WASHINGTON — Medical research has traditionally treated cancer as a disease to be cured, but Microsoft’s latest efforts to aid the medical professionals treats it as a puzzle to be solved.
The company recently announced a range of initiatives in which computer scientists are working out the complexities of cancer and the best options for treatments. The efforts range from a way to sort through the mountain of research data on cancer to a “moonshot” effort to program cells to fight cancer and other diseases.
Much of the work happens at the genetic level, Microsoft and their associated scientists say.
“We’re in a revolution with respect to cancer treatment,” said David Heckerman, a scientist and senior director of the genomics group at Microsoft.
“Even 10 years ago people thought that you treat the tissue: You have brain cancer, you get brain cancer treatment. You have lung cancer, you get lung cancer treatment. Now, we know it’s just as, if not more, important to treat the genomics of the cancer, e.g. which genes have gone bad in the genome.”
That generates a mountain of information, both in terms of genetic mutations and combinations, and in the research on the genomes.
Bloomberg Technology reports that there are more than 800 cancer medicines and vaccines in clinical trials. The reports on all these drugs are far more than any oncologist can sift through — and that’s where “machine learning” comes in.
Microsoft gives as an example of machine learning a program’s ability to recognize photos of cats based on previous photos of cats a system has seen. The key is to translate that to the task of sifting through research.
Microsoft’s Hoifung Poon says his Hanover project is designed to help scientists sift through all the data. He showed Bloomberg Technology pictures of a patient whose cancer had been knocked back but had reappeared.
“There are already hundreds of these kinds of specifically targeted drugs, so even if you think let’s pair two drugs, there are tens of thousands of options,” Poon said. “It’s very hard to wrestle with. You might need several drugs to lock down all of the tumor’s pathways.”
Meanwhile, research is looking at the cancer gene directly.
“The tools that are used to model and reason about computational processes — such as programming languages, compilers and model checkers — are used to model and reason about biological processes,” Microsoft said in the statement.
Jasmin Fisher, a Microsoft researcher and biochemist in Cambridge, England, says that she’s taking a computational approach to the process that turns a cell cancerous. She’s trying to figure out the behavior of a cell the way a computer scientist would decode a computer program he didn’t create. The goal, Microsoft says, is to figure out in a schematic way the behavior of a healthy cell, compare it to a cancerous cell, and work out how it can be fixed.
“If you can figure out how to build these programs, and then you can debug them, [cancer is] a solved problem,” she said.
