Spike Sorting with VanillaSort
Abstract
Training spike detectors on real recordings is challenging because algorithmically generated labels can be noisy and incomplete. We propose VanillaSort, combining multichannel detection with spatially augmented, template-guided clustering. VanillaDet uses visibility-aware masking, truncated Gaussian targets and a temporally tolerant positive-bag loss, followed by conditional event-SNR gating. VanillaCluster combines HuiduRep embeddings with relative-amplitude features for Gaussian mixture clustering and refines assignments using cross-fitted waveform templates built from selected core events. VanillaDet improves detection accuracy over SimSort by two and three percentage points on the static and drift subsets of Hybrid Janelia, respectively. The complete pipeline also improves sorting performance over the corresponding HuiduRep baselines. These results support learning from imperfect real-data labels and incorporating waveform consistency into neuronal assignment.
Related
- Efficient and reproducible pipelines for spike sorting large-scale electrophysiology data
- Systematic Spike Sorting Errors Revealed by Juxtacellular Ground Truth in the Awake Brain
- Single-cell DNA cytometry with magnetic- and fluorescence-activated bead sorting
- HRS dephosphorylation at membrane contact sites promotes sorting within multivesicular endosomes
- Cutting-edge microfluidic technology allows detection and sorting of single fluorescent extracellular vesicles
BibTeX
@misc{feng2026spike,
title = {{Spike Sorting with VanillaSort}},
author = {Zishuo Feng and Feng Cao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22322},
eprint = {2609.22322},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22322},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Spike Sorting with VanillaSort
AU - Zishuo Feng
AU - Feng Cao
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.22322
UR - https://arxiv.org/abs/2609.22322
AB - Training spike detectors on real recordings is challenging because algorithmically generated labels can be noisy and incomplete. We propose VanillaSort, combining multichannel detection with spatially augmented, template-guided clustering. VanillaDet uses visibility-aware masking, truncated Gaussian targets and a temporally tolerant positive-bag loss, followed by conditional event-SNR gating. VanillaCluster combines HuiduRep embeddings with relative-amplitude features for Gaussian mixture clustering and refines assignments using cross-fitted waveform templates built from selected core events. VanillaDet improves detection accuracy over SimSort by two and three percentage points on the static and drift subsets of Hybrid Janelia, respectively. The complete pipeline also improves sorting performance over the corresponding HuiduRep baselines. These results support learning from imperfect real-data labels and incorporating waveform consistency into neuronal assignment.
ER -