Inverse Design of Copolymers Including Stoichiometry and Chain Architecture

TL;DR

This paper introduces a novel machine learning approach using a variational autoencoder to generate and optimize complex copolymer structures, including stoichiometry and chain architecture, for targeted properties like photocatalytic activity.

Contribution

It develops a semi-supervised VAE model that encodes copolymer structures into a continuous latent space, enabling de-novo design and inverse optimization of complex polymers.

Findings

Successfully generated diverse copolymer structures with specified properties.

Demonstrated inverse design for photocatalyst discovery.

Created a well-organized latent space for polymer design.

Abstract

The demand for innovative synthetic polymers with improved properties is high, but their structural complexity and vast design space hinder rapid discovery. Machine learning-guided molecular design is a promising approach to accelerate polymer discovery. However, the scarcity of labeled polymer data and the complex hierarchical structure of synthetic polymers make generative design particularly challenging. We advance the current state-of-the-art approaches to generate not only repeating units, but monomer ensembles including their stoichiometry and chain architecture. We build upon a recent polymer representation that includes stoichiometries and chain architectures of monomer ensembles and develop a novel variational autoencoder (VAE) architecture encoding a graph and decoding a string. Using a semi-supervised setup, we enable the handling of partly labelled datasets which can be benefitial for domains with a small corpus of labelled data. Our model learns a continuous, well organized latent space (LS) that enables de-novo generation of copolymer structures including different monomer stoichiometries and chain architectures. In an inverse design case study, we demonstrate our model for in-silico discovery of novel conjugated copolymer photocatalysts for hydrogen production using optimization of the polymer's electron affinity and ionization potential in the latent space.