Parkinson's Disease
Predicting the onset of PD using whole-genome sequencing data
Project page TBD, but here is the preprint in the meantime!
In short, we processed WGS data from >2500 patients to build a ML model to predict the onset of Parkinson’s Disease based on germline mutations. Our model achieved an ROC-AUC of 0.77 on the held-out test-set. Genes with high importance scores pointed to pathways such as immune response and protein modifications.
Machine Learning Prediction of Parkinson’s Disease Onset and Subtype Using Germline Variants