Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. In particular, it encodes molecules as numerical vectors preserving the molecular structures and features, on top of which the downstream tasks (e.g., property prediction) can be performed. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning. In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically, we first introduce the features of 2D and 3D molecular graphs. Then we summarize and categorize MRL methods into three groups based on their input. Furthermore, we discuss some typical chemical applications supported by MRL. To facilitate studies in this fast-developing area, we also list the benchmarks and commonly used datasets in the paper. Finally, we share our thoughts on future research directions.
@article{arxiv.2207.04869,
title = {Graph-based Molecular Representation Learning},
author = {Zhichun Guo and Kehan Guo and Bozhao Nan and Yijun Tian and Roshni G. Iyer and Yihong Ma and Olaf Wiest and Xiangliang Zhang and Wei Wang and Chuxu Zhang and Nitesh V. Chawla},
journal= {arXiv preprint arXiv:2207.04869},
year = {2023}
}