Gill, Jaskaran, Chetty, Madhu, Shatte, Adrian, and Hallinan, Jennifer (2021) Use of known gene-gene interactions in S-system based GRN inference. In: Supplemental Proceedings Of Short Papers (Non-peer reviewed) of IEEE CIBCB 2021. pp. 21-22. From: CIBCB 2021: 18th IEEE International Conference in Computational Intelligence in Bioinformatics and Computational Biology, 13-15 October 2021, Melbourne, Australia.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Recent advances in technology have led to substantial increases in the amount of microarray gene expression data available. These data have been used to reconstruct genetic regulatory networks (GRNs) using a variety of different approaches. Of these approaches, de-coupled S-system models and trigonometric differential evolution-based inference processes attempt to reconstruct the complex dynamics of regulatory interactions in a simplified manner. These models require low noise and abundant data to infer GRNs with high accuracy and low computational complexity. However, despite ongoing improvements in technology, the available gene expression data are noisy and limited. Prior knowledge can be used to address these limitations and improve model performance in terms of accuracy and efficiency. In this work, we propose to incorporate knowledge about existing gene-gene interactions to optimize model construction by reducing the search space of the parameters. The method poses no additional computation overhead and leaves room for dealing with falsely induced information. The method will be tested on medium- scale benchmark data with a reduced number of datasets.

Item ID:	81633
Item Type:	Conference Item (Non-Refereed Research Paper)
ISBN:	978-0-908026-67-8
Keywords:	Gene Regulatory Network; S-system Model; Differential evolution; Gene-Gene interaction; Prior knowledge
Date Deposited:	01 May 2024 01:30
FoR Codes:	31 BIOLOGICAL SCIENCES > 3102 Bioinformatics and computational biology > 310201 Bioinformatic methods development @ 50% 31 BIOLOGICAL SCIENCES > 3102 Bioinformatics and computational biology > 310202 Biological network analysis @ 50%
SEO Codes:	28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280102 Expanding knowledge in the biological sciences @ 100%
Downloads:	Total: 1
	More Statistics