BNIMI: Boolean Gene Regulatory Network Inference Based on Mutual Information

Citation

Barman, Shohag and Al Farid, Fahmid and Sarker, Md. Tanjil and Hafiz, Md Ferdous and Khan, Niaz Ashraf and Gope, Hira Lal and Abdul Karim, Hezerul and Mansor, Sarina and Bari, Ahsanul (2024) BNIMI: Boolean Gene Regulatory Network Inference Based on Mutual Information. In: 2024 Multimedia University Engineering Conference (MECON), 23-25 July 2024, Cyberjaya, Malaysia.

[img] Text
BNIMI_ Boolean Gene Regulatory Network Inference Based on Mutual Information.pdf - Published Version
Restricted to Repository staff only

Download (353kB)

Abstract

Network inference is a challenging task in Bioinformatics. Numerous network inference approaches have been proposed, but most of them face scalability challenges when inferring a gene regulatory network because they typically limit the regulatory gene within a range of 1 to 3. Our solution to this issue is the BNIMI network inference approach, which uses mutual information to infer a gene regulatory network. The pairwise mutual information between a target gene and a regulatory gene is computed in the BNIMI. The regulatory and target gene pair is taken into consideration in the gene regulatory network if the mutual information surpasses a large threshold value. We do 100 random shuffles on the time series gene expression data to find the highest mutual information for each target gene in order to establish the threshold value. This maximum value is then considered as the threshold. We tested BNIMI against two popular existing methods (Context Likelihood Relatedness and REVEAL) by running numerous simulations on both artificial and real gene expression data. Our findings show that BNIMI significantly outperforms these established methods in both types of datasets. This means BNIMI is a powerful and effective tool for figuring out how genes regulate each other based on time-series gene expression information.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Network inference, Gene regulatory network, random Boolean network, Gene expression data
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 06 Feb 2025 06:41
Last Modified: 06 Feb 2025 06:41
URII: http://shdl.mmu.edu.my/id/eprint/13366

Downloads

Downloads per month over past year

View ItemEdit (login required)