Inferring Active Neural Circuits Using Diffusion Scores
Abstract
In biological systems, neural circuits compute through directed, short-latency interactions whose effects unfold across multiple time scales and behavioral contexts. We address the problem of inferring these local, lag-specific interactions from sampled neural population activity under varying stimuli, without assuming a parametric form for the underlying dynamics. Our approach leverages denoising score models by estimating joint-window scores over consecutive activity snapshots (i.e., brain states) and converting these scores into calibrated, directed edge tests via cross-block score products. The key insight is that these products recover the Jacobian of the transition map between brain states under nonlinear dynamics. To cleanly separate lag-specific effects, we introduce minimal multi-block windows that condition on intermediate time points, avoiding the omitted-lag bias inherent in pairwise analyses. The resulting method, Score--Block Time Graphs (SBTG), identifies lag-specific directed interactions in sampled neuronal population data. We specifically apply SBTG to whole-brain C. elegans calcium imaging data to recover lag-specific circuit structure not resolved by current methods, including improved alignment with independent connectomes, cell-type-specific temporal organization, and neuromodulatory profiles consistent with known receptor kinetics. These findings highlight the potential for SBTG to serve as a practical ``AI for science'' tool by turning high-dimensional neural population recordings into statistically testable circuit hypotheses.
Related
- Inferring organ aging, hallmark of aging and senescence scores from blood and facial photographs
- Inferring effective neuronal circuits via network flux counting
- Petimot: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
- Graph neural network approach for inferring neuronal connectivity
- Inferring brain-wide interactions using data-constrained recurrent neural network models
BibTeX
@misc{kinger2026inferring,
title = {{Inferring Active Neural Circuits Using Diffusion Scores}},
author = {Savik Kinger and Johannes Bertram and Luciano Dyballa and Eviatar Yemini and Steven W. Zucker},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.02852},
eprint = {2605.02852},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.02852},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Inferring Active Neural Circuits Using Diffusion Scores
AU - Savik Kinger
AU - Johannes Bertram
AU - Luciano Dyballa
AU - Eviatar Yemini
AU - Steven W. Zucker
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2605.02852
UR - https://arxiv.org/abs/2605.02852
AB - In biological systems, neural circuits compute through directed, short-latency interactions whose effects unfold across multiple time scales and behavioral contexts. We address the problem of inferring these local, lag-specific interactions from sampled neural population activity under varying stimuli, without assuming a parametric form for the underlying dynamics. Our approach leverages denoising score models by estimating joint-window scores over consecutive activity snapshots (i.e., brain states) and converting these scores into calibrated, directed edge tests via cross-block score products. The key insight is that these products recover the Jacobian of the transition map between brain states under nonlinear dynamics. To cleanly separate lag-specific effects, we introduce minimal multi-block windows that condition on intermediate time points, avoiding the omitted-lag bias inherent in pairwise analyses. The resulting method, Score--Block Time Graphs (SBTG), identifies lag-specific directed interactions in sampled neuronal population data. We specifically apply SBTG to whole-brain C. elegans calcium imaging data to recover lag-specific circuit structure not resolved by current methods, including improved alignment with independent connectomes, cell-type-specific temporal organization, and neuromodulatory profiles consistent with known receptor kinetics. These findings highlight the potential for SBTG to serve as a practical ``AI for science'' tool by turning high-dimensional neural population recordings into statistically testable circuit hypotheses.
ER -