AI method accelerates drug discovery for Parkinson's disease by 10 times, research results

thank you. Listen to this article using the player above. ✖

Researchers at the University of Cambridge have harnessed the power of artificial intelligence (AI) to speed up screening for new drugs to treat Parkinson's disease.

The technique identified five highly potent potential drug candidates for further analysis, suggesting that the method could speed up the drug discovery process by 10 times.

This study natural chemical biology.

Development of disease-modifying treatments

Parkinson's disease affects more than 6 million people worldwide. It causes a wide range of symptoms, from characteristic motor symptoms to problems affecting the gut, sleep, mood, and cognition.

The number of people with Parkinson's disease is expected to triple by 2040, making it the world's fastest growing neurological disease. Despite the increasing burden of Parkinson's disease, no disease-modifying treatments that aim to directly target the mechanisms that cause the disease and improve symptoms have yet been approved for the disease.

Parkinson's disease is thought to be caused by rogue proteins that misfold and aggregate to form Lewy bodies, which eventually accumulate within nerve cells and cause dysfunction and even cell death.

Trials of potentially disease-modifying treatments for Parkinson's disease are underway, but experimental methods to identify the correct molecular targets are lacking, creating a technological gap that hinders their development.

“One route to exploring potential treatments for Parkinson's disease requires the identification of small molecules that can inhibit the aggregation of alpha-synuclein, a protein closely associated with the disease.” Mr. P, the author, said:Roff.Michele Wendruscoro, Professor of Biophysics in the Yusuf Hameed Department of Chemistry, Cambridge. “However, this is a very time-consuming process, and it can take months or even years just to identify good candidates for further testing.”

In a new study, Vendruscolo and colleagues at the University of Cambridge harnessed the power of AI to accelerate and reduce costs associated with drug development for Parkinson's disease.

Iterative screening with AI

Researchers have developed a machine learning-based approach that screens libraries containing millions of compounds to identify candidates that bind to protein aggregates and prevent their growth.

The top ranked compounds were then tested experimentally to find the one that most potently inhibited protein aggregation. This information is iteratively fed back into the machine learning model to ultimately identify the best candidate compound.

“Instead of screening experimentally, we screen computationally,” Vendruscolo explained. “By using the knowledge gained from the initial screen with a machine learning model, we were able to train the model to identify specific regions on these small molecules that are involved in binding. We can rescreen to find more potent molecules.”

This method allowed the researchers to develop compounds that target pockets on the surface of the aggregates that enable proliferation. These compounds are much more powerful and less expensive to develop than previous examples.

“Machine learning is having a real impact on the drug discovery process, speeding up the entire process of identifying the most promising candidates,” Vendruscolo said. “For us, this means that we can start working on multiple drug discovery programs instead of just one. , these are exciting times.”

reference: Horn RI, Andrzejewska EA, Alam P, et al. Discovery of potent inhibitors of alpha-synuclein aggregation using structure-based iterative learning. Nut Chem Biol. 2024.Doi: 10.1038/s41589-024-01580-x

This article is press release Published by the University of Cambridge. Material has been edited for length and content.