Multi-view spectral graph convolution with consistent edge attention for molecular modeling

Although graph convolutional networks (GCNs) that extend the convolution operation from images to graphs have led to competitive performance, the existing GCNs are still difficult to handle a variety of applications, especially cheminformatics problems. Recently multiple GCNs are applied to chemical compound structures which are represented by the hydrogen-depleted molecular graphs of different size. GCNs built for a binary adjacency matrix that reflects the connectivity among nodes in a graph do not account for the edge consistency in multiple molecular graphs, that is, chemical bonds (edges) in different molecular graphs can be similar due to the similar enthalpy and interatomic distance. In this paper, we propose a variant of GCN where a molecular graph is first decomposed into multiple views of the graph, each comprising a specific type of edges. In each view, an edge consistency constraint is enforced so that similar edges in different graphs can receive similar attention weights when passing information. Similarly to prior work, we prove that in each layer, our method corresponds to a spectral filter derived by the first order Chebyshev approximation of graph Laplacian. Extensive experiments demonstrate the substantial advantages of the proposed technique in quantitative structure-activity relationship prediction. (c) 2021 Published by Elsevier B.V.

Automated summary

Despite the competitive performance of graph convolutional networks (GCNs) extending the convolution operation from images to graphs, current GCNs struggle with a variety of applications, particularly cheminformatics problems. Recent applications of multiple GCNs to chemical compound structures have revealed the need to consider edge consistency among nodes in different molecular graphs to accurately reflect the chemical bonds and similarities. The proposed variant of GCN decomposes molecular graphs into multiple views, enforcing edge consistency constraints to ensure similar attention weights for similar edges in different graphs during information propagation.