Differentiable Programming of Chemical Reaction Networks
Molecular Networks
2023-02-07 v1 Machine Learning
Abstract
We present a differentiable formulation of abstract chemical reaction networks (CRNs) that can be trained to solve a variety of computational tasks. Chemical reaction networks are one of the most fundamental computational substrates used by nature. We study well-mixed single-chamber systems, as well as systems with multiple chambers separated by membranes, under mass-action kinetics. We demonstrate that differentiable optimisation, combined with proper regularisation, can discover non-trivial sparse reaction networks that can implement various sorts of oscillators and other chemical computing devices.
Cite
@article{arxiv.2302.02714,
title = {Differentiable Programming of Chemical Reaction Networks},
author = {Alexander Mordvintsev and Ettore Randazzo and Eyvind Niklasson},
journal= {arXiv preprint arXiv:2302.02714},
year = {2023}
}