A P2P Framework for Developing Bioinformatics Applications in Dynamic Cloud Environments

Bioinformatics is advanced from in-house computing infrastructure to cloud computing for tackling the vast quantity of biological data. This advance enables large number of collaborative researches to share their works around the world. In view of that, retrieving biological data over the internet becomes more and more difficult because of the explosive growth and frequent changes. Various efforts have been made to address the problems of data discovery and delivery in the cloud framework, but most of them suffer the hindrance by a MapReduce master server to track all available data. In this paper, we propose an alternative approach, called PRKad, which exploits a Peer-to-Peer (P2P) model to achieve efficient data discovery and delivery. PRKad is a Kademlia-based implementation with Round-Trip-Time (RTT) as the associated key, and it locates data according to Distributed Hash Table (DHT) and XOR metric. The simulation results exhibit that our PRKad has the low link latency to retrieve data. As an interdisciplinary application of P2P computing for bioinformatics, PRKad also provides good scalability for servicing a greater number of users in dynamic cloud environments.