AI-driven control of bioelectric signalling for real-time topological reorganization of cells

TL;DR

This work argues that real-time morphogenetic control can be advanced by combining deep reinforcement learning (DRL) with live bioelectric measurements and lab automation. By formulating a continuous-action DRL framework coupled to a digital twin of tissue electrophysiology, the approach seeks to learn policies that set membrane potentials $V_{mem}$ via ion-channel permeabilities $P_{ion}$ and gating variables to steer tissue topology and cell states. Key contributions include a concrete state/action/reward formulation for heart morphogenesis, a causal-inference extension using do-calculus, and an experimental-pathway outline in Drosophila for validating bioelectric control of organ recovery. The proposed framework aims to deliver precise, scalable bioelectric modulation methods with potential impact on regenerative medicine, cancer therapy, and synthetic biology, supported by neuromorphic computing considerations and standardized bioelectric code development. Realization of these ideas could enable digital-twin informed, top-down programming of bioelectric circuits to guide complex tissue regeneration and disease treatment.

Abstract

Understanding and manipulating bioelectric signaling could present a new wave of progress in developmental biology, regenerative medicine, and synthetic biology. Bioelectric signals, defined as voltage gradients across cell membranes caused by ionic movements, play a role in regulating crucial processes including cellular differentiation, proliferation, apoptosis, and tissue morphogenesis. Recent studies demonstrate the ability to modulate these signals to achieve controlled tissue regeneration and morphological outcomes in organisms such as planaria and frogs. However, significant knowledge gaps remain, particularly in predicting and controlling the spatial and temporal dynamics of membrane potentials (V_mem), understanding their regulatory roles in tissue and organ development, and exploring their therapeutic potential in diseases. In this work we propose an experiment using Deep Reinforcement Learning (DRL) framework together with lab automation techniques for real-time manipulation of bioelectric signals to guide tissue regeneration and morphogenesis. The proposed framework should interact continuously with biological systems, adapting strategies based on direct biological feedback. Combining DRL with real-time measurement techniques -- such as optogenetics, voltage-sensitive dyes, fluorescent reporters, and advanced microscopy -- could provide a comprehensive platform for precise bioelectric control, leading to improved understanding of bioelectric mechanisms in morphogenesis, quantitative bioelectric models, identification of minimal experimental setups, and advancements in bioelectric modulation techniques relevant to regenerative medicine and cancer therapy. Ultimately, this research aims to utilize bioelectric signaling to develop new biomedical and bioengineering applications.

Figures (4)

• Figure 1: Illustration of the cellular components used in the GHK equation.
• Figure 2: Illustration of the DRL framework, from training to deployment (See Appendix \ref{['sec:experiment']} for a description of the experimental setup).
• Figure 3: Causal Graph Representing the Relationships Between DRL Actions, Bioelectric Signals, Cellular behaviours, and Environmental Factors.
• Figure 4: Expanded Causal Graph Including Calcium signalling and Gene Expression.