Visit additional Tabor Communication Publications
October 08, 2012
Life Sciences can mean different things to different people. In genomic research, it referrers to the art of sequencing; in BioPharma, it covers molecular dynamics and protein docking; and in clinical, electronic records. However, all three markets have one thing in common, the sequencing of the human genome and the control, analysis, and distribution of that data. Today with the continued decrease in sequencing costs, life sciences research is moving from beakers to bytes and increasingly relies on the analysis of large volumes of data.
Data-dominated efforts today aim to accelerate drug R&D, improve clinical trials, and personalize medicine. Most of the work in these areas requires the use of high performance computing clusters or supercomputers to derive decision-making information from terabytes to petabytes of data.
Across these widely disparate areas of work, researchers face similar computational infrastructure problems that can impede progress. To avoid obstacles and accelerate their research, life scientists need a low-latency, high-performance computing infrastructure that delivers predictable and consistent performance. They also need to collaborate and share large datasets with upstream and downstream partners. And they need an infrastructure that supports automation to simplify data aggregation, assimilation, and management.
The need for speed
Life sciences research and development increasingly relies on computational analysis. Such analysis provides the critical information needed to make intelligent decisions about which new drug candidates hold promise and should be advanced and which should be put aside.
With the growing reliance on computational analysis, and the changes in data generation and usage, life sciences organizations need an IT infrastructure that ensures computational workflows are optimized and not impeded.
Pressure to run the workflows as fast as possible so research decisions can be made sooner comes from several business drivers.
Many pharmaceutical companies today have sparse new drug pipelines. Delays caused by slowdowns in research due to slow data analysis simply keep the pipelines empty.
Because less than one percent of all drug candidates make it to market and the cost of moving a drug along the development pipeline mounts hugely the further along it gets, knowing which drugs to fail out of the process early is key to financial success. Faster early-stage analysis provides the data needed to make an early decision providing a significant savings in time and investment.
Compounding the need to quickly identify promising candidates and fill the pipelines is the fact that many blockbuster drugs have gone or are going off-patent and must be replaced. In fact, patent expirations from 2010 to 2013 will jeopardize revenues amounting to more than $95 billion for ten of the largest drug companies, according to Nature.
Competition to fill the pipelines is heating up. The drastic reduction in new lab equipment operating costs is allowing even the smallest life sciences organizations to compete in early stage R&D.
These factors are forcing companies to change the way they approach new drug research.
First, there is a greater focus on computational analysis during early stage research and development. The idea is to use information-based models, simulations, virtual molecule screening, and other techniques identify promising new drug candidates quickly and kill off less promising candidates to avoid incurring the costs of later stage clinical trials, development, and approval.
Second, many organizations are seeking to reduce their R&D costs. To accomplish this while still trying to fill their pipelines, they are expanding collaborations with universities, non-profit organizations, and the government. Specifically, beyond opening offices in university-rich places like Cambridge, MA, many pharmaceutical and biotech companies are joining collaborative groups such as the Structural Genomics Consortium, a public-private partnership that supports the discovery of new medicines through open access research. There are also government-led early-stage R&D efforts, such as those underway at the National Center for Advancing Translational Sciences, a group with the goal of developing new methods and technologies to improve diagnostics capabilities and therapeutic efforts across a wide range of human diseases.
Third, the desire to cut costs is creating an emerging market for Sequencing-as-a-Service (SEQaaS). Rather than invest in the sequencing equipment, chemicals, and experienced staff needed to perform the operations, many companies are outsourcing their sequencing to providers such as Illumina, PerkinElmer, and others. This allows them to concentrate on other aspects of drug discovery and development pipeline.
Storage complications and challenges that can impede analysis workflows
These business drivers, combined with the adoption of new lab technologies such as next-generation sequencing, confocal microscopy, and X-ray crystallography, are driving up the volumes of data that life sciences organizations must store and manage. These large volumes and the collaborative nature of life sciences research are placing new demands on storage solution performance and data manageability.
For example, new lab equipment, particularly next-generation sequences are producing multiple terabytes of data per run that must be analyzed and compared to large genomic databases. And while the format of raw data from sequences has varied over time as sequencing vendors have incorporated different processing steps into their algorithms, organizations using the sequencing data must still perform post-sequencing computations and analysis on various size files to derive useful information. From an infrastructure perspective, the sequencing data needs to be staged on high-performance parallel storage arrays so analytic workflows can run at top speeds.
Another factor to consider is that much of the data generated in life sciences organizations now must be retained. When sequencing for clinical applications is approved by the FDA, the Health Insurance Portability and Accountability Act of 1996 (HIPAA) requires that this patient data be retained for 20+ years.
In pharmaceutical companies, long-term access to experimental data is growing as companies seek indications for previously approved drugs. With pipelines sparse, this area of work is exploding. From a storage perspective, older data must be moved to lower cost storage after its initial analysis or use and then be easily found and migrated to higher performance storage when exploring its use for a new indication.
Complicating data management and computational workflows is that fact that life sciences research has become more multi-disciplinary and more collaborative. Within an organization, data from new lab equipment is incredibly rich and of interest to many groups. Researchers in the different disciplines use different analysis tools running on clients with different operating systems and they need to perform their analysis at different times in the data’s life cycle. This makes computational workflows highly unpredictable. This can result in a vastly different user experience from day-to-day. A run that takes two minutes one day might take 45 minutes the next.
An additional implication of the multi-disciplinary and more collaborative nature of life sciences research is that data increasingly must be shared. This can pose problems within a company and it certainly needs special attention when organizations team together and must share petabyte-size databases across widely dispersed geographical regions.
DDN as your technology partner
All of these factors mean storage plays an increasingly important role in life sciences success. Solutions must support highly variable workloads in an HPC environment and be capable of supporting the collaborative nature of the industry. They also must allow researchers using different clients and hosts to have shared access to the data needed for their analysis.
Additionally, solutions must provide life sciences organizations with the flexibility to store data for longer times on appropriate cost/performance devices, while offering data management tools to migrate and protect that data. And there must be a way to facilitate the sharing of very large datasets.
Traditional storage solutions can introduce major performance and management problems when scaled to meet today’s increased requirements for the life sciences. This is why the Cornell Center for Advanced Computing, the National Cancer Institute, TGen, Virginia Tech, the Wellcome Trust Sanger Institute, and many more life sciences organizations are partnering with DataDirect Networks (DDN).
DDN offers an array of storage solutions with different I/O and throughput capabilities to meet the cost/performance requirements of any life sciences workflow. The solutions are extremely scalable in capacity and density. Based on its Storage Fusion Architecture, the DDN SFA 12K line offers a number of firsts including up to 40 GB/s host throughput for reads AND writes, 3.6 PB per rack, and the ability to scale to more than 7.2 PB per system. Furthermore, DDN lets organizations control their cost and performance profile by mixing a variety of media in the same system – SSD, SAS, and SATA – to achieve the appropriate cost/performance mix for their applications.
By consolidating on DDN storage, organizations get fast, scalable storage that solves performance inconsistency issues and provides easy-to-manage long term data retention.
In addition, DDN offers several technologies that help with the common challenges in life sciences research.
For researchers that must share and exchange large datasets within their organization, with collaborative partners, or with sequencing providers, DDN offers Web Object Scaler (WOS), a scale-out cloud storage appliance solution. WOS is an object-based storage system that allows organizations to easily build and deploy their own storage clouds across geographically distributed sites. The storage can scale to unprecedented levels while still being managed as a single entity. WOS provides high-speed access to hyperscale-sized data in the cloud from anywhere in the world, enabling globally distributed users to collaborate as part of a powerful peer-to-peer workflow.
To simplify and automate data management issues so researchers from multiple disciplines can all access the same data, DDN has integrated WOS with the Integrated Rule-Oriented Data-management System (iRODS). The iRODS data grid is an open source, next-generation adaptive middleware architecture for data management that helps researchers organize, share, and find collections of data in file systems.
And to ensure researchers get a high-performance, consistent experience, DDN offers DirectMon, an advanced storage configuration and monitoring solution. DirectMon works across DDN’s line of DDN SFA Storage Arrays, as well as GRIDScaler and EXAScaler shared file system appliances. DirectMon removes the complexity out of managing storage, its ease-of-use features and notifications allow administrators to quickly resolve problems, freeing-up valuable time to concentrate on more important tasks.
For more information about DDN solutions for the life sciences, visit http://www.ddn.com/en/applications/biopharma
Additional information can be found by visiting
In quieter times, sounding the bell of funding big science with big systems tends to resonate further than when ears are already burning with sour economic and national security news. For exascale's future, however, the time could be ripe to instill some sense of urgency....
In a recent solicitation, the NSF laid out needs for furthering its scientific and engineering infrastructure with new tools to go beyond top performance, Having already delivered systems like Stampede and Blue Waters, they're turning an eye to solving data-intensive challenges. We spoke with the agency's Irene Qualters and Barry Schneider about..
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 22, 2013 |
At some point in the not-too-distant future, building powerful, miniature computing systems will be considered a hobby for high schoolers, just as robotics or even Lego-building are today. That could be made possible through recent advancements made with the Raspberry Pi computers.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 15, 2013 |
Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.