Machine learning-aided multidimensional phenotyping of Parkinson's disease patient stem cell-derived midbrain dopaminergic neurons

Abstract

Combining multiple Parkinsons disease (PD) relevant cellular phenotypes might increase the accuracy of midbrain dopaminergic (mDA) in vitro models. We differentiated patient-derived induced pluripotent stem cells (iPSCs) with a LRRK2 G2019S mutation, isogenic control and genetically unrelated iPSCs into mDA neurons. Using automated fluorescence microscopy in 384-well plate format, we identified elevated levels of -synuclein and Serine 129 phosphorylation (pS129), reduced dendritic complexity, and mitochondrial dysfunction. Next, we measured additional image-based phenotypes and used machine learning (ML) to accurately classify mDA neurons according to their genotype. Additionally, we show that chemical compound treatments, targeting LRRK2 kinase activity or -synuclein levels, are detectable when using ML classification based on multiple image-based phenotypes. We validated our approach using a second isogenic patient derived SNCA gene triplication mDA neuronal model. This phenotyping and classification strategy improves the exploitability of mDA neurons for disease modelling and the identification of novel PD drug targets.