Personalized medicine has the potential to radically change the health-care business; just imagine if every cancer patient could get a treatment customized to work best with their genes. But there’s a problem: storing genetic information is a data nightmare–genotyping a single individual can produce up to 1.5 GB of data. That adds up quickly, which is why IBM is stepping in to keep our genetic information organized.
IBM teamed up with the Coriell Institute for Medical Research, the largest biobank of living human cells, to help maintain its collection of biomaterials, which include cell lines and DNA samples representing over half of the 4,000 known genetic diseases–everything from diabetes to cancer.
“The health-care industry is placing
greater emphasis on the use of genetic information in making medical decisions,”
said Scott Megill, Coriell’s chief information officer, in a statement. “As a leader
in genomics, Coriell is exploring the clinical utility of this personalized
approach to medicine. The breadth of data output created by our research
introduced new challenges to analyze and store this information.”
That’s where IBM comes in. The company has implemented a tracking system that allows Coriell to track each sample (these vary by type, disease state, and age, among other things) as it moves through various lab processes. IBM also has deployed real-time freezer monitors so that Coriell can prevent mechanical failures in its cryogenic freezers, which contain up to 48,000 samples at a time.
But while IBM may have solved some of the data storage issues associated with personalized medicine, there are still plenty of other issues to deal with. Among them: are doctors prepared to handle so much data for each one of their patients? Paging Big Blue.