University of California, Berkeley, computer science professor David Patterson says cancer researchers should enlist computer scientists in the fight against cancer. Writing in The New York Times this week, Patterson says that as doctors sequence more and more tumors in the hopes of finding key mutations and treating them, where to put all that data and how to analyze it will get tricky. The cost to sequence millions of short reads is almost small potatoes now compared to the cost of processing the data and turning them into something a doctor can use to personalize treatments. "Cancer tumor genomics is just one example of the Big Data challenge in computer science," Patterson writes. "Big Data is unstructured, uncurated and inconsistent, and housing it often requires a thousand-fold increase in size over traditional databases. It is not pristine data that can be neatly stored in rows and columns."
At Berkeley, Patterson and his team are answering the Big Data challenge — they've created a lab with three goals: "inventing algorithms based on statistical machine learning; harnessing many machines in the cloud; and developing crowd-sourcing techniques to get people to help answer questions that prove too hard for our algorithms and machines." Technology like this could help fight cancer, Patterson says. "It may have been true once that expertise in computer science was needed only by computer scientists. But Big Data has shown us that's no longer the case," he adds. "It is entirely possible that we have the skill sets needed now to fight cancer and to advance sciences in myriad other ways."