Peter Sommer

This study investigates how SNCA triplication affects neuronal extracellular vesicle biology and microglial activation in Parkinson's disease using iPSC-derived models.

The paper develops an imaging and analysis framework to map human microglial activation states using handcrafted and deep learning features, showing deep learning features achieve high classification accuracy and correlate with biological states.

The paper introduces DeepTaskGen, a deep learning method that generates synthetic task-based contrast maps from resting-state fMRI data, outperforming benchmarks and enabling biomarker development for cognitive tasks.

The paper identifies compounds that restore morphology in Parkinson's disease neurons by targeting mitochondrial uncoupling.

The paper presents a comprehensive genetic perturbation dataset using Cell Painting to analyze gene expression effects in human cells, revealing novel gene clusters and functional relationships.

This study screens small molecules in SHANK3-deficient neuronal models to identify compounds that rescue developmental and synaptic defects in Phelan-McDermid syndrome.

This paper uses conditional generative models to transform cell images between conditions, revealing hidden phenotypes by removing natural cell variability.

Cell Painting images and profiles for 115,796 compounds in U2OS cells from 12 laboratories; 15.2% of analyzed compounds are phenotypically active, and cross-laboratory replicates cut reference-compound activity by 34%.

The paper uses machine learning to classify Parkinson's disease patient-derived midbrain dopaminergic neurons based on multiple image-based phenotypes and identifies treatable targets.