Predicting Side Effects with Computer Modeling

Predicting Side Effects with Computer Modeling

June 12th, 2012 // 12:16 pm @ jmpickett

Source

Anticipating side effects is a difficult undertaking for all concerned, but what if a computer could predict the likelihood that drugs would cause certain adverse events being given to patients in clinical trials? Well, a group of scientists from Novartis and the University of California, San Francisco, apparently have developed such a test, which would, undoubtedly, save enormous time and money, and reduce physician and patient concerns.

In a study published in Nature, the researchers created a database of 73 proteins that were associated with adverse events and used a computer program that could quickly analyze drug molecules to predict whether 656 approved drugs were likely to interact with any proteins linked to side effects, the Boston Globe writes. More than 1,000 predictions were made and verified by searching published materials and conducting new lab tests. About half of the predictions were correct, and 151 of the interactions were previously unknown (see this).

“The beauty of computer programs (is) they are very inexpensive,” Eugen Lounkine, the lead researcher and a computational biologist at Novartis, tells the newspaper. “They don’t need the actual physical compounds, so they can assess thousands of those virtual compounds, and that allows us to very, very early on prioritize what compounds we want to look at in further experiments.”

As an example, the researchers found that a prostate cancer drug had an unexpected off-target effect and acted similar to nonsteroidal anti-inflammatory drugs, which can cause problems with the gastrointestinal system. This helped explain a previously mysterious side effect of the prostate drug: upper abdominal pain. And this is why such a computer program is likely to be viewed with optimism.

Side effects, after all, cause about 20 percent of drugs in clinical development to fail, according to the Tufts Center for the Study of Drug Development. “I think this is an extremely powerful tool,” Ken Kaitin, who heads the Tufts program, tells the newspaper. “One of the major challenges for the industry is that compounds enter clinical testing without a very good understanding of how the drugs work and what the side effects are going to be, so you’re essentially entering blind.”