Zhixin Lu

The paper presents a database of over 1,000 differentiable single-neuron models fitted to mouse and human patch-clamp recordings, with PyTorch code for integration into machine learning.

On 495 human Patch-seq neurons, cell type means predicted electrophysiology better than neural networks on scGPT embeddings or gene panels; fusing scGPT embeddings with cell type labels predicted best.

This study uses network control theory to analyze energy dynamics in temporal lobe epilepsy, finding increased control energy requirements and metabolic asymmetry in affected brain regions.

The paper uses network control theory to show that structural brain networks mature during adolescence to reduce the energy cost of activating the frontoparietal system, supporting executive function development.