Knowledge based framework for genetic disease diagnosis using data mining technique

Gene Ontology is a structured repository of concepts that are associated to one or more gene products. The Gene Ontology describes gene products in terms of their associated biological processes, cellular components and molecular functions in a species-independent manner. There are different approaches available to discover the biologically relevant associations between terms of Gene Ontology. Multiple genomic and proteomic semantic annotations scattered in many distributed and heterogeneous data sources such heterogeneity and dispersion hamper the biologists’ ability of asking global queries and performing global evaluations. To overcome this problem, we developed a knowledge based framework to create and maintain a Genomic and Proteomic Knowledge Base, which integrates several of the most relevant sources. We have developed an approach using Multi-Ontology data mining at All Levels (MOAL) to mine cross-ontology association rules, i.e. rules that involve Gene Ontology terms present in its sub-ontologies for identifying the gene attacked disease.