Molecular graph generation with Graph Neural Networks

TL;DR

This paper presents MG^2N^2, a novel graph neural network-based method for sequential molecular graph generation, improving interpretability and performance in drug candidate design tasks.

Contribution

Introduces a modular, sequential molecular graph generator using graph neural networks that enhances interpretability and generalization in molecule creation.

Findings

Capable of generalizing molecular patterns without overfitting

Outperforms baseline models in unconditional generation tasks

Demonstrates effective modular training and interpretability

Abstract

Drug Discovery is a fundamental and ever-evolving field of research. The design of new candidate molecules requires large amounts of time and money, and computational methods are being increasingly employed to cut these costs. Machine learning methods are ideal for the design of large amounts of potential new candidate molecules, which are naturally represented as graphs. Graph generation is being revolutionized by deep learning methods, and molecular generation is one of its most promising applications. In this paper, we introduce a sequential molecular graph generator based on a set of graph neural network modules, which we call MG^2N^2. At each step, a node or a group of nodes is added to the graph, along with its connections. The modular architecture simplifies the training procedure, also allowing an independent retraining of a single module. Sequentiality and modularity make the generation process interpretable. The use of graph neural networks maximizes the information in input at each generative step, which consists of the subgraph produced during the previous steps. Experiments of unconditional generation on the QM9 and Zinc datasets show that our model is capable of generalizing molecular patterns seen during the training phase, without overfitting. The results indicate that our method is competitive, and outperforms challenging baselines for unconditional generation.