MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data

Gene regulatory networks (GRNs) describe the interactions between transcription factors (TFs) and their target genes, playing a crucial role in understanding gene functions and how cells regulate gene expression under different conditions. Recent advancements in multi-omics technologies have provide...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongbo Liu, Hao Chen, Jianxin Wang, Yeru Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Computation
Subjects:
Online Access:https://www.mdpi.com/2079-3197/13/5/124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257916521611264
author Dongbo Liu
Hao Chen
Jianxin Wang
Yeru Wang
author_facet Dongbo Liu
Hao Chen
Jianxin Wang
Yeru Wang
author_sort Dongbo Liu
collection DOAJ
description Gene regulatory networks (GRNs) describe the interactions between transcription factors (TFs) and their target genes, playing a crucial role in understanding gene functions and how cells regulate gene expression under different conditions. Recent advancements in multi-omics technologies have provided new opportunities for more comprehensive GRN inference. Among these data types, gene expression and chromatin accessibility are particularly important, as they are key to distinguishing between direct and indirect regulatory relationships. However, existing methods primarily rely on gene expression data while neglecting biological information such as chromatin accessibility, leading to an increased occurrence of false positives in the inference results. To address the limitations of existing approaches, we propose MultiGNN, a supervised framework based on graph neural networks (GNNs). Unlike conventional GRN inference methods, MultiGNN leverages features extracted from both gene expression and chromatin accessibility data to predict regulatory interactions between genes. Experimental results demonstrate that MultiGNN consistently outperforms other methods across seven datasets. Additionally, ablation studies validate the effectiveness of our multi-omics feature integration strategy, offering a new direction for more accurate GRN inference.
format Article
id doaj-art-cb5ed00281024cab82855e36d47e2ab6
institution OA Journals
issn 2079-3197
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Computation
spelling doaj-art-cb5ed00281024cab82855e36d47e2ab62025-08-20T01:56:17ZengMDPI AGComputation2079-31972025-05-0113512410.3390/computation13050124MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics DataDongbo Liu0Hao Chen1Jianxin Wang2Yeru Wang3School of Information, Beijing Forestry University, Beijing 100083, ChinaSchool of Information, Beijing Forestry University, Beijing 100083, ChinaSchool of Information, Beijing Forestry University, Beijing 100083, ChinaRisk Assessment Division 1, China National Center for Food Safety Risk Assessment, Beijing 100022, ChinaGene regulatory networks (GRNs) describe the interactions between transcription factors (TFs) and their target genes, playing a crucial role in understanding gene functions and how cells regulate gene expression under different conditions. Recent advancements in multi-omics technologies have provided new opportunities for more comprehensive GRN inference. Among these data types, gene expression and chromatin accessibility are particularly important, as they are key to distinguishing between direct and indirect regulatory relationships. However, existing methods primarily rely on gene expression data while neglecting biological information such as chromatin accessibility, leading to an increased occurrence of false positives in the inference results. To address the limitations of existing approaches, we propose MultiGNN, a supervised framework based on graph neural networks (GNNs). Unlike conventional GRN inference methods, MultiGNN leverages features extracted from both gene expression and chromatin accessibility data to predict regulatory interactions between genes. Experimental results demonstrate that MultiGNN consistently outperforms other methods across seven datasets. Additionally, ablation studies validate the effectiveness of our multi-omics feature integration strategy, offering a new direction for more accurate GRN inference.https://www.mdpi.com/2079-3197/13/5/124network inferencegene regulatory networkdeep learning
spellingShingle Dongbo Liu
Hao Chen
Jianxin Wang
Yeru Wang
MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
Computation
network inference
gene regulatory network
deep learning
title MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
title_full MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
title_fullStr MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
title_full_unstemmed MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
title_short MultiGNN: A Graph Neural Network Framework for Inferring Gene Regulatory Networks from Single-Cell Multi-Omics Data
title_sort multignn a graph neural network framework for inferring gene regulatory networks from single cell multi omics data
topic network inference
gene regulatory network
deep learning
url https://www.mdpi.com/2079-3197/13/5/124
work_keys_str_mv AT dongboliu multignnagraphneuralnetworkframeworkforinferringgeneregulatorynetworksfromsinglecellmultiomicsdata
AT haochen multignnagraphneuralnetworkframeworkforinferringgeneregulatorynetworksfromsinglecellmultiomicsdata
AT jianxinwang multignnagraphneuralnetworkframeworkforinferringgeneregulatorynetworksfromsinglecellmultiomicsdata
AT yeruwang multignnagraphneuralnetworkframeworkforinferringgeneregulatorynetworksfromsinglecellmultiomicsdata