A Two-Step Graph Convolutional Decoder for Molecule Generation

Abstract

We propose a simple auto-encoder framework for molecule generation. The molecular graph is first encoded into a continuous latent representation $z$, which is then decoded back to a molecule. The encoding process is easy, but the decoding process remains challenging. In this work, we introduce a simple two-step decoding process. In a first step, a fully connected neural network uses the latent vector $z$ to produce a molecular formula, for example CO${}_2$ (one carbon and two oxygen atoms). In a second step, a graph convolutional neural network uses the same latent vector $z$ to place bonds between the atoms that were produced in the first step (for example a double bond will be placed between the carbon and each of the oxygens). This two-step process, in which a bag of atoms is first generated, and then assembled, provides a simple framework that allows us to develop an efficient molecule auto-encoder. Numerical experiments on basic tasks such as novelty, uniqueness, validity and optimized chemical property for the 250k ZINC molecules demonstrate the performances of the proposed system. Particularly, we achieve the highest reconstruction rate of 90.5\%, improving the previous rate of 76.7\%. We also report the best property improvement results when optimization is constrained by the molecular distance between the original and generated molecules.

References in corpus (8)

• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• Gated Graph Sequence Neural Networks
• Residual Gated Graph ConvNets
• Syntax-Directed Variational Autoencoder for Structured Data

Cited by in corpus (13)

• Benchmarking Graph Neural Networks
• A Survey of Deep Learning for Scientific Discovery
• Graph Representation Learning via Graphical Mutual Information Maximization
• Study of Deep Generative Models for Inorganic Chemical Compositions
• A pipeline for fair comparison of graph neural networks in node classification tasks
• Graph Mixture Density Networks
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
• Top-N: Equivariant set and graph generation without exchangeability
• Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks
• Molecular modeling with machine-learned universal potential functions
• Edge but not Least: Cross-View Graph Pooling
• Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining