Abstract Summary
•
Spike sorting is crucial in neural recording to isolate signals from individual neurons, facilitating the study of neuronal communication and information processing.
•
The research introduces SimSort, a deep learning-based spike sorting approach trained on a large-scale dataset generated through electrophysiology simulations, showcasing zero-shot generalizability to real-world tasks and outperforming existing methods across various benchmarks.
Abstract
Spike sorting is an essential process in neural recording, which identifies and separates electrical signals from individual neurons recorded by electrodes in the brain, enabling researchers to study how specific neurons communicate and process information. Although there exist a number of spike sorting methods which have contributed to significant neuroscientific breakthroughs, many are heuristically designed, making it challenging to verify their correctness due to the difficulty of obtaining ground truth labels from real-world neural recordings. In this work, we explore a data-driven, deep learning-based approach. We begin by creating a large-scale dataset through electrophysiology simulations using biologically realistic computational models. We then present SimSort, a pretraining framework for spike sorting. Trained solely on simulated data, SimSort demonstrates zero-shot generalizability to real-world spike sorting tasks, yielding consistent improvements over existing methods across multiple benchmarks. These results highlight the potential of simulation-driven pretraining to enhance the robustness and scalability of spike sorting in experimental neuroscience.