Azure is leaving its mark in many a field, but one of the biggest contributions of the Microsoft cloud platform may be in genome research. This is an area where sky is the limit.
In all senses of the word!
Medical field genomics is already important in rare diseases, but even smaller hospitals and pathology services are seeing demands for this. Making genome analytics more accessible and affordable is key to opening up new clinical applications.
And the Azure cloud platform is playing its part in this.
As noted, the Australian National University turned to the cloud to take away the administrative overhead of managing HPC devices and accelerate research with more computing power at lower costs.
Azure was the perfect fit for this, and the institution worked with Microsoft partner BizData for this.
The human genome consists of 7 billion DNA base pairs, and it takes 100GB to represent the unique genetic sequence for a person. Storing it is one thing, but actually analyzing the data to understand and identify disease markets and explore the difference between healthy and cancerous cells is another.
Simply put, it is a slow and complex affair.
Dr. Sebastian Kurscheid explains how cloud computing has helped accelerate the focus on the health aspects of genome research and how Azure fits into all this:
“The general infrastructure is available for going from raw data — as primary as it gets — to a highly analyzed and visualized result and that would probably be used for some work that we are currently finalizing that’s actually looking at the 3D structure of the genome in cancer cells. I’m envisaging that if we conduct all this analysis using Azure then also doing some really nice visualization and exploratory analysis using the platform.”
The Department of Genome Science at ANU had access to 30 to 40 local servers and a number of shared HPC environments, with researchers getting workstations armed with 16 cores, 10TB storage and 128GB of RAM.
However, when they transitioned to the cloud with Azure, they found out that alongside a cost reduction to the tune of a quarter of that of managing their own hardware, they also received four times the computational power they had on-premise.
Based on his work within Azure so far, Dr. Kurscheid believes that moving to a cloud solution would have saved him 9 months, freeing him to focus on research.