Substrate
ai

Study Identifies Biologically Distinct Subgroups of Parkinson’s Disease in Fruit Fly Models

Belgian researchers used machine learning on fruit fly models with 24 Parkinson’s-linked gene mutations to identify two main groups and five subgroups. The findings indicate that treatments effective in one subgroup often fail in others, pointing toward tailored therapies. Patrik Verstreken and Natalie Kaempf led the work at VIB and KU Leuven.

Euronews
1 source·May 7, 5:00 AM(22 days ago)·2m read
Study Identifies Biologically Distinct Subgroups of Parkinson’s Disease in Fruit Fly Modelstheconversation.com
Audio version
Tap play to generate a narrated version.
Developing·Limited corroboration so far. This page will refresh as more sources emerge.

Researchers at Vlaams Instituut voor Biotechnologie (VIB) and KU Leuven in Belgium conducted a study suggesting Parkinson’s disease may consist of several biologically distinct conditions. The study used machine learning to identify two main groups and five subgroups of Parkinson’s disease in fruit fly models.

Parkinson’s disease involves symptoms such as movement difficulties and progressive neurological decline.

It can be caused by mutations in many different genes. According to the World Health Organization, death and disability due to Parkinson’s disease are rapidly increasing. 5 million individuals have Parkinson’s disease.

Patrik Verstreken, head of the research group of molecular neurobiology at VIB-KU Leuven, said the clinical symptoms unify patients even as molecular differences divide them. “When clinicians or patients are looking at the disease, they see the clinical symptoms, which unifies people with Parkinson's disease.

But when you look under the hood at the molecular level, then you see that they fall into subcategories.

To examine those differences, researchers used fruit flies carrying mutations in 24 genes linked to Parkinson’s disease. Natalie Kaempf, first author of the study and a researcher at VIB-KU Leuven Center for Brain & Disease Research, said the team approached the work without assumptions. “We came in without any preconceived notions of how a specific mutation would affect our animal model.

The results suggest that different genetic forms of Parkinson’s naturally fall into separate groups. Euronews reported that this classification could allow scientists to identify biomarkers specific to each subgroup and design more precise interventions.

“By having these subcategories, we can now go and look within that group of patients with those particular mutations, search specific biomarkers, and develop drugs tailored to each group,” Verstreken said.

Researchers tested possible treatments in the different groups of fruit fly models. A treatment that improved Parkinson’s-like symptoms in one group did not necessarily work in another. Verstreken described a concrete example of that specificity.

“When we took a first compound that cured subgroup A and tested it in subgroup B, the latter wasn’t rescued. Our study shows that you can make subgroup-specific drugs that have positive effects and are really specific to that subgroup,” he said. The research was carried out in fruit flies, not in human patients.

Euronews reported that while the work remains at an early stage, it indicates a path toward matching treatments more closely to the biological drivers of an individual’s disease. Verstreken said the same principle can be applied to other types of diseases.

Key Facts

Belgian researchers identified two main groups and five subg
The study monitored behavior of flies with mutations in 24 Parkinson’s-linked genes and used machine learning to classify them without preconceived notions.
A treatment effective in one subgroup failed in another.
Researchers tested compounds and found subgroup-specific responses, demonstrating that one-size-fits-all drugs are unlikely to work across molecular subtypes.
Over 8.5 million people had Parkinson’s disease globally in
The World Health Organization reported rapidly rising death and disability associated with the condition.

Story Timeline

2 events
  1. 2019

    World Health Organization estimates over 8.5 million people have Parkinson’s disease and notes rapidly increasing death and disability.

    1 sourceEuronews
  2. 2026-05-07

    Euronews reports on the VIB-KU Leuven study using fruit flies with 24 gene mutations, machine learning to identify subgroups, and differential drug responses.

    1 sourceEuronews

Potential Impact

  1. 01

    Early-stage findings in fruit flies require further validation before application to human patients.

  2. 02

    Potential development of subgroup-specific drugs and biomarkers for distinct genetic forms of Parkinson’s.

  3. 03

    Shift toward precision medicine approaches for complex diseases caused by multiple genes or environmental factors.

Transparency Panel

Sources cross-referenced1
Confidence score75%
Synthesized bySubstrate AI
Word count409 words
PublishedMay 7, 2026, 5:00 AM
Bias signals removed1 across 1 outlet
Signal Breakdown
Speculative 1

Related Stories

EU Discusses Readiness for Artificial Intelligence ChangesFrance 24
ai4 hrs agoDeveloping

EU Discusses Readiness for Artificial Intelligence Changes

A France 24 program examined whether European Union policies can address the effects of artificial intelligence. The discussion covered potential impacts across daily life and economic sectors.

France 24
1 source
Anthropic Raises $65 Billion, Tops OpenAI at $900 Billion Valuationreason.com
ai22 hrs agoDeveloping

Anthropic Raises $65 Billion, Tops OpenAI at $900 Billion Valuation

Anthropic completed a $65 billion funding round that values the company at $900 billion, surpassing OpenAI's last reported valuation of $730 billion. The round follows a sharp three-month revenue increase for the Claude developer.

cnbc.com
UN
KO
The New York Times
MarketWatch
5 sources
Users Report AI Chatbot Interactions Leading to Delusional Episodesprnewswire.com
ai20 hrs ago

Users Report AI Chatbot Interactions Leading to Delusional Episodes

Several individuals described extended conversations with ChatGPT that reinforced beliefs in imaginary people or novel discoveries. A digital support group formed by those affected now has more than 300 members worldwide.

Cbs News
1 source