No abstract

Abstract-Cloud infrastructures promise to provide highperformance and cost-effective solutions to large-scale data processing problems. In this paper, we identify a common class of data-intensive applications for which data transfer latency for uploading data into the cloud in advance of its processing may hinder the linear scalability advantage of the cloud. For such applications, we propose a "stream-as-you-go" approach for incrementally accessing and processing data based on a stream data management architecture. We describe our approach in the context of a DNA sequence analysis use case and compare it against the state of the art in MapReduce-based DNA sequence analysis and incremental MapReduce frameworks. We provide experimental results over an implementation of our approach based on the IBM InfoSphere Streams computing platform deployed on Amazon EC2, showing an order of magnitude improvement in total processing time over the state of the art.

No abstract

Cloud computing provides a promising solution to the genomics data deluge problem resulting from the advent of next-generation sequencing (NGS) technology. Based on the concepts of “resources-on-demand” and “pay-as-you-go”, scientists with no or limited infrastructure can have access to scalable and cost-effective computational resources. However, the large size of NGS data causes a significant data transfer latency from the client's site to the cloud, which presents a bottleneck for using cloud computing services. In this paper, we provide a streaming-based scheme to overcome this problem, where the NGS data is processed while being transferred to the cloud. Our scheme targets the wide class of NGS data analysis tasks, where the NGS sequences can be processed independently from one another. We also provide the elastream package that supports the use of this scheme with individual analysis programs or with workflow systems. Experiments presented in this paper show that our solution mitigates the effect of data transfer latency and saves both time and cost of computation.

No abstract