Title: Gene regulatory networks optimisation method based on joint evaluation of network structure and node attribute

Authors: Luxuan Qu; Junchang Xin; Yinghui Xiang; Mingcan Wang; Zhiqiong Wang

Addresses: School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China; Ara Institute of Canterbury International Engineering College, Shenyang Jianzhu University, Shenyang, Liaoning, China ' School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China ' Ara Institute of Canterbury International Engineering College, Shenyang Jianzhu University, Shenyang, Liaoning, China ' School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China ' College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China

Abstract: Accurately modelling gene regulatory networks (GRNs) is essential for revealing the mechanisms of disease development. However, existing methods often include false positive edges, reducing model accuracy. Current optimisation algorithms, primarily focusing on removing triangular structure edges, tend to ignore many redundant edges and sometimes delete correct ones due to improper parameter settings. This paper introduces a GRNs optimisation based on joint evaluation of network structure and node attribute. The approach addresses redundancy in both triangular and mutual structures, allowing for the identification of more redundant edges. By incorporating global node attribute, the method limits the removal of correct regulatory edges. This joint evaluation ensures that only the truly redundant relationships are deleted. Experimental results demonstrated that NSNA achieved an overall nearly 7% improvement both in F1-score and AUC compared to modelling method without optimisation. The approach offers potential benefits for advancing disease research and improving network modelling.

Keywords: gene regulatory networks; joint evaluation; network structure; node attribute; redundancy relationships.

DOI: 10.1504/IJSPM.2024.146005

International Journal of Simulation and Process Modelling, 2024 Vol.21 No.4, pp.227 - 237

Received: 01 Oct 2024
Accepted: 15 Nov 2024
Published online: 01 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article