Abstract
The availability of massive amounts of biological data, distributed in various data sources, in conjunction with the need to understand the underlying biological processes of life, has prompted the development of a wide range of data analysis tools, most of which are publicly available through the Internet. However, due to the heterogeneity and complexity of the domain, performing a specific analysis by combining tools is complicated. In this paper, we argue that the software agent metaphor constitutes a flexible approach that efficiently addresses integration of bioinformatics analysis tools and dynamic composition-execution of data analysis workflows. To substantiate this assertion, a scalable engineering methodology is presented, aiming to address horizontal and/or vertical integration, through functionally related multiagent systems. The proposed approach is mediator-oriented, relying primarily on agent coordination strategies and semantic domain descriptions. The applicability and virtue of the proposed systems are illustrated through test cases addressing integration of computational gene finders.