Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties

被引:50
作者
Shui, Zeren [1 ]
Karypis, George [1 ]
机构
[1] Univ Minnesota, Comp Sci & Engn, Minneapolis, MN 55455 USA
来源
20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020) | 2020年
关键词
Heterogeneous molecular graphs; many-body interactions; graph neural networks; molecular property prediction;
D O I
10.1109/ICDM50108.2020.00058
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:492 / 500
页数:9
相关论文
共 34 条
[1]  
Anderson B, 2019, ADV NEUR IN, V32
[2]  
[Anonymous], 2018, ARXIV180603146
[3]  
[Anonymous], 1980, HORIZONS QUANTUM CHE
[4]   Machine learning unifies the modeling of materials and molecules [J].
Bartok, Albert P. ;
De, Sandip ;
Poelking, Carl ;
Bernstein, Noam ;
Kermode, James R. ;
Csanyi, Gabor ;
Ceriotti, Michele .
SCIENCE ADVANCES, 2017, 3 (12)
[5]  
Cohen TS, 2016, PR MACH LEARN RES, V48
[6]   MANY-BODY EFFECTS IN INTERMOLECULAR FORCES [J].
ELROD, MJ ;
SAYKALLY, RJ .
CHEMICAL REVIEWS, 1994, 94 (07) :1975-1997
[7]  
Faber FA, 2017, ARXIV170205532
[8]  
Gilmer J, 2017, PR MACH LEARN RES, V70
[9]  
Glorot X., 2010, P INT C ART INT STAT, P249
[10]  
Hamilton WL, 2017, ADV NEUR IN, V30