In a recent study published in Nature Biomedical Engineering, researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a strategy using tissue models and machine-learning algorithms to identify the transporters used by specific drugs. This is important because certain drugs rely on the same transporters, and if taken together, they can interfere with each other.
The study focused on three transporters in the gastrointestinal (GI) tract – BCRP, MRP2, and PgP. The researchers used a tissue model to measure drug absorbability and knocked down the expression of each transporter with short RNA strands. This allowed them to study how each transporter interacts with different drugs.
They tested 23 commonly used drugs and trained a machine-learning model to predict drug interactions based on similarities between chemical structures. The model successfully predicted interactions, including one between the antibiotic doxycycline and the blood thinner warfarin. This prediction was confirmed when data from patients showed an increase in warfarin levels when doxycycline was prescribed.
This approach can also be used to identify potential interactions between new drugs currently in development and could improve drug absorbability. These findings could lead to the development of new oral drug delivery systems and improve patient safety. The study was funded in part by the U.S. National Institutes of Health, the Department of Mechanical Engineering at MIT, and the Division of Gastroenterology at Brigham and Women’s Hospital.