Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks

TL;DR

This paper introduces a novel method to translate trained binary-weight ReLU neural networks into chemical reaction networks, enabling molecular computation that is robust and compatible with biological hardware.

Contribution

It establishes a direct link between neural networks and chemical reactions, allowing neural models to be implemented in molecular systems for bioengineering applications.

Findings

Chemical reaction networks can implement binary-weight ReLU neural networks.

The method successfully classifies datasets like IRIS and MNIST.

Chemical networks can discriminate virus types based on gene expression.

Abstract

Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.