IBM Corp’s Watson supercomputer is set to tackle scientific research head-on after being re-programmed to analyse Big Data in the cloud.

It’s just launched a new system called Watson Discovery Advisor for analyzing scientific and medical research. Big Blue claims that the system understands the nuances of natural language so well it’s able to comb through libraries of research papers, and can even suss out scientific language well enough to know how chemical compounds react. Watson Discovery Advisor will use the data contained in millions of studies available in public databases to rapidly analyze and test new hypothese, says IBM.

“A new scientific research paper is published nearly every 30 seconds, which equals more than a million annually,” explains IBM. “According to the National Institutes of Health, a typical researcher reads about 23 scientific papers per month, which translates to nearly 300 per year, making it humanly impossible to keep up with the ever-growing body of scientific material available.”

Watson Discovery Advisor is already being used in clinical trials carried out by the pharmaceutical company Johnson & Johnson. The idea is that Watson will help to speed up this kind of research by matching new drugs with the right patients to maximize their effectiveness while minimizing side effects.

Until now, this kind of work has always been done manually. It generally takes human researchers around ten months to collect and prepare all the data they need to make an analysis.

“On average, a scientist might read between one and five research papers on a good day,” said Dr Olivier Lichtarge, principal investigator and professor of molecular and human genetics, biochemistry and molecular biology at Baylor College of Medicine.

“To put this in perspective with p53, there are over 70,000 papers published on this protein. Even if I’m reading five papers a day, it could take me nearly 38 years to completely understand all of the research already available today on this protein. Watson has demonstrated the potential to accelerate the rate and the quality of breakthrough discoveries.”

Lichtarge’s team has used Watson to help them identify proteins that modify p53, a key protein that’s related to many kinds of cancer. Typically, cancer researchers only identify one new protein they can work on each year, but thanks to Watson’s super-fast analysis they’ve already discovered six potential proteins they can target for new research.

photo credit: David Baker (sophos9) via photopin cc