HGATLink: single-cell gene regulatory network inference via the fusion of heterogeneous graph attention networks and transformer.

ABSTRACT:

Background

Gene regulatory networks (GRNs) involve complex regulatory relationships between genes and play important roles in the study of various biological systems and diseases. The introduction of single-cell sequencing (scRNA-seq) technology has allowed gene regulation studies to be carried out on specific cell types, providing the opportunity to accurately infer gene regulatory networks. However, the sparsity and noise problems of single-cell sequencing data pose challenges for gene regulatory network inference, and although many gene regulatory network inference methods have been proposed, they often fail to eliminate transitive interactions or do not address multilevel relationships and nonlinear features in the graph data well.

Results

On the basis of the above limit

SUBMITTER: Sun Y 

PROVIDER: S-EPMC11817978 | biostudies-literature | 2025 Feb

REPOSITORIES: biostudies-literature