Authors: Zoheir Ezziane
Addresses: Applied Science and Technology, Women's College, Higher Colleges of Technology, P.O. 17258, Al-Ain, UAE
Abstract: The wealth of available datasets in genomics and proteomics has spawned a corresponding interest in knowledge discovery methods that enable researchers to attain substantial biological meanings pertaining to model various human diseases. The scale and complexity of these datasets give rise to important challenges in data management and analysis. This paper aims at designing a framework that helps researchers to better conduct data analysis through seamless biological data integration from various literature and online databases. A rule-based program is designed and implemented to access the GO database and retrieve datasets related to apoptosis. An advanced relational learning method is employed to infer causal relationships between the retrieved datasets. As a result, this framework aims at providing a level of query processing beyond even some high-profile websites. This will lead to an improved understanding of the pathogenesis of a certain disease and eventually to its therapy. In addition, this work also provides a comprehensive picture of biological processes, gene functions and protein properties that may detect disease patterns and lead to novel disease concepts.
Keywords: medical knowledge discovery; novel disease concepts; disease patterns; signal transduction; signalling pathways; metabolic networks; apoptosis; relational reasoning; bio-inspired computing; biomedical discovery; biomedical knowledge; knowledge discovery systems; data analysis; biological data integration; gene functions; protein properties; knowledge management.
International Journal of Bio-Inspired Computation, 2010 Vol.2 No.1, pp.65 - 70
Available online: 03 Dec 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article