Skip to main content

KU Leuven and SandboxAQ Join Forces to Accelerate Parkinson’s Treatment Discovery with AI

 Formfees 20/01/2025

Professor Peter Vangheluwe’s lab at KU Leuven is collaborating with SandboxAQ, an AI company, to accelerate the discovery and testing of drug candidates that can restore the function of ATP10B. ATP10B is a protein associated with protection against Parkinson’s disease. This innovative AI technology will accelerate and expand the search for molecules that can improve ATP10B function, paving the way for new treatments for Parkinson’s disease.

Building on research grants from the Michael J. Fox Foundation for Parkinson’s Research and the Aligning Science Across Parkinson’s Initiative, the Vangheluwe lab, in collaboration with SandboxAQ’s AI platform, will contribute to a better understanding of the underlying mechanisms of ATP13A2 and ATP10B dysfunction in Parkinson’s.

In Parkinson’s disease, communication and energy management in brain cells are disrupted. The ATP10B gene plays an essential role in this by supporting the transport of a specific type of fat molecule (glucosylceramide) within cells. If this process goes wrong, brain cells have difficulty surviving.

The ATP10B protein is very complex, and we do not yet fully understand how it can move fat molecules. However, scientists are looking for drugs (small molecules) that can help the protein function better. This could potentially limit or prevent the damage to brain cells caused by Parkinson’s.

The laboratory of Professor Peter Vangheluwe at KU Leuven is a world leader in unravelling the disease mechanism of Parkinson’s disease and has previously made important discoveries about the role of various genes in the development of the disease.

For this project, Professor Vangheluwe’s Laboratory for Cellular Transport Systems is collaborating with the Centre for Drug Design and Discovery (CD3) of KU Leuven Research and Development and SandboxAQ, a spin-off from Alphabet Inc (the parent company of Google).

SandboxAQ uses advanced AI simulations and Large Quantitative Models (LQMs) to accelerate and improve drug discovery projects, using methods such as protein folding, free energy calculations, and protein language models to design both small molecules and antibodies. Their in-house AI and physics-based structure prediction capabilities, which have already demonstrated remarkable accuracy in multiple projects for biotech and large pharmaceutical companies, will be used to decipher the structure of ATP10B.

This is crucial to understand the formation of the protein, identify the structural basis of the relevant state for activation and find binding sites. The structure prediction will allow to apply an integrated virtual screening workflow combining active learning methods with physics-based methods in the search for activators of the ATP10B system, thus unlocking the potential of the protein.

Contest Video

Enquiry Form

Advertisement

Tags

Recent Article

Testimonials

Social Media Auto Publish Powered By : XYZScripts.com