NOBLE – Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models
Creators
-
1.
ETH Zurich
-
2.
California Institute of Technology
-
3.
University of Alberta
- 4. Alberta Machine Intelligence Institute (Amii)
-
5.
Cedars-Sinai Medical Center
- 6. Archimedes AI, Athena Research Center
Abstract
Characterizing the cellular properties of neurons is fundamental to understanding their function in the brain. In this quest, the generation of bio-realistic models is central towards integrating multimodal cellular data sets and establishing causal relationships. However, current modeling approaches remain constrained by the limited availability and intrinsic variability of experimental neuronal data. The deterministic formalism of bio-realistic models currently precludes accounting for the natural variability observed experimentally. 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 synthetic data generated from bio-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 enables the efficient generation of synthetic neurons that closely resemble experimental data and exhibit trial-to-trial variability, offering a 4200× speedup over the numerical solver. NOBLE is the first scaled-up deep learning framework that validates its generalization with real experimental data. To this end, NOBLE captures fundamental neural properties in a unique and emergent manner that opens the door to a better understanding of cellular composition and computations, neuromorphic architectures, large-scale brain circuits, and general neuroAI applications.
Copyright and License
Creative Commons Attribution 4.0 International
Acknowledgement
L.G. was responsible for the complete technical implementation of this work. C.A.A. and A.A. conceptualized this work. L.G., V.D., and B.T. jointly developed the methodology of the novel NOBLE framework. P.H.W. and C.A.A. provided neuroscience-specific domain expertise, contextualizing the relevance and impact of this work within the broader field of neuroscience. P.H.W. supplied the biophysical PDE models and developed the multi-objective optimization pipeline. L.G. and P.H.W. produced the figures. L.G., V.D., B.T., P.H.W., and C.A.A. co-wrote the manuscript. C.A.A. and A.A. provided supervision and editorial comments.
Funding
A.A. is supported by the Bren Endowed Chair, ONR (MURI grant N00014-23-1-2654), and the AI2050 Senior Fellow program at Schmidt Sciences. C.A.A. is supported by the National Institutes of Health R01 - NS120300 and R01 - NS130126. P.H.W. is supported by the National Institutes of Health R01 - NS130126.
Contributions
Valentin Duruisseaux and Bahareh Tolooshams contributed equally to this work.
L.G. was responsible for the complete technical implementation of this work. C.A.A. and A.A. conceptualized this work. L.G., V.D., and B.T. jointly developed the methodology of the novel NOBLE framework. P.H.W. and C.A.A. provided neuroscience-specific domain expertise, contextualizing the relevance and impact of this work within the broader field of neuroscience. P.H.W. supplied the biophysical PDE models and developed the multi-objective optimization pipeline. L.G. and P.H.W. produced the figures. L.G., V.D., B.T., P.H.W., and C.A.A. co-wrote the manuscript. C.A.A. and A.A. provided supervision and editorial comments.
Files
2506.04536v3.pdf
Files
(35.5 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:0d12260e9d33500990d558dc1eae1d4b
|
35.5 MB | Preview Download |
Additional details
Funding
- California Institute of Technology
- Office of Naval Research
- N00014-23-1-2654
- Schmidt Sciences
- AI2050 Senior Fellow program
- National Institutes of Health
- R01 - NS120300
- National Institutes of Health
- R01 - NS130126
Dates
- Submitted
-
2025-06-05
- Updated
-
2025-06-12
- Updated
-
2025-10-27