Molecular graph generation with Graph Neural Networks

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.

20 pages, 4 figures (2 figures are composed of double images, for a total of 6 images)

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• Statistical mechanics of complex networks
• Auto-Encoding Variational Bayes
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Categorical Reparameterization with Gumbel-Softmax
• Automatic chemical design using a data-driven continuous representation of molecules
• Variational Graph Auto-Encoders
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• Constrained Graph Variational Autoencoders for Molecule Design
• Syntax-Directed Variational Autoencoder for Structured Data
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• NetGAN: Generating Graphs via Random Walks
• Efficient Graph Generation with Graph Recurrent Attention Networks
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
• Hierarchical Generation of Molecular Graphs using Structural Motifs
• Edge-based sequential graph generation with recurrent neural networks
• Efficient Generation of Structured Objects with Constrained Adversarial Networks
• Graph Deconvolutional Generation

Cited by in corpus (12)

• Graph Neural Networks for Molecules
• Unnoticeable Backdoor Attacks on Graph Neural Networks
• Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
• Label-Wise Graph Convolutional Network for Heterophilic Graphs
• Bayesian Graph Neural Network for Fast identification of critical nodes in Uncertain Complex Networks
• Unveiling Molecular Moieties through Hierarchical Grad-CAM Graph Explainability
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• Scalable Graph Neural Network-based framework for identifying critical nodes and links in Complex Networks
• Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
• Projection-based model-order reduction via graph autoencoders suited for unstructured meshes
• AIRES: Accelerating Out-of-Core GCNs via Algorithm-System Co-Design
• Towards Self-Explainable Graph Neural Network