Recent research has determined that a set of computer models can predict the negative side effects in hundreds of current drugs, based on the similarity between their chemical structures and those molecules known to cause side effects. The conclusion was driven by researchers at the University of California at San Francisco, and will appear in a paper in the journal Nature.
Led by researchers in the UCSF School of Pharmacy, Novartis Institutes for BioMedical Research (NIBR), and SeaChange Pharmaceuticals, Inc., it looked at how a computer model could help researchers eliminate risky drug prospects by identifying which ones were most likely to have adverse side effects. The researchers focused on 656 drugs that are currently prescribed, with known safety records or side effects. They were able to predict such undesirable targets — and thus potential side effects — half of the time.
According to Brian Shoichet, PhD, a UCSF professor of pharmaceutical chemistry and joint advisor on the project alongside Laszlo Urban, MD, PhD, at Novartis, this work was the first to tackle hundreds of compounds at once. As a result, he says, it offers a possible new way for researchers to focus their efforts on developing the compounds that will be safest for patients, while potentially saving billions of dollars each year that goes into studying and developing drugs that fail.
“The biggest surprise was just how promiscuous the drugs were, with each drug hitting more than 10 percent of the targets, and how often the side-effect targets were unrelated to the previously known targets of the drugs,” Shoichet said in a statement. “That would have been hard to predict using standard scientific approaches.”
Among reasons that potential drugs fail in clinical trials, adverse drug effects are the second most common reason behind effectiveness. This can cost up to $1 billion over 15 years, the researchers say. Some drugs, recent research estimates, can cost as high as $12 billion.
“This basically gives you a computerized safety panel, so someday, when you’re deciding among hundreds of thousands of compounds to pursue, you could run a computer program to prioritize for those that may be safest,” Michael Keiser, PhD, co-first author of the paper, said in a statement.