Ronen Talmon

This study shows that VTA dopaminergic inputs to M1 are essential for reorganizing layer 2-3 network dynamics during motor learning.

SORBET uses geometric deep learning to predict phenotypes from spatial transcriptomics and proteomics data, showing improved accuracy over existing methods.

The paper introduces a graph-based method for analyzing multiplexed spatial data, applied to imaging mass cytometry to predict treatment sensitivity with 92% accuracy.

The paper identifies layer-specific outcome signals in mouse motor cortex that support reinforcement learning of skilled movements.