summary: Researchers have used AI to quickly discover treatments for Parkinson's disease. They used machine learning techniques to screen millions of compounds and were able to identify five promising candidates that prevent harmful aggregation of alpha-synuclein, a key protein in Parkinson's disease.
This AI-powered approach could speed up the screening process by 10 times, significantly reduce costs, and bring new treatments to patients faster. This discovery represents an important advance in drug discovery.
Important facts:
- The AI approach enabled the identification of compounds that inhibit α-synuclein aggregation, significantly speeding up a process that previously took years.
- Improvements in screening efficiency were 10 times faster, costs were reduced by 1,000 times, and drug discovery efficiency was significantly increased.
- More than 6 million people worldwide are affected by Parkinson's disease, and that number is expected to triple by 2040, highlighting the urgent need for effective treatments.
sauce: cambridge university
Researchers have used artificial intelligence techniques to significantly accelerate the search for treatments for Parkinson's disease.
Researchers at the University of Cambridge designed and used an AI-based strategy to identify compounds that block the aggregation, or aggregation, of alpha-synuclein, a protein that is a hallmark of Parkinson's disease.
The team used machine learning techniques to rapidly screen a chemical library containing millions of entries and identified five highly potent compounds for further investigation.
Parkinson's disease affects more than 6 million people worldwide, and that number is expected to triple by 2040. Currently, there are no disease-modifying treatments for Parkinson's disease.
The process of screening drug candidates from large chemical libraries must occur long before potential treatments can be tested in patients, is extremely time-consuming, expensive, and often unsuccessful.
By using machine learning, researchers were able to speed up the initial screening process by a factor of 10 and cut costs by a factor of 1,000. This could mean potential treatments for Parkinson's disease could reach patients much faster.
Results will be reported in a journal natural chemical biology.
Parkinson's disease is the most rapidly progressing neurological disease worldwide. In the UK, one in every 37 people currently alive will be diagnosed with Parkinson's disease in their lifetime.
In addition to motor symptoms, Parkinson's disease can also affect the gastrointestinal system, nervous system, sleep patterns, mood, and cognition, which can lead to decreased quality of life and significant disability.
Proteins are responsible for important cellular processes, and in Parkinson's disease, these proteins go out of control and cause nerve cell death. When proteins misfold, abnormal clusters called Lewy bodies form, which can accumulate in brain cells and interfere with their normal function.
Professor Michel Wendruskoro, from the Yusuf Hameed Department of Chemistry, said: “One route to exploring potential treatments for Parkinson's disease could include inhibiting the aggregation of alpha-synuclein, a protein closely associated with the disease. “Identification of small molecules is necessary.” He led the research.
“However, this is a very time-consuming process, and it can take months or even years just to identify good candidates for further testing.”
Although clinical trials for Parkinson's disease are currently underway, no disease-modifying drugs have been approved, reflecting the inability to directly target the molecular species that cause the disease.
This has been a major stumbling block in Parkinson's disease research, as there is a lack of ways to identify and address the right molecular targets. This technological gap significantly hinders the development of effective treatments.
The Cambridge team developed a machine learning method that screens chemical libraries containing millions of compounds to identify small molecules that bind to amyloid aggregates and block their growth.
We then experimentally tested a small number of the top compounds to select the most potent aggregation inhibitors.
The information obtained from these experimental assays was iteratively fed back into the machine learning model, and highly potent compounds were identified after several iterations.
“Instead of screening experimentally, we are screening computationally,” said Wendruscoro, co-director of the Center for Misfolding Diseases.
“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.”
Using this method, the Cambridge team developed a compound that targets pockets on the surface of the aggregates that are responsible for the exponential growth of the aggregates themselves. These compounds are hundreds of times more potent and much cheaper to develop than previously reported compounds.
“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 we can start working on multiple drug discovery programs instead of just one. The significant savings in time and cost will enable us to do a lot more, which is exciting right now.” It's a time.”
Funding: The research was carried out at the Institute of Health Chemistry in Cambridge, which was established with support from the UK Research Partnership Investment Fund (UKRPIF) to facilitate the translation of academic research into clinical programmes.
About this AI and Parkinson's disease research news
author: sarah collins
sauce: cambridge university
contact: Sarah Collins – University of Cambridge
image: Image credited to Neuroscience News
Original research: Open access.
“Discovery of potent inhibitors of α-synuclein aggregation using structure-based iterative learning” Michele Vendruscolo et al. natural chemical biology
abstract
Discovery of potent inhibitors of α-synuclein aggregation using structure-based iterative learning
Machine learning techniques have the potential to reduce the cost and failure rate of traditional drug discovery pipelines.
This problem is particularly pressing for neurodegenerative diseases, where the development of disease-modifying drugs is particularly difficult.
To address this issue, we here describe a machine learning approach to identify small molecule inhibitors of α-synuclein aggregation, a process implicated in Parkinson's disease and other synucleinopathies.
Because α-synuclein aggregate growth occurs through autocatalytic secondary nucleation, we aim to identify compounds that bind to catalytic sites on the surface of the aggregates.
To achieve this goal, we iteratively use structure-based machine learning to first identify and then step-wise optimize secondary nucleation inhibitors.
Our results show that this approach leads to the facile identification of compounds that are two orders of magnitude more potent than those previously reported.
