A research team from the Korea Advanced Institute of Science and Technology has developed an AI model to predict adverse effects between oral anti-COVID-19 drugs and prescription drugs.
Researchers from KAIST’s Department of Biochemical Engineering created a new version of the DeepDDI AI-based drug interaction prediction model to test how ritonavir and nirmatrelvir, two components of pharmaceutical giant Pfizer’s Paxlovid, would interact with prescription drugs.
The new DeepDDI2 model can calculate and process a total of 113 types of drug interactions, according to a press release.
Paxlovid was later found to interact with approximately 2,248 prescription drugs: 1,403 drugs with ritonavir and 673 drugs with nirmatrelvir.
The researchers then offered alternative options for prescription drugs with high adverse effects with Paxlovid: They found 124 drugs with low potential adverse effects with ritonavir and 239 drugs with nirmatrelvir.
WHY IS IT IMPORTANT
COVID-19 patients with comorbidities, such as high blood pressure and diabetes, are likely to take antiviral drugs along with other drugs. However, drug interactions and adverse drug effects with Paxlovid “have not been sufficiently investigated,” the KAIST researchers said. Using AI technology, they then set out to explore how the continued use of antiviral therapy along with other drugs can lead to serious and unwanted complications.
THE GREAT TREND
Pfizer is on the verge of obtaining full US Food and Drug Administration approval for Paxlovid. It comes as an advisory committee voted last week to recommend approval because it deems the drug safe and effective. The company received emergency use approval for Paxlovid from the regulator in December 2021. Following the vote of advisors, the US FDA is expected to make a final decision on its full approval by May .
REGISTRATION
“The results of this study are significant at times like when we should resort to the use of hastily developed drugs in the face of emergencies like the COVID-19 pandemic. [With DeepDDI2]it is now possible to very quickly identify and take the necessary action against adverse drug reactions caused by drug interactions,” Professor Sang Yup Lee of KAIST said in a statement.