Fast reconstruction of degenerate populations of conductance-based neuron models from spike times

2025-09-16

AI Summary

Accurately inferring the degenerate ion channel composition underlying neuronal spiking behavior—while establishing a quantitative mapping between spiking patterns and biophysical mechanisms—remains challenging, especially when only spike timing is available and voltage traces or detailed prior models are absent. Method: We propose a “deep learning + dynamic input conductance (DIC)” hybrid framework: a deep neural network directly learns the distribution of ion channel parameters from spike trains, while DIC theory imposes biophysically grounded constraints on the solution space, eliminating reliance on intracellular voltage recordings or prespecified conductance models. Contribution/Results: This is the first method enabling interpretable, generalizable inference of functional ion channel components solely from spike timing. It generates physiologically consistent “twin neuron” populations that replicate target spiking statistics. Our approach significantly outperforms existing techniques in accuracy, computational speed, and interpretability. An open-source, no-code visualization toolkit enables interactive, user-friendly modeling for non-programmers.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bio-inspired Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Neurons communicate through spikes, and spike timing is a crucial part of neuronal processing. Spike times can be recorded experimentally both intracellularly and extracellularly, and are the main output of state-of-the-art neural probes. On the other hand, neuronal activity is controlled at the molecular level by the currents generated by many different transmembrane proteins called ion channels. Connecting spike timing to ion channel composition remains an arduous task to date. To address this challenge, we developed a method that combines deep learning with a theoretical tool called Dynamic Input Conductances (DICs), which reduce the complexity of ion channel interactions into three interpretable components describing how neurons spike. Our approach uses deep learning to infer DICs directly from spike times and then generates populations of "twin" neuron models that replicate the observed activity while capturing natural variability in membrane channel composition. The method is fast, accurate, and works using only spike recordings. We also provide open-source software with a graphical interface, making it accessible to researchers without programming expertise.

Problem

• Reconstructing neuron models from spike times
• Connecting spike timing to ion channel composition
• Inferring dynamic conductances using deep learning

Innovation

• Deep learning infers DICs from spike times
• Generates twin neuron models replicating activity
• Open-source software with graphical interface