Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators

Abstract

Characterizing the properties of neuronal cell types is central to understanding brain function. Yet, biophysically realistic neuron models remain difficult to scale to large populations while preserving the richness of cellular dynamics and within-cell-type variability. We present a cell-type-specific neural-operator framework for scalable neuronal population modeling. Rather than training separate surrogate models for individual neurons, the proposed framework learns a shared operator across multiple modeled neurons from the same cell type, conditioned on biologically interpretable electrophysiological features. Relative to the original single-neuron \texttt{NOBLE} setting, learning across heterogeneous neurons requires a richer electrophysiological conditioning representation and a training objective designed to preserve diverse spiking dynamics. This enables efficient generation of large ensembles of somatic voltage responses while preserving variability across cells and model configurations. We evaluate the approach using membrane dynamics metrics, action potential waveform metrics, spike timing accuracy, input-output firing relationships, and electrophysiological feature distributions. Our framework reproduces subthreshold membrane dynamics, spike waveforms, and firing-rate responses across major cortical inhibitory neuron types, while accurately preserving spike timing despite the sensitivity of threshold-crossing dynamics. The predicted electrophysiological feature distributions show strong agreement with detailed simulator outputs and human experimental recordings, including high explained variability in properties such as inter-spike intervals, firing frequency, action-potential shape, and post-spike recovery.

Dynamics of a Harvested Predator-Prey Model with a Generalized Holling Type~III Response Capturing Group Defense
Wael El Khateeb, Farjana Akter, Chanaka Kottegoda +1
arXiv23 Oct 2026PreprintCC BY 4.0Full textEvolutionary biology Dynamical systemsarXiv
Separation, isolation, and membrane lipid profiling of selectively vulnerable and resilient neurons
M. Sadek, M. Yokomizo, E. Williams +6
bioRxiv6 Oct 2026PreprintCC BY-NCFull textNeurosciencebioRxiv
Low-intensity ultrasound drives offline neuromodulation through passive membrane mechanisms in synaptically isolated hippocampal neurons
M. Stippinger, E. Edes, B. Kovacs +5
bioRxiv28 Sep 2026PreprintCC BY-NC-NDFull textNeurosciencebioRxiv
Complete timing of copy-number amplification histories reveals whole-genome duplication dynamics and coincident oncogene amplification bursts
D. C. Gulhan, J. Brew, P. J. Park
bioRxiv23 Sep 2026PreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
Spatially confined dopamine from locus coeruleus axons selectively shapes hippocampal dynamics and action timing
D. Luo, J. Cao, R. Heldman +2
bioRxiv2 Sep 2026PreprintCC BYFull textNeurosciencebioRxiv

Cite

BibTeX RIS

BibTeX

@misc{ghafourpour2026capturing,
  title = {{Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators}},
  author = {Luca Ghafourpour and Cindy Zhao and Valentin Duruisseaux and Bahareh Tolooshams and Philip H. Wong and Costas A. Anastassiou and Anima Anandkumar},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.06933},
  eprint = {2611.06933},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.06933},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators
AU  - Luca Ghafourpour
AU  - Cindy Zhao
AU  - Valentin Duruisseaux
AU  - Bahareh Tolooshams
AU  - Philip H. Wong
AU  - Costas A. Anastassiou
AU  - Anima Anandkumar
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.06933
UR  - https://arxiv.org/abs/2611.06933
AB  - Characterizing the properties of neuronal cell types is central to understanding brain function. Yet, biophysically realistic neuron models remain difficult to scale to large populations while preserving the richness of cellular dynamics and within-cell-type variability. We present a cell-type-specific neural-operator framework for scalable neuronal population modeling. Rather than training separate surrogate models for individual neurons, the proposed framework learns a shared operator across multiple modeled neurons from the same cell type, conditioned on biologically interpretable electrophysiological features. Relative to the original single-neuron \texttt{NOBLE} setting, learning across heterogeneous neurons requires a richer electrophysiological conditioning representation and a training objective designed to preserve diverse spiking dynamics. This enables efficient generation of large ensembles of somatic voltage responses while preserving variability across cells and model configurations. We evaluate the approach using membrane dynamics metrics, action potential waveform metrics, spike timing accuracy, input-output firing relationships, and electrophysiological feature distributions. Our framework reproduces subthreshold membrane dynamics, spike waveforms, and firing-rate responses across major cortical inhibitory neuron types, while accurately preserving spike timing despite the sensitivity of threshold-crossing dynamics. The predicted electrophysiological feature distributions show strong agreement with detailed simulator outputs and human experimental recordings, including high explained variability in properties such as inter-spike intervals, firing frequency, action-potential shape, and post-spike recovery.
ER  -

Abstract

Related

Cite