Neural CRNs: A Natural Implementation of Learning in Chemical Reaction Networks

TL;DR

This paper introduces a dynamical systems approach to implement neural computations in chemical reaction networks, enabling autonomous learning in molecular circuits with simplified reactions and scalable nonlinear models.

Contribution

It proposes a novel dynamical systems framework for chemical neural networks, demonstrating end-to-end supervised learning, simplified reaction schemes, and scalable nonlinear modeling.

Findings

End-to-end supervised learning with minimal phases

Implementation using only unimolecular and bimolecular reactions

Linear scaling of nonlinear models with input dimensionality

Abstract

Molecular circuits capable of autonomous learning could unlock novel applications in fields such as bioengineering and synthetic biology. To this end, existing chemical implementations of neural computing have mainly relied on emulating discrete-layered neural architectures using steady-state computations of mass action kinetics. In contrast, we propose an alternative dynamical systems-based approach in which neural computations are modeled as the time evolution of molecular concentrations. The analog nature of our framework naturally aligns with chemical kinetics-based computation, leading to more compact circuits. We present the advantages of our framework through three key demonstrations. First, we assemble an end-to-end supervised learning pipeline using only two sequential phases, the minimum required number for supervised learning. Then, we show (through appropriate simplifications) that both linear and nonlinear modeling circuits can be implemented solely using unimolecular and bimolecular reactions, avoiding the complexities of higher-order chemistries. Finally, we demonstrate that first-order gradient approximations can be natively incorporated into the framework, enabling nonlinear models to scale linearly rather than combinatorially with input dimensionality. All the circuit constructions are validated through training and inference simulations across various regression and classification tasks. Our work presents a viable pathway toward embedding learning behaviors in synthetic biochemical systems.