A Distributed Parallel Computing Environment for Bioinformatics Problems

Abstract

Certain bioinformatics research, such as sequence alignment, alternative splicing, protein function/structure prediction, gene identify, bio-chip data analysis, and so on, requires massive computing power, which is hardly available in a single computing node. In order to facilitate bioinformatics research, we have designed and implemented a distributed and parallel computing environment with grid technology, in which, biologists can solve bioinformatics problems using distributed computing resources in parallel and reduce execution time. In this environment, the computing power and program information of computing nodes are described with XML documents. A web service named Local Resource Management Service is deployed on each computing node so that the distributed resources can be accessed in a uniform manner. With an API suite, biologists can use distributed computing resources in parallel easily in their applications. Further more, users can monitor the status of distributed resources dynamically on the portal. A real use case of alternative splicing is also presented, through which we have analyzed the usability, efficiency, and stability of the environment.

Distributed Spatial Data Mining in Geospatial Knowledge Service Grid

“…Fig.2: Execution process of spatial data mining in GeoKSGrid test bed [3] With the development of information technology, the Internet is shifting from an information and communication infrastructure to a knowledge delivery infrastructure [1]. The discovery and extraction of knowledge from geographically distributed sources is increasingly important in many practical uses [1,10]. Although, there are several knowledge discovery systems implemented on parallel and distributed computing platforms to achieve high performance and large scale data analysis that stored at a single site, but they can't handle and analyze multi-site and multiowner data repositories, it is also a big problem for them to combination use of large data set size, geographic distribution of data, users and resources, and computationally intensive analysis demands.…”