Computer scientists should be signing up in droves to fight cancer because they may have the best skills to help cure the disease, writes University of California, Berkeley professor David Patterson.
He says the cost of sequencing the genome of a cancer tumor could soon become affordable, and then doctors would be able to prescribe a personalized, targeted therapy to stop a cancer's growth or cure it. Patterson notes that computer scientists could collect cancer genomes in a repository and make them available to scientists and health professionals.
The University of California, Santa Cruz's David Haussler is working to create a five-petabyte store that would house more than 20,000 genomes.
Patterson says computer scientists also could find a personalized, targeted therapy for each tumor among myriad possible combinations of drugs. The Foldit game by Zoran Popovic at the University of Washington is an example of a way to find such a small needle in a very large haystack.
Meanwhile, Patterson notes that Berkeley's AMP Lab is creating algorithms based on statistical machine learning, harnessing machines in the cloud, and developing crowdsourcing techniques to get people to answer more difficult questions, all in an attempt to obtain timely and cost-effective answers to "big data" questions.
From New York Times
View Full Article
No entries found