High-content phenotyping of Parkinson's disease patient stem cell-derived midbrain dopaminergic neurons using machine learning classification

• Published in: Stem cell reports 2022-10, Vol.17 (10), p.2349-2364
• Main Authors: Vuidel, Aurore, Cousin, Loïc, Weykopf, Beatrice, Haupt, Simone, Hanifehlou, Zahra, Wiest-Daesslé, Nicolas, Segschneider, Michaela, Lee, Joohyun, Kwon, Yong-Jun, Peitz, Michael, Ogier, Arnaud, Brino, Laurent, Brüstle, Oliver, Sommer, Peter, Wilbertz, Johannes H.
• Format: Article
• Language: English
• Subjects: disease modeling; iPSC; LRRK2; machine learning; Parkinson's disease; Resource; SNCA
• ISSN: 2213-6711; 2213-6711
• DOI: 10.1016/j.stemcr.2022.09.001

Combining multiple Parkinson's disease (PD) relevant cellular phenotypes might increase the accuracy of midbrain dopaminergic neuron (mDAN) in vitro models. We differentiated patient-derived induced pluripotent stem cells (iPSCs) with a LRRK2 G2019S mutation, isogenic control, and genetically unrelated iPSCs into mDANs. Using automated fluorescence microscopy in 384-well-plate format, we identified elevated levels of α-synuclein (αSyn) and serine 129 phosphorylation, reduced dendritic complexity, and mitochondrial dysfunction. Next, we measured additional image-based phenotypes and used machine learning (ML) to accurately classify mDANs according to their genotype. Additionally, we show that chemical compound treatments, targeting LRRK2 kinase activity or αSyn 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 mDAN model which overexpresses αSyn. This phenotyping and classification strategy improves the practical exploitability of mDANs for disease modeling and the identification of novel LRRK2-associated drug targets. [Display omitted] •Parkinson’s disease phenotypes are present in two midbrain neuronal models•Assay automation and adaption to 384-well plates•Machine learning classifies neuronal genotypes based on image-extracted features•Machine learning identifies drug-treated neurons based on image-extracted features In this article, Wilbertz and colleagues show that machine learning based on phenotypic features can distinguish Parkinson’s disease patient stem cell-derived dopaminergic neurons from isogenic controls. LRRK2 G2019S or SNCA triplication neurons were fluorescently stained, and quantitative phenotypic features were extracted. The resulting phenotypic profiles allowed classification algorithms to identify different genotypes and the detection of chemical compound effects.