Decoding brain anatomy from neuronal neighborhoods with MYCEL
- 1University of California Santa Cruz
Abstract
Extracellular recordings carry information about neuronal location, and pooling per-unit predictions across neighboring electrodes improves its readout, but whether this local pooling should be learned is untested. We present MYCEL (Message-passing Yields Cellular Embeddings of Location), a graph neural network whose nodes are spike-sorted units carrying waveform and spike-timing features selected on cell-type ground truth, and whose edges encode recording geometry. On the Allen Brain Observatory Visual Coding Neuropixels dataset, learned message passing outperforms fixed aggregation, with the largest gains where single units are least informative. On the International Brain Laboratory Brain Wide Map, MYCEL matches the strongest population model at one-tenth the pairwise interactions. On held-out animals, the embeddings recover laminar depth within visual cortex. Retrained with only the edge geometry changed, the same framework decodes anatomy in macaque visual cortex and human medial temporal lobe. Thus, how neighboring neurons are combined matters as much as the features that describe them.
Related
- Trigeminal Nerve Stimulation Attenuates Traumatic Brain Injury-Induced Neuronal Damage via CGRP-PINK1 Mitophagy Axis
- Cerebral microthrombi promote focal Cav-1-dependent blood-brain barrier impairment, triggering neuroinflammation and neuronal damage after traumatic brain injury
- Brain-Resident CD8+ T Cells Regulate Neuronal Activity and Behavior via Interferon-Gamma
- Generalizable neural decoding for clinically scalable brain-computer interfaces.
- Multilingual Brain Decoding Reveals Shared Cortical Semantic Geometry
BibTeX
@misc{gonzalezferrer2026decoding,
title = {{Decoding brain anatomy from neuronal neighborhoods with MYCEL}},
author = {J. Gonzalez-Ferrer and A. Moreno-Ochando and J. R. Minnick and A. Schneider and M. Teodorescu and D. Haussler and M. A. Mostajo-Radji},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.26.754562},
url = {https://www.biorxiv.org/content/10.64898/2026.09.26.754562v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Decoding brain anatomy from neuronal neighborhoods with MYCEL
AU - J. Gonzalez-Ferrer
AU - A. Moreno-Ochando
AU - J. R. Minnick
AU - A. Schneider
AU - M. Teodorescu
AU - D. Haussler
AU - M. A. Mostajo-Radji
PY - 2026
DA - 2026/09/26
PB - bioRxiv
DO - 10.64898/2026.09.26.754562
UR - https://www.biorxiv.org/content/10.64898/2026.09.26.754562v1
AB - Extracellular recordings carry information about neuronal location, and pooling per-unit predictions across neighboring electrodes improves its readout, but whether this local pooling should be learned is untested. We present MYCEL (Message-passing Yields Cellular Embeddings of Location), a graph neural network whose nodes are spike-sorted units carrying waveform and spike-timing features selected on cell-type ground truth, and whose edges encode recording geometry. On the Allen Brain Observatory Visual Coding Neuropixels dataset, learned message passing outperforms fixed aggregation, with the largest gains where single units are least informative. On the International Brain Laboratory Brain Wide Map, MYCEL matches the strongest population model at one-tenth the pairwise interactions. On held-out animals, the embeddings recover laminar depth within visual cortex. Retrained with only the edge geometry changed, the same framework decodes anatomy in macaque visual cortex and human medial temporal lobe. Thus, how neighboring neurons are combined matters as much as the features that describe them.
ER -