Researchers Use Artificial Intelligence to Predict Side Effects of Drug Combinations


Researchers predict the side effects of drug combinations using artificial intelligence, according to a study published on July 10, 2018.

This study was conducted by the researchers at the Stanford University. Doctors are not aware of the side effects that might arise by adding another drug to a patient’s personal pharmacy. The main issue is that it is impractical to test a new drug in combination with all other drugs, as there are so many drugs in the market and for one drug there would be five thousand new experiments.

Computer science experts developed an artificial intelligence system that can predict the potential side effects from various drug combinations. The system was called as Decagon and it is expected to help doctors in making better decisions about which drugs to describe and help researchers find better combinations of drugs to treat complex diseases. There are around 1000 different known side effects and 5,000 drugs in the market, making for nearly 125 billion possible side effects between all possible pairs of drugs.

However, researchers realized that this problem can be solved by studying the effect of drugs on the cellular machinery in our body. A massive network was composed by them, which describes how over 19,000 proteins in our bodies 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.

Leskovec, a member of Stanford Bio-X, Stanford Neurosciences Institute and the Chan Zuckerberg Biohub, said, “It was surprising that protein interaction networks reveal so much about drug side effects.” At present, this system is capable of finding side effects associated with pairs of drugs. In the future, the research team hopes to extend their results to include more complex regimens.


Comments are closed.