Microsoft spam-detecting algorithm helps with HIV research
When the first computer viruses popped up, their behavior was so similar to that of their biological counterparts that security researchers simply chose to appropriate the already existing expression.
And it is that very same similarity that has now – years and years later – helped medical researchers glean crucial insights into how a particular virus still manages to avoid being beaten.
“It turns out there are a lot of similarities between the way spammers evolve their approaches to avoid filters and the way that the HIV virus is constantly mutating,” writes Microsoft’s Steve Clayton, and so the Redmond giant has offered some of its technology to help the researchers in their quest for developing a cure for the (relatively) modern blight.
The project brought together experts from a number of institutions that test potential vaccines for HIV: MIT, Harvard, the Center for the AIDS Programme of Research in South Africa, the Ragon Institute at Massachusetts General Hospital, and the KwaZulu-Natal Research Institute for Tuberculosis and HIV. With all the testing going on, these various institutions have an immense amount of data that had to be analyzed in order to detect patterns in the virus’ evolution.
“That’s where David Heckerman and Jonathan Carlson of Microsoft Research along with a Microsoft Computational Biology Tool called PhyloD come in,” explaines Clayton. “This software enables efficient data mining which then leads to specific cell analysis that helps detail virus patterns for further analysis. PhyloD contains an algorithm, code and visualization tools to perform complex pattern recognition and analysis – enabling Heckerman and his colleagues to learn how different individual immune systems respond to the many mutations of the virus.”
Of course, such a tool is not enough – massive computer power is needed in order to make the analysis last days instead of months (or years). Luckily, Microsoft has that at its disposal, as well, so it took only a few days to receive the results. In the end, they “discovered” six times as many possible attack points on the HIV virus.
The algorithm that PhyloD employs was originally designed to detect the different tactics that spammers use to try an bypass email spam filters in Hotmail, Outlook and Exchange. And while spam and HIV both still present great problems, interdisciplinary approaches to research such as this one do raise hope for the future.