Two weeks ago, The Genome Analysis Centre (TGAC) based in the U.K. turned on the first of two new SGI UV300 computers. Next week, or thereabouts, TGAC will bring a second identical system online. Combined with its existing SGI UV2000, TGAC will have the largest SGI system dedicated to life sciences in the world. The upgrade will allow TGAC to significantly shorten the time required to assemble wheat genomes, a core activity in TGAC efforts to enhance worldwide food security.
The upgrade is part of TGAC’s central mission to use advanced HPC and bioinformatics to seek solutions to the world food productivity challenge. TGAC’s specialty is wheat, which is a major base component of the world’s food supply.
It turns out the wheat genome is notoriously difficult to work with. For starters, it contains roughly 17 gigabases (nucleotide pairs), which is five times the size of the human genome. The wheat genome contains 80 percent ‘repeats’ – sections of DNA sequence that are especially difficult to assemble and confound most sequencing algorithms. Lastly, the wheat genome is hexaploid, meaning it has six sets of chromosomes versus two for the human genome – the thinking here is that modern wheat is a kind combination of three ancestral strains.
All boiled down, wheat is tough to deal with from a sequence assembly perspective, and when TGAC help produced the first draft of the complete wheat genome a year or so ago, it was heralded as a major achievement.
Unfortunately the world’s wheat yields have been declining for a variety of reasons. “Our work – through genome assembly, alignment, and variant calling – is to help work out what the [gene] functions are and to get that data back to the research community and breeders who hopefully can breed new types of wheat that are less susceptible to heat and pathogens, etc.,” said Tim Stitt, Head of Scientific Computing at TGAC.
Not surprisingly high performance computing is critical to TGAC’s effort. “Because of the work that we do and its size and scale, we need to cutting edge technologies to be able to handle the work quickly and effectively.” TGAC was, for example, one of the first major genomics centers to deploy the specialized FPGA-based DRAGEN processor to accelerate alignment and variant calling. “Alignment used to take 3-4 day, now it takes 3-4 hours using the FPGA,” said Stitt.
By comparison, genome assembly is more difficult than alignment, especially so called de novo sequencing which doesn’t use a reference genome as a guide. On TGAC’s earlier systems, it was taking four weeks to assemble a wheat genome. The new UV300s, which replace a pair of aging UV100s, have been especially configured for assembly work (memory, processor speed) and are expected to shorten the time required to assemble wheat genomes to less than three weeks.
Here’s a brief overview of the new machines:
- This new TGAC platform comprises two SGI UV 300 systems totaling 24 terabytes (TB) of shared-memory, 512 Intel Xeon Processor E7 v3 cores and 64TB of Intel P3700 SSDs with NVMe storage technology. Each SGI UV 300 flash memory solution features 12TB of shared memory with 7th generation SGI NUMAlink ASIC technology, scaling up to 64 TB of global addressable memory as a single system.
- Paired with flash storage, the combined 24TB SGI UV 300 supercomputers can increase processing speeds of heavy workloads in scientific research by 80 percent. This combination of leading-edge technology allows TGAC researchers to benefit from the faster processing capabilities of the SGI UV 300, providing an extraordinarily powerful platform for genomics analysis.
“Having a shared memory server is an important element,” said Stitt. “A single assembly typically requires 4-6TB of RAM. What’s somewhat unique about this platform compared to the previous ones are the 32 TB of solid state drives (per machine) with NVME. That should give us a significant boost on the IO side. Our wheat files can be close to 1TB in size and must be read into memory.”
Besides memory enhancement, the jump to E7 v3 processors was a major step up from the Sandy Bridge processors in the UV100. “We’ve essentially skipped a generation – Ivy Bridge – and gone straight to Haswell. That alone would give us a boost in performance. Really it’s the whole package – memory, processors, storage, etc. The UV100s were purchased five or six years ago and that’s a lifetime in HPC.”
TGAC runs multiple jobs on SGI computers and is in the process of switching schedulers. Altair’s PBS is used on the old system, but Stitt is transitioning to Slurm, which is being used on the new UV300 that’s running. They both work well, said Stitt. “We’ve evaluated Slurm over past 6 – 8 months. It worked very well for what we want to do and it’s free. Really it was a cost decision and may free up revenue we’d normally spend on licenses and allow us to put it towards more hardware.”
Stitt notes the new UV300 solutions are considerably more dense that the older machines, “The UV300 comes in 5U rack space; the UV100 with effectively less memory, fewer cores, probably took over a rack of space.” He’s expecting greater energy efficiency as a result.
Researchers are still in the early stages of using the first UV300, said Stitt, who like HPC managers throughout life sciences must serve a diverse researcher constituency, many of whom aren’t comfortable with command line tools. “You need to know a little but about Linux to log into our HPC systems. A lot of our users, particularly our external users, don’t have backgrounds in programming and Linux and command lines and things,” Stitt said.
To make things easer, TGAC also allows users to use tools like Galaxy as a front end to the systems. “These researchers can access our systems through the Galaxy interface where they can set up workflows and Galaxy will launch them on the back end. Actually, we have a whole research team that works on data integration and the equivalent of scientific portals to help here.”
Along the line of reaching the maximum number of researchers, TGAC is in the midst of a project to forge closer ties with iPlant, a U.S.-based effort also tackling worldwide food production and agriculture. A few key iPlant organization and mission points are bulleted here:
- Established by the U.S. National Science Foundation (NSF) in 2008 to develop cyberinfrastructure for life sciences research and democratize access to U.S. supercomputing capabilities.
- A virtual organization lead by The University of Arizona, Texas Advanced Computing Center, Cold Spring Harbor Laboratory, and University of North Carolina at Wilmington.
- Developing the national cyberinfrastructure for data-intensive biology driven by high-throughput sequencing, phenotypic and environmental datasets.
- Providing powerful extensible platforms for data storage, bioinformatics, image analyses, cloud services, APIs, and more.
- Making broadly applicable cyberinfrastructure resources available across the life science disciplines (e.g., plants, animals, and microbes).
“We won an award recently to build an iPlant U.K. here at TGAC. We’re working with iPlant folks to put together an iPlant infrastructure and at some point hopefully federate the two sites together. It’s a big project that we are halfway through,” said Stitt. The goal is to facilitate and speed dissemination of TGAC result by having an open system for sharing data.
Stitt is also working to make better use of the DRAGEN FPGA system, “It’s working brilliantly and we certainly haven’t exceeded our limits on it. We are expecting to generate more data coming from new lines of wheat and our interest lies is streamlining the two technologies – the DRAGEN chip with the SGI system.” That’s part of TGAC’s IO challenge generally. “We have raw data coming off the sequencing machines that we need to get onto the SGI platform, particularly the SSD drives. That data is used to generate an assembly, which we’ll store on our file system, and we need to pipe that into our DRAGEN FPGA [which sits on another system.]”