Automatic chemical design using a data-driven continuous representation of molecules

TL;DR

This paper introduces a neural network-based method to convert molecules into a continuous space, enabling efficient generation, exploration, and optimization of chemical compounds for drug discovery and small molecules.

Contribution

The authors develop a deep learning model that maps molecules to and from a continuous latent space, facilitating novel molecule generation and property optimization.

Findings

Generated new molecules by sampling and perturbing in latent space.

Enabled gradient-based optimization for molecule property improvement.

Demonstrated effectiveness on drug-like and small molecules.

Abstract

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in the set of molecules with fewer that nine heavy atoms.