Cancer Research Uses Parallel Computing

The National Cancer Institute’s Pediatric Oncology Branch is using parallel computing software to accelerate medical discoveries.

The researchers use a Matlab-based application called CORR4DM to correlate one genomic array against a database of 100,000 parts of a gene, in search of specific DNA components or attributes. The results help them to understand the relationship between the genes, and may even direct future genomic research.

Running a single correlation on a desktop computer could take a week or more to complete. An explosion in the amount of genomic data available to researchers has made their work increasingly difficult. Their tasks require more computing power, more system memory, and - all too often - more time. And in the race to understand how genetics and cancer are linked, time is precious. Thus, once the sample sizes grew to consist of tens of thousands of arrays, it became obvious parallel computing was necessary to provide larger correlations.

Scientists made use of Interactive Supercomputing's (ISC) Star-P software. This allows them to make use of powerful high performance computers to explore vast public databases to have insight into the genetic risk factors for cancer, foster new procedures for testing tumors, or even identify genetic changes resulting from treatment. The software also allowed them to quickly interact with the data. 'Star-P' (as described in our past posting) lets scientists continue to work with their preferred tools, shielding them from the programming complexities of parallel systems. It can automatically connect MATLAB to the server and parallelises the application code.