Written by : Jayati Dubey
January 29, 2025
The research team used an AI-driven integrative model to analyze genetic data from brain-specific DNA and gene expression databases.
Researchers from the Cleveland Clinic Genome Center (CCGC) have successfully applied advanced artificial intelligence (AI) models to study Parkinson’s disease (PD), identifying genetic factors influencing disease progression and potential FDA-approved drugs that could be repurposed for treatment.
The findings, published in npj Parkinson’s Disease, highlight how AI-driven systems biology can integrate diverse datasets—including genetic, proteomic, pharmaceutical, and patient data—to uncover hidden patterns that may lead to new treatment strategies.
Parkinson’s disease is the second most common neurodegenerative disorder after dementia, yet there is no existing cure or method to slow disease progression.
Current treatments focus solely on managing symptoms, leaving millions of patients worldwide without long-term solutions.
"There is an urgent need to develop new disease-modifying therapies for Parkinson’s disease," said Dr. Lijun Dou, a postdoctoral fellow in Dr. Feixiong Cheng’s Genomic Medicine Lab and the study’s first author.
Developing drugs that can halt or reverse Parkinson’s disease is especially difficult due to gaps in understanding how genetic mutations contribute to the disorder.
Many mutations associated with Parkinson’s occur in non-coding regions of DNA, meaning they don’t directly alter genes but can still influence gene function.
"We know that variants in non-coding regions can impact different genes, but we don’t know which genes are affected in Parkinson’s disease," Dr. Dou explained.
To address this challenge, the research team used an AI-driven integrative model to analyze genetic data from brain-specific DNA and gene expression databases.
This approach allowed them to identify specific genes affected by non-coding DNA variants.
By combining their findings with protein interaction datasets, the team pinpointed several key risk genes linked to Parkinson’s disease, including SNCA and LRRK2.
Many of these genes are known to trigger inflammation in the brain when dysregulated, suggesting that targeting inflammation could be a promising treatment strategy.
Once the researchers identified potential risk genes, they explored whether existing FDA-approved drugs could be repurposed to target these genes.
Developing new drugs from scratch is a time-consuming and expensive process, often taking 15 years or more for approval. Repurposing existing drugs offers a faster and more cost-effective alternative.
"Individuals currently living with Parkinson’s disease can’t afford to wait that long for new treatment options," said Dr. Cheng, the study’s lead researcher and director of CCGC.
"If we can use already FDA-approved drugs, we can significantly reduce the time needed to provide new treatment options."
To identify promising drug candidates, the team integrated genetic findings with pharmaceutical databases and analyzed electronic health records (EHRs) for insights into patient outcomes.
One notable discovery was that individuals who had taken simvastatin, a commonly prescribed cholesterol-lowering drug, were less likely to develop Parkinson’s disease over their lifetime.
This suggests that simvastatin may have protective effects against Parkinson’s, making it a strong candidate for further laboratory testing.
Beyond simvastatin, the researchers also identified several immunosuppressive and anti-anxiety medications that may have potential in Parkinson’s treatment and warrant further study.
Traditionally, the process of identifying disease-related genes, understanding their impact on proteins, and testing potential drugs is highly time- and resource-intensive.
The AI-driven network-based approach used in this study significantly accelerated these steps, increasing the chances of finding effective treatment options.
"Using traditional methods, completing any of these steps would take significant time and resources," said Dr. Dou.
"Our AI-based approach allowed us to speed up the process and identify multiple promising drug candidates in a much shorter timeframe."
The next phase of research will focus on testing simvastatin’s potential as a Parkinson’s treatment in laboratory models.
Additionally, the team will evaluate other promising drugs, particularly those affecting inflammation pathways in the brain.
This study was supported by grants from the National Institute on Aging (NIA) and the National Institute of Neurological Disorders and Stroke (NINDS), both part of the National Institutes of Health (NIH).
Stay tuned for more such updates on Digital Health News.