AI semantic similarity study leads to new drug candidates for Parkinson’s disease

Summary: Using AI, the researchers identified Probucol, an existing cholesterol-lowering drug that promotes the removal of mitochondria, as a potential new therapy for the treatment of Parkinson’s disease.

Source: OLP

The words researchers use to describe their findings can be harnessed to uncover potential new treatments for Parkinson’s disease, according to a new study published March 2 in the open-access journal PLoS Biology by Angus McQuibban of the University of Toronto, Canada, and colleagues.

The study used an artificial intelligence (AI) system to identify an existing cholesterol-lowering drug that has the ability to promote the removal of mitochondria, energy components of the cell that are damaged by disease.

The full pathogenetic pathway leading to Parkinson’s disease (PD) is unknown, but one clear contributor is mitochondrial dysfunction and the inability to get rid of defective mitochondria, a process called mitophagy.

At least five genes implicated in PD are linked to impaired mitophagy, either directly or indirectly, and so the authors searched for compounds that might enhance the process of mitophagy.

Several of these compounds have been identified, but most of them also cause cell damage, ruling them out as drug candidates. This led the authors to wonder if the literature describing these compounds might lead them to other compounds, those not previously linked to improved mitophagy but described with terms that also appear in articles dealing with known activators.

Identifying patterns of such semantic similarity is one of the core competencies of IBM Watson for Drug Discovery, an AI program running on a supercomputer that scans published literature for patterns of keywords, d expressions and juxtapositions.

The team used the program to develop a semantic “fingerprint” of authentic mitophagy enhancers, then searched the literature for similar fingerprints on a pool of over three thousand candidates from a drug database. .

The 79 best candidates were screened in cell culture against a mitochondrial poison. The top three candidates in this test were then tested on several other mitophagy tests, which identified the cholesterol-lowering drug probucol as the compound with the best combination of efficacy and likely safety.

Probucol was also found to improve motor function, survival, and neuron loss in two different animal models of Parkinson’s disease (PD is primarily a movement disorder).

This shows the outline of the faces
At least five genes implicated in PD are linked to impaired mitophagy, either directly or indirectly, and so the authors searched for compounds that might enhance the process of mitophagy. Image is in public domain

The effect of probucol on mitophagy required the formation and action of lipid droplets, transient cellular structures that help maintain mitochondrial integrity during stress and which accumulate abnormally in Parkinson’s disease.

Probucol is known to target ABCA1, a protein involved in lipid transport, and reducing ABCA1 levels reduced the ability of probucol to promote mitophagy, suggesting that ABCA1 is a likely mediator of the role of droplets lipids in mitophagy.

“Our study presented a dual in silico/cellular screening methodology that identified known and novel mechanisms leading to improved mitophagy,” McQuibban said.

“Given the link between lipid droplet accumulation and ABCA1, it seems likely that probucol enhances mitophagy through lipid droplet mobilization. Targeting this mechanism may be advantageous.

McQuibban adds, “In our study, we used the IBM Watson AI platform to efficiently identify currently approved drugs that could potentially be reused as therapies for Parkinson’s disease.

About this research news on AI, Parkinson’s disease and neuropharmacology

Author: Press office
Source: OLP
Contact: Press office – PLOS
Picture: Image is in public domain

See also

This shows a woman rubbing her shoulder

Original research: Free access.
“AI-guided screen identifies probucol as an activator of mitophagy through lipid droplet modulation” by Angus McQuibban et al. PLOS Biology


AI-guided screening identifies probucol as an activator of mitophagy through modulation of lipid droplets

Failures in mitophagy, a process by which damaged mitochondria are eliminated, lead to neurodegeneration, while improved mitophagy promotes the survival of dopaminergic neurons.

Using an artificial intelligence platform, we used a natural language processing approach to assess the semantic similarity of candidate molecules with a set of well-established mitophagy enhancers.

The best candidates were selected in a cell-based mitochondrial clearance assay. Probucol, a lipid-lowering drug, has been validated in several orthogonal mitophagy assays. In vivo, probucol improved survival, locomotor function, and loss of dopaminergic neurons in zebrafish and fly models of mitochondrial damage.

Probucol functioned independently of PINK1/Parkin, but its effects on mitophagy and in vivo depended on ABCA1, which negatively regulates mitophagy following mitochondrial damage. Autophagosome and lysosomal markers were elevated by probucol treatment in addition to increased contact between lipid droplets (DLs) and mitochondria. Conversely, LD expansion, which occurs after mitochondrial damage, was suppressed by probucol, and probucol-mediated improvement in mitophagy required LDs.

Probucol-mediated changes in LD dynamics may prime the cell for a more efficient mitophagic response to mitochondrial damage.

Leave a Comment