Here at Lenovo, we like to say that our HPC products and people help to Enable Amazing Every Day. We get to see customers utilize our equipment to do everything from seismic and weather modeling, to fluid dynamics and computer-aided design. The life sciences and biotechnology industries have also adopted a broad use of IT in research to be able to quickly understand how biological processes work. That knowledge can lead to discoveries that can have a lasting impact on all of us—from the medicines we take to the food we eat.
Biogemma is one such biotech firm doing amazing work in the area of plant genomics, and they’re using Lenovo systems. Their research is focused on making crops more resilient to environmental conditions such as disease and drought to obtain higher yields. Biogemma faced two problems that were interlinked, but required different IT solutions. First, they needed to analyze huge volumes of genetic sequence data created by their bioinformatics research. Second, they required a highly scalable, parallelized system that could quickly and effectively perform statistical comparisons between millions of gene sequences.
Like most biotech companies, Biogemma wanted one solution that could solve both problems. For bioinformatics workloads requiring large amounts of memory per core, Biogemma deployed a Lenovo System x3850 X6 server featuring Intel Xeon E7 Series processors with 48 cores and 1.5 TB of memory. For the highly parallelized statistical workloads, Biogemma deployed a 36-node Lenovo NeXtScale nx360 M5 cluster, each node having two 12-core Intel Xeon E5 processors, for a total of 864 cores and 34.5 teraflops of performance.
According to Nathalie Rivière, Upstream Genomics Coordinator / Bioinformatics Manager at Biogemma, “We selected the solution proposed by Lenovo and its partner, Serviware, based partly on its price-performance ratio and partly on the expertise both parties showed during the benchmarking process, which helped us to optimize the solution and tune our applications. Their expertise also helped us significantly in improving the scheduling and prioritization of compute jobs.” And the results? “A job that typically took a day to run now completes in a matter of hours or even minutes—up to a 99 percent improvement,” according to Rivière.
You can read more about the Biogemma solution in the case study we’ve posted.