A graph representation of molecular ensembles for polymer property prediction

Abstract

Synthetic polymers are versatile and widely used materials. Similar to small organic molecules, a large chemical space of such materials is hypothetically accessible. Computational property prediction and virtual screening can accelerate polymer design by prioritizing candidates expected to have favorable properties. However, in contrast to organic molecules, polymers are often not well-defined single structures but an ensemble of similar molecules, which poses unique challenges to traditional chemical representations and machine learning approaches. Here, we introduce a graph representation of molecular ensembles and an associated graph neural network architecture that is tailored to polymer property prediction. We demonstrate that this approach captures critical features of polymeric materials, like chain architecture, monomer stoichiometry, and degree of polymerization, and achieves superior accuracy to off-the-shelf cheminformatics methodologies. While doing so, we built a dataset of simulated electron affinity and ionization potential values for >40k polymers with varying monomer composition, stoichiometry, and chain architecture, which may be used in the development of other tailored machine learning approaches. The dataset and machine learning models presented in this work pave the path toward new classes of algorithms for polymer informatics and, more broadly, introduce a framework for the modeling of molecular ensembles.

arXiv comment17 pages, 5 figures, 1 table (SI with 12 pages, 3 figures, 2 tables)

References in corpus (9)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Uncovering electron scattering mechanisms in NiFeCoCrMn derived concentrated solid solution and high entropy alloys
• Polymer Informatics: Current Status and Critical Next Steps
• Machine learning on DNA-encoded libraries: A new paradigm for hit-finding
• Polymer Informatics with Multi-Task Learning
• Message-passing neural networks for high-throughput polymer screening
• Copolymer Informatics with Multi-Task Deep Neural Networks
• Potentials and challenges of polymer informatics: exploiting machine learning for polymer design

Cited by in corpus (3)

• polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
• TransPolymer: a Transformer-based language model for polymer property predictions
• Polymer informatics at-scale with multitask graph neural networks