Virtual technology on CPSE-Bio

Explosive growth of biomedical data in various platforms presents a major challenge for bioinformatics research. To analyze the ever-increasing amount of data, it requires unprecedented storage resources and computing power. To maximize the limited resources for big data, we propose a model on Bioinformatics Problem Solving Environment based on Cloud Computing (CPSE-Bio). The proposed technique combines the Hadoop with virtualization technology, allowing each core on multicore computers to be virtualized as a computing node in the Hadoop cluster to take advantage of a common feature of modern processor with multicores. Adding virtualization creates more effective computing nodes in the cluster than the one without, and analysis and experiments demonstrate that our model enhances the resource utilization and computing efficiency in CPSE-Bio.