Computerworld – IBM's Watson artificial intelligence platform has joined forces with researchers at MIT and Harvard to study how thousands of cancers mutate to become resistant to drug treatments that initially worked to beat back the disease.
By discovering how cancers adapt to overcome drug therapies, researchers at MIT's and Harvard's Broad Institute genomics research center hope to develop a new generation of therapies that cancers cannot circumvent.
While a growing number of treatments can hold cancers in check for months or years, most cancers eventually recur, according to the Broad Institute researchers. This is in part because tumors acquire mutations that make them drug resistant.
That cancer drug resistance is a major cause of nearly 600,000 annual deaths in the U.S. alone, according to Eric Lander, the founding director of the Broad Institute. While scientists have discovered the cause of drug resistance in a small number of cancer cases, which has led to the development of new, successful treatments, most cases are not fully understood.
The new five-year, $50 million genome project will study thousands of drug resistant tumors and draw on Watson's computational and machine learning methods to help researchers understand how cancers become resistant to therapies.
The study's funding will come from IBM.
"Defeating cancer involves playing a high-stakes game of biological chess. When we make a move with a therapy, cancer often responds with a counter-move by finding a way to become resistant. The key will be learning from clinical experience, so that we know cancer's moves in advance and can plan strategies to cut off its escape routes," Lander said.
To help understand how cancers become resistant to specific therapies, the Broad Institute will generate tumor genome sequence data from patients who initially respond to treatment but whose cancers then become drug-resistant. The Broad Institute will use new genome-editing methods to conduct large-scale cancer drug resistance studies in the laboratory, to help identify tumors' specific vulnerabilities. IBM scientists will use Watson to analyze this data and identify genomic patterns that may help researchers and clinicians predict drug sensitivity and resistance.
Earlier this month, IBM and Quest Diagnostics launched IBM Watson Genomics, a service available to U.S. oncologists to help advance personalized medicine by combining cognitive computing with genomic tumor sequencing. The service marked the first time that Watson for Genomics was made widely available to patients and physicians across the country.
The collaboration with the Broad Institute announced today is the latest application of Watson for Genomics to help researchers and clinicians tackle the challenges and opportunities of cancer genomics.
Watson for Genomics will sift through anonymized patient data that will be made available to the scientific community to catalyze research worldwide, and uncover hidden patterns that could help scientists better understand the molecular underpinnings behind cancer treatment resistance.
"The Broad Institute is leading the industry in areas of cancer biology, genomics and computational biology, and we are proud to bring Watson's data prowess to help researchers learn more about one of most important medical challenges that too often stands in the way of effective cancer treatment," John Kelly III, IBM Research's senior vice president of Cognitive Solutions, said in a statement. "Our hope is that this effort, if successful, could eventually lead to significant breakthroughs. Someday, patients who would not otherwise have options in their battle against cancer may have reason for hope."