Communications Chemistry (Feb 2023)

Hierarchical Molecular Graph Self-Supervised Learning for property prediction

  • Xuan Zang,
  • Xianbing Zhao,
  • Buzhou Tang

DOI
https://doi.org/10.1038/s42004-023-00825-5
Journal volume & issue
Vol. 6, no. 1
pp. 1 – 10

Abstract

Read online

Graph Neural Networks are employed to encode molecular graph representations, but structural information and chemical functions are largely missing. Here, the authors develop hierarchical molecular graph self-supervised learning as a framework to learn molecule representation for property prediction.