Connect with us


AI identifies new potential treatments for Parkinson’s disease




AI identifies new potential treatments for Parkinson's disease

A new artificial intelligence (AI)-based strategy has significantly accelerated the identification of potential new drugs for the treatment of Parkinson’s disease. The work, published in the magazine Nature Chemical Biologycould mean new treatments for Parkinson’s disease reach clinical trials and patients faster.

Discovering drugs for serious diseases is often a slow, difficult and expensive process. Developing a drug typically takes from early laboratory testing to full approval for use in patients 10-15 year.

“This is an extremely time-consuming process – just identifying a lead candidate for further testing can take months or even years,” says Michele Vendruscolo, head of the study and professor at the Yusuf Hamied Department of Chemistry at the University of Cambridge. in the United Kingdom

AI and machine learning techniques have shown promise in accelerating the first phase of this process, discovering potential drugs for this purpose cancers and several other diseases, dozens of which lead to it biomedical start-up companies to bet on the potential of AI for drug discovery.

“One route to search for potential treatments for Parkinson’s disease requires the identification of small molecules that can inhibit the aggregation of alpha-synuclein, a protein closely linked to the disease,” Vendruscolo says in a study. press release.

The new study showed how an AI-based strategy significantly accelerated this process and was a thousand times cheaper than traditional methods, identifying a small number of potentially useful compounds that were taken for laboratory testing. The results of these experiments were then fed back to the machine learning model to further optimize the predictions.

“The use of AI to develop machine learning approaches for drug discovery for protein aggregation diseases such as Parkinson’s disease has finally arrived,” said Michael S. Okun, MD, national medical advisor for the Parkinson’s Foundation and director of the Fixel Institute for Neurological Diseases at the University of Florida. “The more than 20-fold improvement over typical hit rates in drug screening was impressive in this study and will add to the list of potential drugs to be considered for clinical trials,” he added. Okun, who was not involved in the investigation.

Almost 90,000 Americans According to the Parkinson’s Foundation, Parkinson’s disease is diagnosed every year, with one million people in the US currently living with the disease. Despite this, there are currently no curative treatments for the disease, only medications to manage symptoms, including tremors, balance and mobility problems, and muscle stiffness.

“Machine learning has a real impact on drug discovery: it accelerates the entire process of identifying the most promising candidates,” said Vendruscolo. “For us, this means we can work on multiple drug discovery programs – instead of just one. So much is possible thanks to the huge reduction in both time and costs – it’s an exciting time.”

However, discovering promising new compounds is only one, very early step in actually making proven medicines available to patients.

“However, whether this innovation will accelerate the discovery of new Parkinson’s drugs is complicated, as the introduction of more compounds could actually slow down the pipeline,” Okun said. “There will thus be a need for a parallel and major investment in basic science research to better understand the pathogenesis of Parkinson’s disease and more accurately apply this, and other new AI-based drug discovery methods.”