Differentiable Programming of Chemical Reaction Networks
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2023
- DOI:
- 10.48550/arXiv.2302.02714
- arXiv:
- arXiv:2302.02714
- Bibcode:
- 2023arXiv230202714M
- Keywords:
-
- Quantitative Biology - Molecular Networks;
- Computer Science - Machine Learning