Computer Model Predicts Drug Side Effects

Author(s):

A new set of computer models designed to predict the side effects of current and experimental drugs holds the potential to improve drug development and patient treatment.

This article published with permission from The Burrill Report.

A new set of computer models designed to predict the side effects of current and experimental drugs holds the potential to improve drug development and patient treatment.

The new models could potentially be used to test thousands of drugs in the future to help avoid off-target drug interactions and toxicity issues, such as the cardiac problems that were associated with the weight-loss combination drug fen-phen. Such problems are often detected only after fatalities have led regulators to question a drug’s safety.

“By providing a way to identify the unintended targets of a drug, this advance will not only help streamline the drug development pipeline, but also will provide valuable guidance in efforts to repurpose existing drugs for new diseases and conditions,” says Peter Preusch, who oversees structure-based drug design grants at the National Institutes of Health’s National Institute of General Medical Sciences, which partly supported the study.

The new method, called the “similarity ensemble” approach, was developed by a team co-led by the University of California San Francisco School of Pharmacy, Novartis Institutes for BioMedical Research, and the UCSF spinoff SeaChange Pharmaceuticals. It was used to evaluate 656 currently prescribed drugs with known safety records or side effects using bioinformatics techniques to recognize their chemical similarity to other molecules known to cause side effects. Using the new approach, the team was able to predict off-target bindings, and thus potential side effects, for half the drugs it tested.

The platform’s predictions yielded a success rate over 20 times higher than existing broad-scale computational approaches, according to SeaChange, which is developing the method to find new therapeutic uses of known drugs and address toxicology issues.

Michael Keiser, a co-author of the paper and co-founder SeaChange, says that the approach “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.”