MIT Team Unveils New Strategy to Identify Drug Absorption Pathways

A team led by MIT researchers has made significant strides in understanding how orally administered drugs are absorbed in the digestive tract. The innovative approach combines a tissue model and machine learning to identify the specific transporters that drugs use to pass through the gastrointestinal tract lining.

“One of the challenges in modeling absorption is that drugs are subject to different transporters. This study is all about how we can model those interactions, which could help us make drugs safer and more efficacious, and predict potential toxicities that may have been difficult to predict until now,” says Giovanni Traverso, senior author of the study published in Nature Biomedical Engineering.

The research focused on three key transporters: BCRP, MRP2, and PgP. By utilizing a laboratory-grown pig intestinal tissue model, the researchers were able to measure drug absorbability and determine the role of individual transporters. They achieved this by using siRNA to suppress transporter expression and observing the impact on drug absorption.

The study tested 23 commonly used drugs, which helped in mapping out the transporters each drug utilized. Building on this data, the researchers trained a machine-learning algorithm to predict drug-transporter interactions based on drug chemical structures. The model's predictions were then validated using patient data from Massachusetts General Hospital and Brigham and Women’s Hospital, revealing that the antibiotic doxycycline could interfere with the blood thinner warfarin and other medications.

This novel method not only helps in predicting potential drug interactions but also aids in enhancing drug safety and efficacy. It could also be instrumental for drug developers in improving the absorbability of new drugs by adjusting their formulations to interact better with transporters.