Detecting more rare diseases through analysis in three dimensions

The European Regional Development Fund (EFRO) and the province of Gelderland are financially supporting the project ‘Diagnostics-in-3D’ with more than half a million euros. The aim of the project is to improve diagnostics of patients with rare diseases through a combination of artificial intelligence, smart computing power and genetics. For this project Radboudumc, together with the companies Bio-Prodict and Vartion from the Nijmegen region will join forces.

Bio-Prodict has automated the prediction of the effect of missense mutations on proteins with the AI-based Helix platform. By using anonymous patient data and AI from Radboudumc and innovative computing infrastructure provided by Vartion, major steps can be taken in predicting the effect of mutations on the 3D structure of a protein, and thus on its function. For this, the representation of the 3D protein data, the deep learning architecture to be used and the computing power will be optimized. In the “Diagnostics-in-3D “project, Bio-Prodict, Vartion and Radboudumc aim to automate and accelerate diagnostics for rare diseases. In doing so, they will mainly focus on the rare diseases that cause intellectual disabilities, a subject in which Radboudumc in Nijmegen has already built up a great deal of expertise.