Using AI to Design Drugs from Scratch

I've written a number of times in the past about the growing use of Artificial Intelligence in the drug discovery process, whether it's in terms of identifying molecules for analysis or predicting potential side effects.

A recent paper from a team at the University of North Carolina at Chapel Hill Eshelman School of Pharmacy suggests that AI can now go one step further and design new drug molecules from scratch.

Their method, which is known as Reinforcement Learning for Structural Evolution (ReLeaSE), consists of two neural networks that the researchers refer to as the teacher and the student. The teacher component of the system understands the syntax and linguistic rules behind the chemical structures of around 1.7 million biologically active molecules. The student component they learn from these in order to propose molecules that can be used in new medicines.

The Language of Medicine

"If we compare this process to learning a language, then after the student learns the molecular alphabet and the rules of the language, they can create new 'words,' or molecules," the researchers say. "If the new molecule is realistic and has the desired effect, the teacher approves. If not, the teacher disapproves, forcing the student to avoid bad molecules and create good ones."

The team believes that ReLeaSE will be a powerful addition to the virtual screening process that is used by drug companies to identify viable drug candidates. By screening virtually, scientists can evaluate huge numbers of candidates relatively quickly and cost-effectively. Most screening approaches only work for known chemicals, however. ReLeaSE is different in that it has the ability to both create and evaluate new molecules.

"A scientist using virtual screening is like a customer ordering in a restaurant. What can be ordered is usually limited by the menu," the team explains. "We want to give scientists a grocery store and a personal chef who can create any dish they want."

The team tested ReLeaSE in the generation of a number of molecules with properties that they had previous specified, whether in terms of bioactivity or safety profiles. The platform was then used to design molecules with customized physical properties and then to design new compounds with inhibitory activity against a particular enzyme that is known to be linked with leukemia.

"The ability of the algorithm to design new, and therefore immediately patentable, chemical entities with specific biological activities and optimal safety profiles should be highly attractive to an industry that is constantly searching for new approaches to shorten the time it takes to bring a new drug candidate to clinical trials," the researchers conclude.