IBM Watson to Help New York Genome Center Treat Cancer
IBM’s artificially intelligent supercomputer will help tailor unique treatments to individual cancer patients.
IBM Watson is commonly known as the supercomputer that defeated Ken Jennings in a game of Jeopardy! three years ago, but the artificially intelligent computer system has proven capable of doing a great deal more than simply winning quiz shows. On Wednesday, March 19, the New York Genomic Center announced that it is partnering with IBM in a clinical trial to help treat patients diagnosed with glioblastoma, an aggressive brain cancer which kills over 13,000 people in the US every year.
The goal of this collaboration is to allow oncologists to deliver more personalized care to patients. While recent research has yielded substantial discoveries of the genetic drivers behind cancers such as glioblastoma, the vast majority of patients are unable to find personalized treatment based on their particular cancerous mutations. In order to attempt such a feat, doctors would need to sequence each patient’s unique genome and then compare it with enormous amounts of medical journals, studies, and records in an effort to find the best course of action for an individual’s exact condition.
Watson’s cloud-based prototype, designed expressly for genomic research, however, will be able to efficiently and effectively do just that in a fraction of the time it would take a team of clinicians—combing through reams of data to connect the dots between an individual’s genome, the path the cancer has taken, medical records, and up-to-date scientific research. Using its powerful computational capabilities, Watson will be able to sequence billions of genetic base pairs every minute, mapping out a single person’s unique genome in a fraction of the time it would have once taken.
“Since the human genome was first mapped more than a decade ago, we’ve made tremendous progress in understanding the genetic drivers of disease,” said Dr. Robert Darnell, President and Scientific Director of the New York Genome Center. “The real challenge before us is how to make sense of massive quantities of genetic data and translate that information into better treatments for patients. Applying the cognitive computing power of Watson is going to revolutionize genomics and accelerate the opportunity to improve outcomes for patients with deadly diseases by providing personalized treatment.”
“Our goal is to provide Watson a consistent stream of genomic data, electronic medical records, pharmacological information and medical literature related to an individual patient’s cancer,” he added. “Together with the NYGC analytics resources of tools and people, we will assess the impact of gene mutations on tumor cells—the cause-and-effect trail of the cancer.”
Watson will compare billions of DNA samples with a cancer patient’s genome sequence, and sort through millions of pages of biomedical information to tailor its recommendations to the individual. Through this process, oncologists will be able to use Watson as a sort of advisor, allowing the computer to find existing drugs or treatments that can be used to attack each patient’s cancer and cutting down on the time it would take to find the right solution.
“As genomic research progresses and information becomes more available, we aim to make the process of analysis much more practical and accessible through cloud-based, cognitive innovations like Watson,” said Dr. John Kelly III, Senior VP of IBM Research. “If successful, this will be a major transformation that will help improve the lives of millions of patients around the world.”
The initial trial will involve nine New York institutions and cover 20 patients. If it succeeds, Watson will be able to effectively learn from each new scenario it treats and use that new information to help other patients in the future.
“We hope to learn lessons from taking on glioblastoma that eventually will be useful in addressing many of the more than 100,000 cancer cases that are diagnosed each year in New York State alone,” said Darnell.