Interpretable Reaction–Diffusion Learning for Molecular Communication via Graph Kolmogorov–Arnold Networks
- 1Department of Electrical and Computer Engineering, Baylor University, Waco, TX 76798, USA, and with the Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA
Abstract
Molecular communication (MC) lets biological cells coordinate collective behaviors through diffusion-mediated signaling molecules that couple intracellular reaction kinetics across a spatial graph. Existing graph neural networks are accurate but opaque, while classical reaction–diffusion models require an explicit kinetics function unavailable in most biological settings. This paper proposes Reaction–Diffusion Graph Kolmogorov–Arnold Networks (RD-GKAN), an interpretable architecture whose forward pass implements reaction–diffusion dynamics: a learnable B-spline per species captures the reaction, and diffusion uses an explicit graph Laplacian with prescribed distance-dependent weights, MC-derived where the channel parameters are available. Each learned spline is projected onto a symbolic library via sparse regression, selecting the dominant kinetics basis (e.g., Hill or Michaelis–Menten) without assuming the form a priori. Evaluation spans five independent domains: MC testbeds, bacterial quorum sensing, ERK signaling waves, and wound-healing and two-tissue spatial transcriptomics. Under leakage-controlled evaluation, graph-structured coupling improves none of the real-data tasks. A trivial persistence baseline matches or outperforms the full model on both temporal datasets. The S. aureus device suppresses diffusive coupling, so that result is a specificity check; the ERK monolayers carry documented collective waves, and there the null reflects a task dominated by temporal autocorrelation. Static spatial reconstruction reduces to local self-feature denoising rather than inter-cellular communication, a caution for spatial graph learning. On synthetic data, B-spline parameterization outperforms an MLP by$6.2\times $and distance-dependent edge weights improve accuracy$2.4\times $over binary coupling.
Related
- Pathway-Masked Kolmogorov–Arnold Networks Yield an Interpretable Transcriptomic Score Associated with Colorectal Cancer Progression Independently of Clinical Stage
- Interpretable Machine Learning in Food Analysis: Closed-Form Chemometric Calibration of Mid- and Near-Infrared Spectra Using Kolmogorov-Arnold Networks.
- Low-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator Learning
- Interpretable side reaction detection via atom representations derived from multi-tier reaction perspectives
- GridXAI-diffusion an adaptive graph intelligence framework for interpretable data integrity analysis in smart grid cybersecurity systems
BibTeX
@article{dong2026interpretable,
title = {{Interpretable Reaction–Diffusion Learning for Molecular Communication via Graph Kolmogorov–Arnold Networks}},
author = {Liang Dong},
journal = {IEEE transactions on molecular, biological, and multi-scale communications},
year = {2026},
month = sep,
doi = {10.1109/tmbmc.2026.3731398},
url = {https://doi.org/10.1109/tmbmc.2026.3731398},
note = {CC BY},
}
RIS
TY - JOUR
TI - Interpretable Reaction–Diffusion Learning for Molecular Communication via Graph Kolmogorov–Arnold Networks
AU - Liang Dong
PY - 2026
DA - 2026/09/07
JO - IEEE transactions on molecular, biological, and multi-scale communications
DO - 10.1109/tmbmc.2026.3731398
UR - https://doi.org/10.1109/tmbmc.2026.3731398
AB - Molecular communication (MC) lets biological cells coordinate collective behaviors through diffusion-mediated signaling molecules that couple intracellular reaction kinetics across a spatial graph. Existing graph neural networks are accurate but opaque, while classical reaction–diffusion models require an explicit kinetics function unavailable in most biological settings. This paper proposes Reaction–Diffusion Graph Kolmogorov–Arnold Networks (RD-GKAN), an interpretable architecture whose forward pass implements reaction–diffusion dynamics: a learnable B-spline per species captures the reaction, and diffusion uses an explicit graph Laplacian with prescribed distance-dependent weights, MC-derived where the channel parameters are available. Each learned spline is projected onto a symbolic library via sparse regression, selecting the dominant kinetics basis (e.g., Hill or Michaelis–Menten) without assuming the form a priori. Evaluation spans five independent domains: MC testbeds, bacterial quorum sensing, ERK signaling waves, and wound-healing and two-tissue spatial transcriptomics. Under leakage-controlled evaluation, graph-structured coupling improves none of the real-data tasks. A trivial persistence baseline matches or outperforms the full model on both temporal datasets. The S. aureus device suppresses diffusive coupling, so that result is a specificity check; the ERK monolayers carry documented collective waves, and there the null reflects a task dominated by temporal autocorrelation. Static spatial reconstruction reduces to local self-feature denoising rather than inter-cellular communication, a caution for spatial graph learning. On synthetic data, B-spline parameterization outperforms an MLP by$6.2\times $and distance-dependent edge weights improve accuracy$2.4\times $over binary coupling.
SN - 2332-7804
ER -