At the ongoing Conference on Retroviruses and Opportunistic Infections in Boston, workers for Microsoft Research said they have been using database andto identify previously unseen patterns in genetic mutations of HIV. Working in collaboration with doctors and scientists from the University of Washington in Seattle and Australia's Royal Perth Hospital, the researchers plan to propose designs for new HIV vaccines based on the newly discovered patterns.
The researchers said their work illustrates howcan use machine-learning, data-mining and other software methods to sort through millions of strains of HIV and improve vaccines. By seeking out genetic patterns that could be used to train a person's immune system to fight the virus, they are already making headway, the researchers said. The group reported that the first of its proposed vaccine designs is already undergoing laboratory testing.
"The potential for these vaccines is a powerful example of how computer science is transforming medical research and other areas of science," James Mullins, a microbiology professor at University of Washington, said in a statement. "These technologies weren't initially conceived as medical research tools, but they may prove to be critical to the ongoing battle to slow down or halt HIV and other deadly viruses."
Microsoft Research said the new vaccine designs are being tested at the University of Washington, where samples of immune cells are taken from HIV-infected patients and examined to help determine what genetic patterns may aid in warding off HIV. Additional tests are scheduled at the Royal Perth Hospital. Results from both trials should be available later this year, the researchers said.
The group plans to use the same techniques to analyze different strains of HIV gathered from around the globe.
"Science is changing rapidly with the explosion of new data, and we've only scratched the surface of what computers can do to help advance this kind of research," David Heckerman, senior researcher at Microsoft's Research Machine Learning and Applied Statistics Group, said in a statement. "I'm inspired by the idea that new algorithms and software we have developed could potentially benefit so many people some day."