GALDS: A Graph-Autoencoder-based Latent Dynamics Surrogate model to predict neurite material transport

2025-07-14

AI Summary

Simulating intraneuronal transport in dendritic arbors suffers from high computational cost and low accuracy. To address this, we propose a latent-dynamics surrogate model coupling a graph autoencoder with neural ordinary differential equations (Neural ODEs). The graph autoencoder projects high-dimensional geometric structures, velocity fields, and concentration distributions into a low-dimensional latent space; within this space, a graph neural network drives the Neural ODE to model spatiotemporal evolution, thereby avoiding error accumulation inherent in recurrent architectures. This design significantly reduces model complexity and data dependency. Experiments demonstrate that the model achieves a mean relative error of only 3%—with a peak under 8%—on unseen neuronal geometries and anomalous transport scenarios. Moreover, inference speed is accelerated tenfold over state-of-the-art surrogates. The approach thus provides an efficient, robust, and generalizable solution for large-scale simulation of neuronal material transport.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Neurons exhibit intricate geometries within their neurite networks, which play a crucial role in processes such as signaling and nutrient transport. Accurate simulation of material transport in the networks is essential for understanding these biological phenomena but poses significant computational challenges because of the complex tree-like structures involved. Traditional approaches are time-intensive and resource-demanding, yet the inherent properties of neuron trees, which consists primarily of pipes with steady-state parabolic velocity profiles and bifurcations, provide opportunities for computational optimization. To address these challenges, we propose a Graph-Autoencoder-based Latent Dynamics Surrogate (GALDS) model, which is specifically designed to streamline the simulation of material transport in neural trees. GALDS employs a graph autoencoder to encode latent representations of the network's geometry, velocity fields, and concentration profiles. These latent space representations are then assembled into a global graph, which is subsequently used to predict system dynamics in the latent space via a trained graph latent space system dynamic model, inspired by the Neural Ordinary Differential Equations (Neural ODEs) concept. The integration of an autoencoder allows for the use of smaller graph neural network models with reduced training data requirements. Furthermore, the Neural ODE component effectively mitigates the issue of error accumulation commonly encountered in recurrent neural networks. The effectiveness of the GALDS model is demonstrated through results on eight unseen geometries and four abnormal transport examples, where our approach achieves mean relative error of 3% with maximum relative error <8% and demonstrates a 10-fold speed improvement compared to previous surrogate model approaches.

Problem

• Predict material transport in complex neurite networks efficiently
• Overcome computational challenges of traditional simulation methods
• Reduce error accumulation and training data requirements

Innovation

• Graph autoencoder encodes neurite geometry and dynamics
• Latent space predicts system dynamics via Neural ODEs
• Reduces error accumulation and training data needs