SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation

TL;DR

SimSort introduces a deep learning framework trained on large-scale simulated neural data that generalizes well to real-world spike sorting, improving accuracy and robustness in neural signal analysis.

Contribution

The paper presents SimSort, a novel simulation-based pretraining approach for spike sorting that achieves zero-shot transfer to real data, addressing ground truth limitations.

Findings

Outperforms existing spike sorting methods on multiple benchmarks.

Demonstrates zero-shot generalization from simulated to real neural data.

Enhances robustness and scalability of spike sorting techniques.

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.