Drugs taken orally must pass through the digestive tract, aided by transporter proteins found in the lining of the tract. If two drugs use the same transporter, they can interfere with each other. Addressing this issue, a team of researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a strategy to identify the transporters used by different drugs. This information could improve patient treatment by ensuring that drugs that rely on the same transporter aren’t prescribed concurrently, thereby avoiding interference. The research could also boost drug development by helping design drugs that are more absorptive.
The team, led by Giovanni Traverso, used both tissue models and machine-learning algorithms in their research. They managed to reveal that a commonly prescribed antibiotic and a blood thinner could interfere with each other. Transporters they studied included BCRP, MRP2, and PgP. By using siRNA to knock down the expression of each transporter in pig intestinal tissue, the researchers were able to see how each transporter interacts with different drugs. They studied how each drug would behave when certain transporters were not available, giving them insights into which transporters each drug uses.
The researchers tested 23 commonly used drugs, subsequently training a machine-learning model on their data and data from several drug databases. The model could then predict which drugs would interact with which transporters based on the drugs’ chemical structures. In analyzing 28 existing drugs and 1,595 experimental drugs, the model made almost 2 million predictions of potential drug interactions.
Patient data was used to confirm the model’s predictions. This revealed that prescribing doxycycline and warfarin together increases warfarin levels in the bloodstream. The model also correctly predicted that the absorption of doxycycline is affected by digoxin, levetiracetam, and tacrolimus. Interestingly, the drug tacrolimus was the only one from the list previously suspected to interact with doxycycline. This discovery, made possible by the new model, highlights the potential safety implications of prescribing certain drugs together.
This approach is not just beneficial in identifying potential interactions between existing drugs, but also instrumental in the development of new drugs. The technology enables drug developers to fine-tune new drug molecules to either prevent interactions with other drugs or improve their absorptivity. Biotech company Vivtex, co-founded by former MIT postdoc Thomas von Erlach, MIT Institute Professor Robert Langer, and Traverso, is currently exploring this kind of drug-tuning. Funding for the research was provided partially 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.