ePrints

scBPGRN: Integrating single-cell multi-omics data to construct gene regulatory networks based on BP neural network

Lookup NU author(s): Tao Ding

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

© 2022 Elsevier LtdThe deterioration and metastasis of cancer involve various aspects of genomic changes, including genomic DNA changes, epigenetic modifications, gene expression, and other complex interactions. Therefore, integrating single-cell multi-omics data to construct gene regulatory networks containing more omics information is of great significance for understanding the pathogenesis of cancer. In this article, an algorithm integrating single-cell RNA sequencing data and DNA methylation data to construct a gene regulatory network based on the back-propagation (BP) neural network (scBPGRN) is proposed. This algorithm uses biweight extreme correlation coefficients to measure the correlation between factors and uses neural networks to calculate generalized weights to construct gene regulation networks. Finally, the node strength is calculated to identify the genes associated with cancer. We apply the scBPGRN algorithm to hepatocellular carcinoma (HCC) data. We construct a regulatory network and identify top-ranked genes, such as MYCBP, KLHL35, PRKCZ, and SERPINA6, as the key HCC-related genes. We analyze the top 100 genes, and the HCC-related genes are concentrated in the top 20. In addition, the single cell data is found to consist of two subpopulations. We also apply scBPGRN to two subpopulations. We analyze the top 50 genes in them, and the HCC-related genes are concentrated in the top 20. The consequences of functional enrichment analysis indicate that the gene regulatory network we have constructed is valid. Our results have been verified in several pieces of literature. This study provides a reference for the integration of single-cell multi-omics data to construct gene regulatory networks.

Publication metadata

Author(s): Xuan C, Wang Y, Zhang B, Wu H, Ding T, Gao J

Publication type: Article

Publication status: Published

Journal: Computers in Biology and Medicine

Year: 2022

Volume: 151

Issue: A

Online publication date: 28/10/2022

Acceptance date: 22/10/2022

ISSN (print): 0010-4825

ISSN (electronic): 1879-0534

Publisher: Elsevier Ltd

URL: https://doi.org/10.1016/j.compbiomed.2022.106249

DOI: 10.1016/j.compbiomed.2022.106249

Altmetrics

Share