Renato Marciano Maciel

This study shows that automatic deep learning models for mouse sleep scoring struggle to generalize across labs due to signal variability and label noise, and proposes four robust models trained on diverse data.

The paper develops an automated workflow for whole brain analysis of neuronal activity using c-Fos immunohistochemistry and open-source tools, enabling accurate and unbiased quantification across contexts.

The paper compares hypothalamic neuron activation during wakefulness and paradoxical sleep using TRAP2-red mice, identifying new markers and subpopulations.

The paper compares brain activation patterns induced by wakefulness drugs and non-pharmacological methods in mice, revealing distinct neural populations involved.