Drug discovery, Netflix style?

Apr 14, 2010 by Larry Hardesty
Graphic: Christine Daniloff

(PhysOrg.com) -- In the last 10 years, the growth of the Internet has made ranking algorithms one of the hottest topics in computer science. The most famous ranking algorithm is Google's, which determines the order of search results, but close behind are the Netflix and Amazon algorithms that make recommendations on the basis of customers' prior decisions. Now researchers at MIT and Harvard Medical School have shown that ranking algorithms could find an important application in a somewhat surprising field: drug development.

Drug development typically begins with the identification of a “target” — a molecule involved in the underlying some disease. The next step is to try to find chemicals that either promote or suppress the molecule’s production. Scientists have assembled huge libraries — both virtual and physical — of that might be active against biological targets, and drug developers who have identified a target usually select a group of candidate drugs from those libraries.

But the majority of drug candidates fail — they prove to be either toxic or ineffective — in clinical trials, sometimes after hundreds of millions of dollars have been spent on them. (For every new drug that gets approved by the U.S. , have spent about $1 billion on research and development.) So selecting a good group of candidates at the outset is critical.

Drug companies have been using artificial-intelligence algorithms to help select drug candidates since the late 1990s. But in a paper appearing in the next issue of the American Chemical Society’s Journal of and Modeling, Shivani Agarwal, a postdoctoral associate in the Computer Science and Artificial Intelligence Laboratory, Deepak Dugar, a graduate student in chemical engineering, and the Harvard Medical School’s Shiladitya Sengupta showed that even a rudimentary ranking can predict drugs’ success more reliably than the algorithms currently in use.

At a general level, the new algorithm and its predecessors work in the same way. First, they’re fed data about successful and unsuccessful drug candidates. Then they try out a large variety of mathematical functions, each of which produces a numerical score for each drug candidate. Finally, they select the function whose scores most accurately predict the candidates’ actual success and failure.

The difference lies in how the algorithms measure accuracy of prediction. When older algorithms evaluate functions, they look at each score separately and ask whether it reflects the drug candidate’s success or failure. The MIT researchers’ algorithm, however, looks at scores in pairs, and asks whether the function got their order right.

“The criterion we’re giving it is almost the simplest ranking criterion you could construct,” Agarwal says. Nonetheless, in experiments involving data on existing drugs, it consistently predicted the drugs’ success more reliably than the algorithms now in use. The improvements were relatively modest, but to Agarwal, they’re an indication that recent research on more sophisticated ranking algorithms holds real promise for drug discovery.

“There’s a really very systematic improvement over previous methods, and that’s quite striking,” says Peter Bartlett, a professor of computer science and engineering at the University of California, Berkeley. “This is a very nice empirical demonstration that these methods are more effective than the standard methods.”

Anton Hopfinger, a professor at the University of New Mexico College of Pharmacy, cautions that when computer systems rank drug candidates, “the key component is not too surprisingly the properties of the drug or molecule you use to train the system.” That is, the success of the system depends crucially on the mathematical descriptions of the drug candidates. Even the ideal algorithm is helpless if it’s acting on data uncorrelated with a molecule’s biological activity.

But Agarwal is a computer scientist, not a biologist. So while the biologists continue to refine their descriptions of the chemical properties of biological molecules, Agarwal continues to refine her algorithms for ranking drug candidates. At the moment, she’s investigating algorithms that maximize the accuracy of the rankings at the top of a list, even at the expense of lower rankings, since drug developers are generally interested in only a handful of the most promising .

Explore further: Making radiation-proof materials for electronics, power plants

More information: Journal paper: pubs.acs.org/doi/pdf/10.1021/ci9003865

Related Stories

Researchers develop more computer-aided drug design

Mar 10, 2008

Researchers in Germany report an advance toward the much awaited era in which scientists will discover and design drugs for cancer, arthritis, AIDS and other diseases almost entirely on the computer, instead of relying on ...

Networking computers to help combat disease

Jan 23, 2006

Last year there were about 350-500 million infections and approximately 1.3 million deaths due to malaria, mainly in the tropics. Malaria is spread by female mosquitoes, which carry protozoan parasites called ...

Compound screening for drug development made simpler

Mar 24, 2010

The identification of compounds that could be promising candidates for drug development has become easier following research by the Walter and Eliza Hall Institute's medicinal chemistry group.

Recommended for you

User comments : 0

More news stories

Impact glass stores biodata for millions of years

(Phys.org) —Bits of plant life encapsulated in molten glass by asteroid and comet impacts millions of years ago give geologists information about climate and life forms on the ancient Earth. Scientists ...

Researchers successfully clone adult human stem cells

(Phys.org) —An international team of researchers, led by Robert Lanza, of Advanced Cell Technology, has announced that they have performed the first successful cloning of adult human skin cells into stem ...