Molecular Graph Generation via Geometric Scattering

TL;DR

This paper introduces a novel method for molecular graph generation that leverages geometric scattering transforms and generative adversarial networks to produce valid, optimized molecules efficiently, overcoming limitations of traditional GNNs and sequential generation methods.

Contribution

The authors propose a representation-first approach using geometric scattering transforms and GANs for direct molecular graph generation, improving validity and property optimization.

Findings

Learned meaningful representations of drug datasets

Generated valid molecules with optimized properties

Provided a platform for goal-directed drug synthesis

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.