Relevance of Nonlinear Dimensionality Reduction for Efficient and Robust Spike Sorting

Spike sorting is one of the cornerstones of extracellular electrophysiology. By leveraging advanced signal processing and data analysis techniques, spike sorting makes it possible to detect, isolate, and map single neuron spiking activity from both in vivo and in vitro extracellular electrophysiological recordings. A crucial step of any spike sorting pipeline is to reduce the dimensionality of the recorded spike waveform data. Reducing the dimensionality of the processed data is mandatory to apply the clustering algorithms responsible for detecting, isolating, and sorting the recorded putative neurons. In this paper we propose and illustrate on both synthetic and experimental data that employing the nonlinear dimensionality reduction technique Uniform Manifold Approximation and Projection can drastically improve the performance, efficiency, robustness, and scalability of spike sorting pipelines without increasing their computational cost. We show how replacing the linear or expert-defined dimensionality reduction methods commonly used in spike sorting pipelines by unsupervised, mathematically grounded, nonlinear methods increases the number of correctly sorted neurons, makes the identification of quieter, seldom spiking neurons more reliable, enables deeper and more precise explorations and analysis of the neural code, and paves new ways toward more efficient and end-to-end automatable spike sorting pipelines of large-scale extracellular neural recording as those produced by high-density multielectrode arrays.