Work

KEGNI: knowledge graph enhanced framework for gene regulatory network inference

Year: 2025

Type: article

Abstract: Inference of cell type-specific gene regulatory networks (GRNs) is a fundamental step in investigating complex regulatory mechanisms. Here, we present KEGNI (Knowledge graph-Enhanced Gene regulatory Network Inference), a knowledge-guided framework that employs a graph autoencoder to capture gene regulatory relationships and incorporates a knowledge graph to infer GRNs based on scRNA-seq data. KEGNI shows superior performance compared to multiple methods using scRNA-seq data or paired scRNA-seq and scATAC-seq data. KEGNI can identify driver genes and elucidate the regulatory mechanisms underlying distinct cellular contexts. The modular design of KEGNI supports the integration of various knowledge graphs for context-specific tasks.

Source: Genome biology

DOI: 10.1186/s13059-025-03780-7

Authors: Pengxiao Li, Lin Li, Jingminjie Nan, Jiahuan Chen, Jielin Sun, Yanan Cao

Institutions: Shanghai Jiao Tong University, Ruijin Hospital

Language: English

Topic: Gene Regulatory Network Analysis

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $5,490

Funders: National Natural Science Foundation of China, Shanghai Jiao Tong University, National Science and Technology Major Project, National Key Research and Development Program of China