As they carry great potential for modeling complex interactions, graph neural network (GNN)-based methods have been widely used to predict quantum mechanical properties of molecules. Most of the existing methods treat molecules as molecular graphs in which atoms are modeled as nodes. They characterize each atom's chemical environment by modeling its pairwise interactions with other atoms in the molecule. Although these methods achieve a great success, limited amount of works explicitly take many-body interactions, i.e., interactions between three and more atoms, into consideration. In this paper, we introduce a novel graph representation of molecules, heterogeneous molecular graph (HMG) in which nodes and edges are of various types, to model many-body interactions. HMGs have the potential to carry complex geometric information. To leverage the rich information stored in HMGs for chemical prediction problems, we build heterogeneous molecular graph neural networks (HMGNN) on the basis of a neural message passing scheme. HMGNN incorporates global molecule representations and an attention mechanism into the prediction process. The predictions of HMGNN are invariant to translation and rotation of atom coordinates, and permutation of atom indices. Our model achieves state-of-the-art performance in 9 out of 12 tasks on the QM9 dataset.
|Original language||English (US)|
|Title of host publication||Proceedings - 20th IEEE International Conference on Data Mining, ICDM 2020|
|Editors||Claudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||9|
|State||Published - Nov 2020|
|Event||20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy|
Duration: Nov 17 2020 → Nov 20 2020
|Name||Proceedings - IEEE International Conference on Data Mining, ICDM|
|Conference||20th IEEE International Conference on Data Mining, ICDM 2020|
|Period||11/17/20 → 11/20/20|
Bibliographical noteFunding Information:
This work was supported in part by NSF (1447788, 1704074, 1757916, 1834251), Army Research Office (W911NF1810344), Intel Corp, and the Digital Technology Center at the University of Minnesota. Access to research and computing facilities was provided by the Digital Technology Center and the Minnesota Supercomputing Institute. We are grateful to Mingjian Wen for his fruitful comments, corrections and inspiration.
© 2020 IEEE.
- Graph neural networks
- Heterogeneous molecular graphs
- Many-body interactions
- Molecular property prediction