NOBLE -- Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models

2025-06-05

AI Summary

To address the challenges of scarce experimental data, difficulty in characterizing inter-neuronal variability, and the intractability of fully recapitulating biophysical complexity in biological neuron modeling, this paper introduces NOBLE—a neural operator framework. NOBLE constructs, for the first time, an interpolatable, biology-informed latent space that fuses multimodal features—electrophysiological, transcriptomic, and morphological—to map neuronal attributes to trial-to-trial variable somatic voltage response distributions. Leveraging frequency-modulated latent embeddings and biophysically grounded supervised training, NOBLE achieves end-to-end validation on real experimental data and enables high-fidelity synthetic neuron generation. Compared to conventional numerical solvers, NOBLE accelerates inference by 4,200×, substantially enhancing computational efficiency for large-scale brain circuit simulation and neuromorphic computing.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Characterizing the diverse computational properties of human neurons via multimodal electrophysiological, transcriptomic, and morphological data provides the foundation for constructing and validating bio-realistic neuron models that can advance our understanding of fundamental mechanisms underlying brain function. However, current modeling approaches remain constrained by the limited availability and intrinsic variability of experimental neuronal data. To capture variability, ensembles of deterministic models are often used, but are difficult to scale as model generation requires repeating computationally expensive optimization for each neuron. While deep learning is becoming increasingly relevant in this space, it fails to capture the full biophysical complexity of neurons, their nonlinear voltage dynamics, and variability. To address these shortcomings, we introduce NOBLE, a neural operator framework that learns a mapping from a continuous frequency-modulated embedding of interpretable neuron features to the somatic voltage response induced by current injection. Trained on data generated from biophysically realistic neuron models, NOBLE predicts distributions of neural dynamics accounting for the intrinsic experimental variability. Unlike conventional bio-realistic neuron models, interpolating within the embedding space offers models whose dynamics are consistent with experimentally observed responses. NOBLE is the first scaled-up deep learning framework validated on real experimental data, enabling efficient generation of synthetic neurons that exhibit trial-to-trial variability and achieve a $4200 imes$ speedup over numerical solvers. To this end, NOBLE captures fundamental neural properties, opening the door to a better understanding of cellular composition and computations, neuromorphic architectures, large-scale brain circuits, and general neuroAI applications.

Problem

• Capturing experimental variability in biological neuron models
• Overcoming limitations of current deep learning in biophysical complexity
• Efficiently generating synthetic neurons with trial-to-trial variability

Innovation

• Neural operator with biologically-informed latent embeddings
• Predicts neural dynamics with experimental variability
• Achieves 4200x speedup over numerical solvers