Application of message passing neural networks for molecular property prediction.

Journal: Current opinion in structural biology
Published Date:

Abstract

Accurate molecular property prediction, as one of the classical cheminformatics topics, plays a prominent role in the fields of computer-aided drug design. For instance, property prediction models can be used to quickly screen large molecular libraries to find lead compounds. Message-passing neural networks (MPNNs), a sub-class of Graph neural networks (GNNs), have recently been demonstrated to outperform other deep learning methods on a variety of tasks, including the prediction of molecular characteristics. In this survey, we provide a brief review of the MPNN models and their applications on molecular property prediction.

Authors

  • Miru Tang
    Guangzhou Laboratory, Guangzhou, 510005, Guangdong Province, China; Bioland Laboratory (Guangzhou Regenerative Medicine and Health-Guangdong Laboratory), Guangzhou, 510530, China; State Key Laboratory of Respiratory Disease, Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou, 510530, China.
  • Baiqing Li
    State Key Laboratory of Medicinal Chemical Biology and College of Pharmacy, Tianjin Key Laboratory of Molecular Drug Research, Nankai University, Tianjin 300071, People's Republic of China.
  • Hongming Chen
    Hit Discovery, Discovery Sciences, Innovative Medicines and Early Development Biotech Unit, AstraZeneca R&D Gothenburg, 431 83, Mölndal, Sweden.