Data Analysis and Visualization Using HPC and Cloud ABSTRACT BACKGROUND MATERIALS AND METHODS

Our work aims to explore interoperability of large-scale cloud data processing software in HPC environments, and involves clustering and 3D visualization of gene sequence collections. We completed visualizing samples of 100K – 400K fungal sequences. This research involves major supercomputer computation as both clustering and visualization steps scale, even up to the square of the sample size. Our experiments were conducted on Indiana University’s Big Red II [1] supercomputer and in collaboration with bioinformatics and biology faculty at IU. communication by transforming map-reduc