Title: Determination of relationships among cancer-related genes using Bayesian networks
Authors: Michael Kofi Ahenkan; Emmanuel S. Adabor; Kwaku F. Darkwah
Addresses: Department of Mathematics, Kwame Nkrumah University of Science and Technology, P.O. Box BP 56, Kumasi, Ghana ' School of Technology, Ghana Institute of Management and Public Administration, P.O. Box AH 50, Achimota, Accra, Ghana ' Department of Mathematics, Kwame Nkrumah University of Science and Technology, P.O. Box BP 56, Kumasi, Ghana
Abstract: A network of relationships among cancer-related genes can be reconstructed from high-throughput datasets obtained by deoxyribonucleic acid (DNA) micro-array technologies. However, modelling such biological networks is challenged by the nature of data and the complexities of relationships among biological variables such as genes. In this paper, Bayesian networks are applied to predict novel regulatory relationships among genes in cancer from genomic datasets. The performances of the methods were assessed by standard metrics such as sensitivities and specificities. Furthermore, in order to validate and verify the reliability of the new predicted relationships among the genes, some of the results were examined with experimentally confirmed relationships found by previous research. Interestingly, some predicted regulatory relationships were also found in the literature. This enhances confidence in the newly predicted network of regulatory relationships, which could become hypotheses for further research.
Keywords: gene relationships; regulatory networks; Bayesian network; search techniques; cancer; Bayes theorem; gene network inference; causal networks; genomic data analysis; DNA micro-array technologies.
DOI: 10.1504/IJCBDD.2022.126989
International Journal of Computational Biology and Drug Design, 2022 Vol.15 No.2, pp.139 - 154
Accepted: 20 Jun 2022
Published online: 16 Nov 2022 *