A team of researchers at Michigan Technological University is harnessing the computing muscle behind the leading video games to understand the most intricate of real-life systems.
Led by Roshan D'Souza, the group has supercharged agent-based modeling, a powerful but computationally massive forecasting technique, by using the graphic processing units which drive the spectacular imagery beloved of video gamers. In particular, the team aims to model complex biological systems, such as the human immune response to a tuberculosis bacterium.
Agent-based modeling simulates the behaviors of complex systems. It can be used to predict the outcomes of anything from pandemics to the price of pork bellies. It is, as the name suggests, based on individual agents: e.g., sick people and well people, predators and prey, etc. It applies rules that govern how those agents behave under various conditions, sets them loose, and tracks how the system changes over time. The outcomes are unpredictable and can be as surprising as real life.
Agent-based modeling has been around since the 1950s, but the process has always been handicapped by a shortage of computing power. Until recently, the only way to run large models quickly was on multi-million-dollar supercomputers, a costly proposition.
D'Souza's team sidestepped the problem by using GPUs popularized in the video game world because they can run models with tens of millions of agents at blazing speeds.
Computer science student Mikola Lysenko, who wrote the software, says a swarm of bright green immune cells that surrounds and contains a yellow TB germ may look like 3D-animations from a PBS documentary but they are actually virtual T-cells and macrophages — the visual reflection of millions of real-time calculations.
"I've been asked if we ran this on a supercomputer or if it's a movie," says D'Souza, an assistant professor of mechanical engineering–engineering mechanics. He notes that their model is several orders of magnitude faster than state-of-the art agent modeling toolkits. According to the researchers, however, this current effort is small potatoes.
"We can do it much bigger," says D'Souza. "This is nowhere near as complex as real life." Next, he hopes to model how a TB infection could spread from the lung to the patient's lymphatic system, blood and vital organs.
Dr. Denise Kirschner, of the University of Michigan in Ann Arbor, developed the TB model and gave it to D'Souza's team, which programmed it into a graphic processing unit. Agent-based modeling hasn't replaced test tubes, she says, but it is providing a powerful new tool for medical research.
Computer models offer significant advantages. "You can create a mouse that's missing a gene and see how important that gene is," says Kirschner. "But with agent-based modeling, we can knock out two or three genes at once." In particular, agent-based modeling allows researchers to do something other methodologies can't: virtually test the human response to serious insults, such as injury and infection.
While agent-based modeling may never replace the laboratory entirely, it could reduce the number of dead-end experiments. "It really helps scientists focus their thinking," Kirschner said. "The limiting factor has been that these models take a long time to run, and [D'Souza's] method works very quickly and efficiently," she said.
Dr. Gary An, a surgeon specializing in trauma and critical care in Northwestern University's Feinberg School of Medicine, is a pioneer in the use of agent-based modeling to understand another matter of life and death: sepsis. With billions of agents, including a variety of cells and bacteria, these massive, often fatal infections have been too complex to model economically on a large scale, at least until now.
"The GPU technology may make this possible," said An. "This is very interesting stuff, and I'm excited about it."
"With a $1,400 desktop, we can beat a computing cluster," says D'Souza. "We are effectively democratizing supercomputing and putting these powerful tools into the hands of any researcher. Every time I present this research, I make it a point to thank the millions of video gamers who have inadvertently made this possible."
The Tech team also looks forward to applying their model in other ways. "We can do very complex ecosystems right now," said Ryan Richards, a computer science senior. "If you're looking at epidemiology, we could easily simulate an epidemic in the US, Canada and Mexico."
"GPUs are very difficult to program. It is completely different from regular programming," said D'Souza, who deflects credit to the students. "All of this work was done by CS undergrads, and they are all from Michigan Tech. I've had phenomenal success with these guys — you can't put a price tag on it."
D'Souza's work was supported by a grant from the National Science Foundation. In addition to Lysenko and Richards, computer science undergraduate Nick Smolinske also contributed to the research.