We've updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.

Advertisement

Guidelines Developed for Using AI To Make Medicines Work Smarter

A collection of medication, with pills of different sizes, shapes and colors.
Credit: Myriam Zilles/ Unsplash
Listen with
Speechify
0:00
Register for free to listen to this article
Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

Read time: 2 minutes

The successful and safe delivery of therapeutics relies on understanding how easily drugs can pass through biological barriers which protect cells.


Drug permeability testing is essential in determining whether medicines can reach their intended targets in the body, but scientists have long struggled to achieve accurate and reproducible data.


There are three ways to measure the success of drug delivery; in the lab, in animals and humans, and using advanced computer simulations. However, the difficult process of matching the results from these three areas of testing continues to be a problem.

Bridging the gap

New research - led by the University of Portsmouth in collaboration with the University of Southampton, King’s College London, and the Massachusetts Institute of Technology - has developed a set of general guidelines for how to compare the values from lab experiments, molecular simulations and AI.


Dr Christian Jorgensen from the University of Portsmouth’s School of Medicine, Pharmacy and Biomedical Sciences, said: “Drug permeability testing is very important because if a drug can’t cross the right barriers, it won’t work properly, no matter how good it looks on paper.


“I spent some years working at a hospital in the US trying to compare permeability data measured in people and animals with computer simulated data, which was no easy feat. Each method of testing has an advantage, so ultimately this is about ensuring the best quality drugs and therapeutics make it to market.


“When you seek drug approval, the more evidence you can supply on the effectiveness of it, the more likely it will be approved. That’s why we’re seeing more and more convergence of the three testing areas.”

Want more breaking news?

Subscribe to Technology Networks’ daily newsletter, delivering breaking science news straight to your inbox every day.

Subscribe for FREE
Only 14 percent of drugs entering clinical trials between 2000 and 2015 received FDA approval in the US. Enhanced permeability testing could improve success rates by ensuring drugs effectively reach their targets while minimising side effects.

Testing the most complex systems

The study, published in the Journal of Chemical Information and Modeling, highlights the importance of understanding how drugs move across all biological barriers. This includes the most complex systems like the blood-brain barrier, which is a significant obstacle in delivering treatments for neurological conditions.


Dr Jorgensen explained: “The strength of the paper is we’ve not just tested the guidelines against a simple system of barriers in the body - we used one of the most complicated, which is also highly relevant in health and therapeutics.


“This work has the potential to accelerate the development of life-saving drugs, especially for conditions like brain disorders where drug delivery is notoriously difficult."


The new guidelines provide a comprehensive roadmap for improving the testing and modeling of drug permeability by looking at the differences of three areas:

  • On computers (In Silico): Scientists use computer programmes to predict how a drug might move through the body based on its chemical properties.

  • In the lab (In Vitro): They test the drug on cells in dishes to see how it behaves in controlled environments.

  • In humans/animals (In Vivo): Sometimes, they test the drug in a living body to see how it works.

Consistency and collaboration

The toolkit emphasises critical factors such as ensuring experimental consistency, addressing data variability, and adopting FAIR (Findable, Accessible, Interoperable, Reusable) principles for data sharing.


The authors also stress the importance of collaboration across fields to improve the accuracy of permeability testing and uncover new insights into drug delivery mechanisms.


Professor Martin Ulmschneider from King's College London said: “By providing clear benchmarks and recommendations, we hope to unify and refine permeability testing practices, and provide  a standardised set of guidelines.


"This is not just about improving individual experiments, it’s about creating a framework that allows the scientific community to compare their discoveries reliably." 


Reference: Jorgensen C, Linville RM, Galea I, et al. Permeability benchmarking:
Guidelines for comparing in silico, in vitro, and in vivo
measurements. J Chem Inf Model. 2025. doi: 10.1021/acs.jcim.4c01815


This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source. Our press release publishing policy can be accessed here.