Use of known gene-gene interactions in S-system based GRN inference

Conference Contribution ResearchOnline@JCU
Gill, Jaskaran;Chetty, Madhu;Shatte, Adrian;Hallinan, Jennifer
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.

Journal

N/A

Publication Name

CIBCB 2021: 18th IEEE International Conference in Computational Intelligence in Bioinformatics and Computational Biology

Volume

N/A

ISBN/ISSN

978-0-908026-67-8

Edition

N/A

Issue

N/A

Pages Count

2

Location

Melbourne, Australia

Publisher

Federation University Australia

Publisher Url

N/A

Publisher Location

Melbourne, VIC, Australia

Publish Date

N/A

Url

N/A

Date

N/A

EISSN

N/A

DOI

N/A