Polymer informatics at-scale with multitask graph neural networks

TL;DR

This paper introduces a graph neural network-based multitask learning approach that rapidly predicts polymer properties, significantly reducing feature extraction time compared to traditional handcrafted methods, thereby enabling large-scale polymer screening.

Contribution

The authors develop a scalable, machine-learning-based method for polymer property prediction that bypasses manual feature extraction, improving speed without sacrificing accuracy.

Findings

Speeds up feature extraction by 10-100 times.

Maintains high accuracy across various polymer property predictions.

Enables screening of massive polymer libraries at scale.

Abstract

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer screening rely on handcrafted chemostructural features extracted from polymer repeat units -- a burdensome task as polymer libraries, which approximate the polymer chemical search space, progressively grow over time. Here, we demonstrate that directly "machine-learning" important features from a polymer repeat unit is a cheap and viable alternative to extracting expensive features by hand. Our approach -- based on graph neural networks, multitask learning, and other advanced deep learning techniques -- speeds up feature extraction by one to two orders of magnitude relative to presently adopted handcrafted methods without compromising model accuracy for a variety of polymer property prediction tasks. We anticipate that our approach, which unlocks the screening of truly massive polymer libraries at scale, will enable more sophisticated and large scale screening technologies in the field of polymer informatics.