offer a powerful approach to model intricate regulatory relationships.
Purpose of the Study:
- To develop a novel framework for predicting enhancer-promoter interactions (EPIs).
- To capture complex EPI patterns, including one-to-one, one-to-many, and many-to-many interactions.
- To improve the accuracy and efficiency of EPI prediction using epigenetic data.
Main Methods:
- Introduction of GATv2EPI, a framework utilizing dynamic graph attention neural networks.
- Leveraging epigenetic information from enhancers, promoters, and surrounding regions.
- Employing a connectivity-based sampling method for dataset partitioning to prevent data leakage and ensure robust model training.
Main Results:
- GATv2EPI demonstrated superior accuracy in recognizing EPIs across four cell lines (NHEK, IMR90, HMEC, K562).
- Achieved a significant 95.29% improvement in training time compared to the TransEPI method.
- Validated the model's effectiveness in capturing complex topological structures in gene regulatory networks.
Conclusions:
- GATv2EPI enhances EPI prediction accuracy by effectively modeling complex topological information within gene regulatory networks.
- The study highlights the critical role of epigenetic features in the vicinity of enhancers and promoters for accurate EPI prediction.
- The developed framework offers a more comprehensive approach to understanding gene regulation.
Related Concept Videos
02:26Protein Networks
3.9K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
3.9K
02:40The Eukaryotic Promoter Region
2.9K
2.9K
02:04Protein-protein Interfaces
12.4K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.4K
01:49Conserved Binding Sites
4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K
01:09Epistasis Analysis
4.9K
Although Mendel chose seven unrelated traits in peas to study gene segregation, most traits involve multiple gene interactions that create a spectrum of phenotypes. When the interaction of various genes or alleles at different locations influences a phenotype, this is called epistasis. Epistasis often involves one gene masking or interfering with the expression of another (antagonistic epistasis). Epistasis often occurs when different genes are part of the same biochemical pathway. The...
4.9K