An Ontology Based Hierarchical Bayesian Network Classification Model to Predict The Effect of DNA Repairs Genes in Human Ageing Process

摘要

Conventional Data Mining (DM) algorithms treated data simply as numbers ignoring thesemantic relationships among them. Consequently, recent researches claimed that ontology isthe best option to represent the domain knowledge for data mining use because of its structuralformat. Additionally, it is reported that ontology can facilitate different steps in the BayesianNetwork (BN) construction task. To this end, this paper investigates the advantages ofconsolidating the Gene Ontology (GO) and the Hierarchical Bayesian Network (HBN) classifierin a flexible framework, which preserves the advantages of both, ontology and Bayesian theory.The proposed Semantically Aware Hierarchical Bayesian Network (SAHBN) is tested using dataset 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 ofSAHBN was compared against eight conventional classification algorithms. Overall, SAHBNhas outperformed existing algorithms in eight experiments out of eleven.