With approximately 5,000 drugs on the market and 1,000 different known side effects, there are nearly 125 billion possible side effects between all possible pairs of drugs. Most have never been prescribed together or systematically studied.
Now, computer scientists from Stanford University have developed an artificial intelligence system that is able to predict potential side effects from drug combinations.
Researchers Marinka Zitnik, Monica Agrawal, and Jure Leskovec started by studying how drugs affect the body’s underlying cellular machinery. They composed a massive network describing how the more than 19,000 proteins in the body interact with each other and how different drugs affect these proteins. Using more than 4 million known associations between drugs and side effects, the team then designed a method to identify patterns in how side effects arise based on how drugs target different proteins.
To do that, they used deep learning, a type of artificial intelligence modeled after the brain. Deep learning looks at complex data and extracts abstract, sometimes counterintuitive patterns in the data. The scientists designed their system to infer patterns about drug interaction side effects and predict previously unseen consequences from taking two drugs together.
Currently, Decagon considers only side effects associated with pairs of drugs. In the future, the team hopes to extend their results to include more complex regimens, Leskovec said. They also hope to create a more user-friendly tool to provide guidance to doctors in prescribing a particular drug and help researchers develop drug regimens for complex diseases with fewer side effects.