Researchers from the University of Cambridge have developed an innovative approach to drug design for Parkinson's disease using artificial intelligence (AI) and machine learning techniques.
The breakthrough: AI and machine learning have reduced the time and cost of searching for Parkinson's treatments tenfold and a thousandfold, respectively.
“One route to search for potential treatments for Parkinson’s requires the identification of small molecules that can inhibit the aggregation of alpha-synuclein, which is a protein closely associated with the disease. But this is an extremely time-consuming process – just identifying a lead candidate for further testing can take months or even years.” —Michele Vendruscolo, Ph.D. of the Yusuf Hamied Department of Chemistry, University of Cambridge
Why it matters
AI expedites the process of bringing potential treatments to the clinical trial phase.
The challenge
- Parkinson’s affects more than six million people worldwide, with that number projected to triple by 2040.
- No disease-modifying treatments for the condition are currently available.
- The condition impacts motor skills and can affect the gastrointestinal system, nervous system, sleeping patterns, mood, and cognition, leading to a reduced quality of life and significant disability.
Dr. Michele Vendruscolo, lead researcher, University of Cambridge
The backstory
- With Parkinson's, proteins misfold and form abnormal clusters called Lewy bodies.
- Lewy bodies build up inside brain cells, causing them to stop functioning correctly.
- Identifying molecules that inhibit this aggregation is crucial in developing effective treatments.
- Using AI, the Cambridge team screened a library containing millions of chemical compounds. They found five that block alpha-synuclein clumping, the protein associated with Parkinson's.
How it worked
The Cambridge team's use of AI successfully identified highly potent compounds that target the exponential proliferation of Lewy bodies
- These compounds are far cheaper to develop and hundreds of times more potent than previously reported ones.
- This breakthrough allows researchers to explore multiple drug discovery programs simultaneously, accelerating the search for a cure.
“Machine learning is having a real impact on drug discovery — it’s speeding up the whole process of identifying the most promising candidates." —Michele Vendruscolo, Ph.D.
