Reviewed by Lexie CornerJan 29 2025
In a study published in npj Parkinson's Disease, researchers from the Cleveland Clinic Genome Center successfully used advanced AI-driven genetic models to analyze Parkinson’s disease.
Feixiong Cheng, Ph.D., and a Cleveland Clinic research team have successfully applied advanced artificial intelligence genetics models to Parkinson's disease. Image Credit: Cleveland Clinic
Researchers identified genetic markers associated with disease progression and pinpointed FDA-approved drugs with potential for repurposing in Parkinson’s disease treatment.
The study uses a “systems biology” method, which employs artificial intelligence to integrate and analyze diverse datasets—including genetic, proteomic, pharmacological, and clinical patient data. This multi-layered analysis enables the identification of complex patterns that may not be detectable when examining a single data type in isolation.
Feixiong Cheng, Ph.D., the study’s lead investigator and Director of the Cleveland Clinic Genome Center, is a leading expert in systems biology. He has developed multiple AI-driven frameworks aimed at discovering novel therapeutic targets, including potential treatments for Alzheimer’s disease.
Parkinson’s disease is the second most common neurodegenerative disorder, right after dementia, but we don’t have a way to stop or slow its progression in the millions of people who live with this condition worldwide; the best we can currently accomplish is managing symptoms as they appear. There is an urgent need to develop new disease-modifying therapies for Parkinson's disease.
Lijun Dou, Ph.D., Postdoctoral Fellow, Genomic Medicine Lab, Cleveland Clinic Genome Center
Developing compounds to slow or halt Parkinson’s disease progression remains a significant challenge, as researchers are still working to pinpoint which specific gene mutations drive particular symptoms, according to Dr. Dou.
“Many of the known genetic mutations associated with Parkinson's disease are in non-coding regions of our DNA, and not in actual genes. We know that variants in noncoding regions can, in turn, impact the function of different genes, but we don’t know which genes are impacted in Parkinson’s disease,” Dr. Dou added.
Using their integrative AI model, the researchers cross-referenced genetic variants associated with Parkinson’s disease against multiple brain-specific DNA and gene expression databases. This approach enabled them to determine whether genetic variations in noncoding regions of DNA influence gene activity in human brain tissue.
The team mapped the identified genes to protein and interactome databases to further validate their findings, assessing how alterations in these genes impact protein interactions in the brain. This analysis revealed several potential risk genes, including SNCA and LRRK2, many of which are implicated in neuroinflammation when dysregulated.
The next step was to investigate whether any existing drugs could be repurposed to target these genes. Given that drug development and approval can take an average of 15 years, even after identifying promising candidates, repurposing FDA-approved drugs offers a potentially faster route to new treatments.
Individuals currently living with Parkinson’s disease can’t afford to wait that long for new options as their conditions continue to progress. If we can use drugs that are already FDA-approved and repurpose them for Parkinson’s disease, we can significantly reduce the amount of time until we can give patients more options.
Feixiong Cheng, Ph.D., Study Lead and Director, Cleveland Clinic Genome Center
By integrating their genetic findings with existing pharmaceutical databases, the team identified several potential drug candidates. They then analyzed electronic medical records to assess whether patients taking these drugs exhibited different Parkinson’s disease outcomes. For instance, individuals who had been prescribed the cholesterol-lowering drug simvastatin showed a reduced lifetime risk of developing Parkinson’s disease.
According to Dr. Cheng, the next step is to evaluate simvastatin’s therapeutic potential in preclinical laboratory models. Additionally, several immunosuppressive and anxiolytic drugs identified in the analysis warrant further investigation.
Dr. Dou concluded, “Using traditional methods, completing any of the steps we took to identify genes, proteins and drugs would be very resource- and time-intensive task. Our integrative network-based analyses allowed us to speed this process up significantly and identify multiple candidates which ups our chance of finding new solutions.”
This study was funded by grants from the National Institutes of Health (NIH)'s National Institute on Aging (NIA) and National Institute of Neurological Disorders and Stroke (NINDS).
Journal Reference:
Dou, L., et. al. (2025) A network-based systems genetics framework identifies pathobiology and drug repurposing in Parkinson’s disease. npj Parkinson's Disease. doi.org/10.1038/s41531-025-00870-y