Molecular Graph Generation via Geometric Scattering

Abstract

Graph neural networks (GNNs) have been used extensively for addressing problems in drug design and discovery. Both ligand and target molecules are represented as graphs with node and edge features encoding information about atomic elements and bonds respectively. Although existing deep learning models perform remarkably well at predicting physicochemical properties and binding affinities, the generation of new molecules with optimized properties remains challenging. Inherently, most GNNs perform poorly in whole-graph representation due to the limitations of the message-passing paradigm. Furthermore, step-by-step graph generation frameworks that use reinforcement learning or other sequential processing can be slow and result in a high proportion of invalid molecules with substantial post-processing needed in order to satisfy the principles of stoichiometry. To address these issues, we propose a representation-first approach to molecular graph generation. We guide the latent representation of an autoencoder by capturing graph structure information with the geometric scattering transform and apply penalties that structure the representation also by molecular properties. We show that this highly structured latent space can be directly used for molecular graph generation by the use of a GAN. We demonstrate that our architecture learns meaningful representations of drug datasets and provides a platform for goal-directed drug synthesis.

Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks

“…In [12], [14], [21], [22], extensive theoretical studies of these networks show that they have desirable stability, invariance, and conservation of energy properties. The practical utility of these networks has been established in [13], which primarily focuses on graph classification, and in [23], [24], [25], which used the graph scattering transform to generate molecules. Building off of these results, which use handcrafted formulations of the scattering transform, recent work [26] has proposed a framework for a datadriven tuning of the traditionally handcrafted geometric scattering design that maintains the theoretical properties from traditional designs, while also showing strong empirical results in whole-graph settings.…”