GRLGRN: graph representation-based learning to infer gene regulatory networks from single-cell RNA-seq data

被引：0

作者：

Kai Wang ^{[1
]}

Yulong Li ^{[1
]}

Fei Liu ^{[1
]}

Xiaoli Luan ^{[1
]}

Xinglong Wang ^{[2
]}

Jingwen Zhou ^{[3
]}

机构：

[1] Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, 1800 Lihu Road, Jiangsu, Wuxi

[2] Science Center for Future Foods, Jiangnan University, 1800 Lihu Road, Jiangsu, Wuxi

[3] Key Laboratory of Industrial Biotechnology, Ministry of Education and School of Biotechnology, Jiangnan University, 1800 Lihu Road, Jiangsu, Wuxi

[4] Engineering Research Center of Ministry of Education on Food Synthetic Biotechnology, Jiangnan University, 1800 Lihu Road, Jiangsu, Wuxi

[5] Jiangsu Province Engineering Research Center of Food Synthetic Biotechnology, Jiangnan University, 1800 Lihu Road, Jiangsu, Wuxi

来源：

BMC Bioinformatics | / 26卷 / 1期

基金：

中国博士后科学基金; 中国国家自然科学基金;

关键词：

Gene expression data; Gene regulatory network; Graph representation learning; Implicit links;

D O I：

10.1186/s12859-025-06116-1

中图分类号：

学科分类号：

摘要：

Background: A gene regulatory network (GRN) is a graph-level representation that describes the regulatory relationships between transcription factors and target genes in cells. The reconstruction of GRNs can help investigate cellular dynamics, drug design, and metabolic systems, and the rapid development of single-cell RNA sequencing (scRNA-seq) technology provides important opportunities while posing significant challenges for reconstructing GRNs. A number of methods for inferring GRNs have been proposed in recent years based on traditional machine learning and deep learning algorithms. However, inferring the GRN from scRNA-seq data remains challenging owing to cellular heterogeneity, measurement noise, and data dropout. Results: In this study, we propose a deep learning model called graph representational learning GRN (GRLGRN) to infer the latent regulatory dependencies between genes based on a prior GRN and data on the profiles of single-cell gene expressions. GRLGRN uses a graph transformer network to extract implicit links from the prior GRN, and encodes the features of genes by using both an adjacency matrix of implicit links and a matrix of the profile of gene expression. Moreover, it uses attention mechanisms to improve feature extraction, and feeds the refined gene embeddings into an output module to infer gene regulatory relationships. To evaluate the performance of GRLGRN, we compared it with prevalent models and performed ablation experiments on seven cell-line datasets with three ground-truth networks. The results showed that GRLGRN achieved the best predictions in AUROC and AUPRC on 78.6% and 80.9% of the datasets, and achieved an average improvement of 7.3% in AUROC and 30.7% in AUPRC. The interpretation discussion and the network visualization were conducted. Conclusions: The experimental results and case studies illustrate the considerable performance of GRLGRN in predicting gene interactions and provide interpretability for the prediction tasks, such as identifying hub genes in the network and uncovering implicit links. © The Author(s) 2025.

引用

共 49 条

[1]

Cramer P., Organization and regulation of gene transcription, Nature, 573, 7772, pp. 45-54, (2019)

[2]

Mao G., Zeng R., Peng J., Et al., Reconstructing gene regulatory networks of biological function using differential equations of multilayer perceptrons, BMC Bioinform, 23, 1, (2022)

[3]

Li X., Ma S., Guo F., Et al., Inferring gene regulatory network via fusing gene expression image and RNA-seq data, Bioinformatics, 38, 6, pp. 1716-1723, (2022)

[4]

Ma B., Fang M., Jiao X., Inference of gene regulatory networks based on nonlinear ordinary differential equations, Bioinformatics, 36, 19, pp. 4885-4893, (2020)

[5]

Shu H., Zhou J., Ma J., Et al., Modeling gene regulatory networks using neural network architectures, Nat Comput Sci, 1, 7, pp. 491-501, (2021)

[6]

Van De Sande B., Flerin C., Davie K., Et al., A scalable SCENIC workflow for single-cell gene regulatory network analysis, Nat Protoc, 15, 7, pp. 2247-2276, (2020)

[7]

Zhang C., Lu Y., Zang T., CNN-DDI: a learning-based method for predicting drug-drug interactions using convolution neural networks, BMC Bioinform, 23, (2022)

[8]

Zhao M., He W., Guo F., Et al., A comprehensive overview and critical evaluation of gene regulatory network inference technologies, Briefings Bioinform, 22, 5, (2021)

[9]

Delgado-Chaves F.M., Gomez-Vela F., Divina F., Et al., Computational analysis of the global effects of Ly6E in the immune response to coronavirus infection using gene networks, Genes, 11, 7, (2020)

[10]

Osterberg L., Domenzain I., Munch J., Et al., A novel yeast hybrid modeling framework integrating Boolean and enzyme-constrained networks enables exploration of the interplay between signaling and metabolism, PLoS Comput Biol, 17, 4, (2021)

← 1 2 3 4 5 →