The system, called Decagon, could help doctors make better decisions about which drugs to prescribe and help researchers find better combinations of drugs to treat complex diseases, said Marinka Zitnik, a postdoctoral fellow at Stanford University in the US.
Once available to doctors in a more user-friendly form, Decagon's predictions would be an improvement over what is available now, which essentially comes down to chance - a patient takes one drug, starts taking another and then develops a headache or worse.
There are about 1,000 different known side effects and 5,000 drugs on the market, making for nearly 125 billion possible side effects between all possible pairs of drugs.
Most of these have never been prescribed together, let alone systematically studied.
Zitnik, Monica Agrawal, a master's student at Stanford, and colleagues realised they could get around that problem by studying how drugs affect the underlying cellular machinery in our body.
They composed a massive network describing how the more than 19,000 proteins in our bodies interact with each other and how different drugs affect these proteins.
Using more than four 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.
The team turned to deep learning, a kind of artificial intelligence modelled after the brain. In essence, deep learning looks at complex data and extracts from them abstract, sometimes counter-intuitive patterns in the data.
In this case, the researchers designed their system to infer patterns about drug interaction side effects and predict previously unseen consequences from taking two drugs together.
Just because Decagon found a pattern does not necessarily make it real, so the group looked to see if its predictions came true, and in many cases, they did.
For example, there was no indication in the team's data that the combination of atorvastatin, a cholesterol drug, and amlopidine, a blood pressure medication, could lead to muscle inflammation, yet Decagon predicted that it would, and it was right, researchers said.
Although it did not appear in the original data, a case report from 2017 suggested the drug combination had led to a dangerous kind of muscle inflammation, they said.
That example was born out in other cases as well. When they searched the medical literature for evidence of ten side effects predicted by Decagon but not in their original data, the team found that five out of the ten have recently been confirmed, lending further credence to Decagon's predictions.
(This story has not been edited by Business Standard staff and is auto-generated from a syndicated feed.)