An Ontology-Based Hierarchical Bayesian Network Classification Model to Predict the Effect of Dna Repairs Genes in Human Ageing Process

Abstract

Conventional Data Mining (DM) algorithms treated data simply as numbers ignoring the semantic relationships among them. Consequently, recent researches claimed that ontology is the best option to represent the domain knowledge for data mining use because of its structural format. Additionally, it is reported that ontology can facilitate different steps in the Bayesian Network (BN) construction task. To this end, this paper investigates the advantages of consolidating the Gene Ontology (GO) and the Hierarchical Bayesian Network (HBN) classifier in a flexible framework, which preserves the advantages of both, ontology and Bayesian theory. The proposed Semantically Aware Hierarchical Bayesian Network (SAHBN) is tested using data set in the biomedical domain. DNA repair genes are classified as either ageing-related or nonageing-related based on their GO biological process terms. Furthermore, the performance of SAHBN was compared against eight conventional classification algorithms. Overall, SAHBN has outperformed existing algorithms in eight experiments out of eleven.