Benchmarking Clustering Strategies for High-Dimensional Spike Time-Windows Data from Multi-Electrode Arrays
- 1Dipartimento di Matematica, Universita' di Genova, Italy
Abstract
From a statistical point of view, clustering spike time-windows from multi-electrode arrays (MEAs) recordings is a challenging high-dimensional, unsupervised clustering task where stationarity, commonly assumed in standard time-series analysis, is often violated and for which a gold standard is currently unavailable. Here we aim at providing practical guidance on how to cluster this type of data by systematically comparing 108 clustering pipelines differing along three main dimensions: (i) the data feature space; (ii) the metrics used to quantify distance between data points; and (iii) the clustering algorithm. For our benchmark we used both labeled synthetic data, mimicking four physiologically-inspired classes of spike time-windows, and a set of real MEAs recordings from a two-dimensional in-vitro neural culture. The performance of the competing pipelines was evaluated in terms of balanced accuracy and computational time when analyzing the synthetic datasets, while the Silhouette score was used for the real dataset, where no ground-truth is available. Overall, our analysis shows that the best combination is formed by k-means with Euclidean distance applied after Principal Component Analysis (PCA) of the spike time-windows. Conversely, hierarchical clustering showed the highest computational burden, while Independent Component Analysis and kernel PCA provided less effective noise suppression.
Related
- Benchmarking 16S rRNA gene amplicon analysis in high-diversity microbial communities reveals fundamental trade-offs in clustering and denoising
- A Pan-Cancer Benchmark of Clustering Strategies for Patient-Specific Gene Regulatory Networks
- 4-Dimensional Chess: Acoustic Localisation Reveals Nested Spatio-temporal Strategies in an Arboreal Communication Network
- Microbiota during early life windows orchestrates intestinal maturation and barrier formation in the offspring
- Large cranial windows distort auditory cortical maps and degrade feature integration in secondary auditory cortex
BibTeX
@misc{sacchi2026benchmarking,
title = {{Benchmarking Clustering Strategies for High-Dimensional Spike Time-Windows Data from Multi-Electrode Arrays}},
author = {L. Sacchi and S. Sommariva and M. A. Unkel and F. M. De Vrij and C. Campi},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.17.752158},
url = {https://www.biorxiv.org/content/10.64898/2026.09.17.752158v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Benchmarking Clustering Strategies for High-Dimensional Spike Time-Windows Data from Multi-Electrode Arrays
AU - L. Sacchi
AU - S. Sommariva
AU - M. A. Unkel
AU - F. M. De Vrij
AU - C. Campi
PY - 2026
DA - 2026/09/17
PB - bioRxiv
DO - 10.64898/2026.09.17.752158
UR - https://www.biorxiv.org/content/10.64898/2026.09.17.752158v1
AB - From a statistical point of view, clustering spike time-windows from multi-electrode arrays (MEAs) recordings is a challenging high-dimensional, unsupervised clustering task where stationarity, commonly assumed in standard time-series analysis, is often violated and for which a gold standard is currently unavailable. Here we aim at providing practical guidance on how to cluster this type of data by systematically comparing 108 clustering pipelines differing along three main dimensions: (i) the data feature space; (ii) the metrics used to quantify distance between data points; and (iii) the clustering algorithm. For our benchmark we used both labeled synthetic data, mimicking four physiologically-inspired classes of spike time-windows, and a set of real MEAs recordings from a two-dimensional in-vitro neural culture. The performance of the competing pipelines was evaluated in terms of balanced accuracy and computational time when analyzing the synthetic datasets, while the Silhouette score was used for the real dataset, where no ground-truth is available. Overall, our analysis shows that the best combination is formed by k-means with Euclidean distance applied after Principal Component Analysis (PCA) of the spike time-windows. Conversely, hierarchical clustering showed the highest computational burden, while Independent Component Analysis and kernel PCA provided less effective noise suppression.
ER -