IBM created a supercomputer that could win Jeopardy, create five star recipes and even could even one day cure cancer.
IBM announced that its Watson computer, alongside a team of researchers, was able to speed up the process of discovery, finding new targets for cancer research.
"We're moving from a time where Watson helps answer questions to one where it tackles the questions that don't have answers," says IBM vice president John Gordon.
Baylor College of Medicine teamed up with Watson to develop an app for the supercomputer called Knowledge Integration Toolkit, or simply KnIT. The app is part of a new system called Watson Discovery Advisor that analyzes scientific and medical papers.
"A new scientific research paper is published nearly every 30 seconds, which equals more than a million annually. 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," IBM says.
The Watson app analyzes scientific research and suggests where researchers should look and what they should look for when attempting to uncover a cure for cancer.
The team of researchers used KnIT to read 23 million MedLine papers, which included 70,000 studies on a tumor suppressor protein called p53 that is linked to half of the cancer cases. They also analyzed data on 500 kinases proteins, which turn p53 on and off.
"On average, a scientist might read between one and five research papers on a good day," says Dr Olivier Lichtarge, the lead researcher and professor of molecular and human genetics, biochemistry and molecular biology at Baylor College of Medicine.
Watson's app doesn't just pull up data like a search engine. The supercomputer interprets research and papers, looking for connections that have been missed. It creates graphs to help researchers analyze and understand the missed connections between proteins and molecular mechanics.
"You are looking for a chain across the papers. If we were playing pool: you would see all the direct shots. What would be less obvious are the combinations," Gordon says.
Watson and team were able to identify six new proteins to target for cancer research. The new proteins were previously unknown kinases that affect p53.
Researchers discovered only 28 target proteins in the last 30 years. Watson and team found the six new ones in a month.
At this rate, maybe a cure for cancer lies in the hands of this supercomputer.
The system is also working on trials for medications and treatments, which is a part of a project for Johnson & Johnson.
The supercomputer cannot do the homework for researchers, but with working with scientists, more medical advancements can be achieved.