Knowledge discovery in biomedical research and drug design : The development and application of biological databases

Abstract

Biological information grows dramatically both in size and diversity in recent years. Databases are developed to store and distribute information worldwide. It has become a routine procedure for the researchers to search of specific biological databases to address some questions before expensive experiments are carried out. In this work, two biological databases were created to meet the research interests of different communities: the Drug Adverse Reaction Target database (DART) and the Kinetic Data of Biomolecular Interaction database (KDBI). DART intends to provide the comprehensive information about drug adverse effect targets of drugs described in the literature, while KDBI aims at offering experimentally determined kinetic data of bio-molecular interaction such as protein-protein interaction, protein-nucleic acids interaction, etc. Knowledge discovery on these two databases were made to facilitate the drug discovery and biomedical research. Support Vector Machines (SVMs) was also applied for the prediction of drug adverse reaction targets. Finally, a novel drug discovery approach was proposed that drug target databases are able to facilitate drug discovery.