aiqbench analysis
This research introduces a hybrid modeling framework that integrates Neural Ordinary Differential Equations into conductance-based biophysical neuron models to capture unknown ion channel kinetics. The approach successfully fits gating dynamics across thousands of models while reducing computational costs by simplifying multicompartment structures without sacrificing mechanistic interpretability. By learning voltage-dependent functions directly from recordings, this method bridges the gap between data-driven flexibility and biological plausibility in neural simulation.
Learning Hybrid Biophysical Neuron Models with Neural ODEs
arXiv:2606.16693v1 Announce Type: cross Abstract: Biophysical neuron models link measurements of neural activity to underlying cellular mechanisms. Yet, a central challenge is that the kinetics of many ion channels are poorly characterized, and practical simplifications -- omitting channels or reducing morphological detail -- introduce systematic gaps between model and biology. Bridging these gaps requires approaches that can flexibly discover unmodeled dynamics while preserving mechanistic interpretability. Here, we introduce a hybrid modeling framework that embeds neural ordinary differential equations into conductance-based biophysical models to capture unknown currents or mis-specified channel kinetics. By parameterizing the neural ODE in terms of voltage-dependent steady-state and time-constant functions, we recover interpretable gating dynamics directly from voltage recordings without assuming a functional form. We show that the hybrid model fits the gating kinetics of 2400 ion channel models and recovers unknown gating dynamics from single current-clamp recordings, generalizing to out-of-distribution stimulus regimes under realistic inputs and parameter misspecification. We also use our method to reduce a multicompartment model of a cortical neuron into a single-compartment hybrid model with a learned axial current, yielding up to an order of magnitude lower computational cost. Together, our results establish a plug-and-play framework for selectively replacing unknown components of conductance-based models with neural ODEs while preserving their mechanistic structure.
Abstract:Biophysical neuron models link measurements of neural activity to underlying cellular mechanisms. Yet, a central challenge is that the kinetics of many ion channels are poorly characterized, and practical simplifications -- omitting channels or reducing morphological detail -- introduce systematic gaps between model and biology. Bridging these gaps requires approaches that can flexibly discover unmodeled dynamics while preserving mechanistic interpretability. Here, we introduce a hybrid modeling framework that embeds neural ordinary differential equations into conductance-based biophysical models to capture unknown currents or mis-specified channel kinetics. By parameterizing the neural ODE in terms of voltage-dependent steady-state and time-constant functions, we recover interpretable gating dynamics directly from voltage recordings without assuming a functional form. We show that the hybrid model fits the gating kinetics of 2400 ion channel models and recovers unknown gating dynamics from single current-clamp recordings, generalizing to out-of-distribution stimulus regimes under realistic inputs and parameter misspecification. We also use our method to reduce a multicompartment model of a cortical neuron into a single-compartment hybrid model with a learned axial current, yielding up to an order of magnitude lower computational cost. Together, our results establish a plug-and-play framework for selectively replacing unknown components of conductance-based models with neural ODEs while preserving their mechanistic structure.
Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG)
arXiv:2606.16693 [q-bio.NC]
(or arXiv:2606.16693v1 [q-bio.NC] for this version)
https://doi.org/10.48550/arXiv.2606.16693 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 302 words
Related coverage
Conditional Flow Matching for Single-Neuron Electrophysiology: Capturing Multimodal Responses Across Stimuli
arXiv · Oct 6, 2026
Machine Learning Methods for Studying Latent Neural Activity Dynamics
arXiv · Jun 10, 2026
Physics-Embedded Neural ODEs for Learning Antagonistic Pneumatic Artificial Muscle Dynamics
arXiv · Aug 3, 2026
UMD Leads $7M MURI to Study Brain’s Hidden Astrocytes
Quantum Zeitgeist · Jun 5, 2026