Science by the Numbers

Professor Uses Computational Biology Research Methods on a Host of Challenges

Desmond Lun

What’s the best way to determine the origin of a crime scene DNA sample?

How about improving the time it takes scientists to evaluate the chemical reaction rates in cells?

And while you’re at it, how do you beat the average return rate for the stock market?

Desmond Lun, a computer science professor, has conducted research making significant progress on answers to all three of these questions. Lun, who was born in Hong Kong and grew up in Australia, earned his doctorate from MIT and did post-doctoral research at Harvard University before joining the faculty at Rutgers University–Camden in 2010. “My academic work has focused on unraveling the complex interactions that underlie living cells using machine learning and other computational methods,” Lun said.

In short, Lun—who conducts his research as part of the Center for Computational and Integrative Biology at Rutgers–Camden—is at the vanguard of biomedical research generated by computer modeling.

Regarding DNA samples, he and other researchers won a $1.7 million Army Research Office grant to create a software program based on a computational method for analyzing DNA evidence. “Our hope is that once it is developed, the software becomes the standard for crime labs everywhere,” Lun said.

In the arena of determining chemical reaction rates in cells, he was among researchers who won a grant from the Samsung Advanced Institute of Technology to use computer modeling to uncover how fast reactions occur in cells. “If we are successful,” he said, “the applications for such a method are endless: biochemical production, biomedicine, bioremediation, and so on.”

And for the stock market? He’s developed a system for that too. “It occurred to me that financial markets are similar to cells—both are highly complex systems that arise from networks of interactions.”

Lun used ideas in computational biology to develop systems to predict the behavior of financial markets. After years of work, he developed an automated trading strategy in 2013 and tested it for three years, showing exceptional results.

In 2016, he established a hedge fund, Taaffeite Capital Management, named for a rare gemstone found in Australia. A Bloomberg article cited his firm’s 21 percent return over the past four years as far superior to the S&P 500 and most hedge fund returns. It described him as “a new kind of quant [Wall Street jargon for quantitative analysts], combining AI [artificial intelligence] wizardry with old-school biology to trade futures.”

Posted in: 2017 FALL, On Campus

Comments are closed.