Protocol for machine learning-based classification of neuronal cell types from spike waveforms

The extensive adoption of electrophysiological methods in neuroscience has underscored the critical need to accurately distinguish neuronal subtypes from spike waveforms for advanced neurophysiological investigations. Here, we present a protocol to categorize neurons according to their waveform characteristics by combining machine learning algorithms with initial spike sorting. We describe steps for data preprocessing, spike sorting, and subsequent analytical procedures implemented through MATLAB and Python scripts. This protocol provides a framework for researchers aiming to classify distinct cell types with confidence. For complete details on the use and execution of this protocol, please refer to Liu et al.¹.